1
|
Zhu S, Sang H, Zhang K, Kong F, Lu J. Synchronization of Intermittently Coupled Neural Networks With Coupling Delay. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025; 36:7984-7996. [PMID: 39042550 DOI: 10.1109/tnnls.2024.3426672] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/25/2024]
Abstract
In recent years, the synchronization of coupled neural networks (CNNs) has been extensively studied. However, existing results heavily rely on assuming continuous couplings, overlooking the prevalence of intermittent couplings in reality. In this article, we address for the first time the synchronization challenge posed by intermittently CNNs (ICNNs) with coupling delay. To overcome the difficulties arising from intermittent couplings, we put forward a general piecewise delay differential inequality to characterize the dynamics during both coupled intervals and decoupled intervals. Based on the proposed inequality, we establish delay-independent synchronization criteria (DISCs) for ICNNs, enabling them to tackle general coupling delay. Notably, unlike previous studies, the achievement of synchronization in our approach does not rely on external control. Furthermore, for ICNNs that synchronize only under small delays, we formulate non-linear matrix inequality (LMI)-based delay-dependent synchronization criteria (DDSCs) that are computationally efficient and do not require delay differentiability. Finally, we provide illustrative examples to demonstrate our theoretical results.
Collapse
|
2
|
He R, Cao J, Tan T. Generative artificial intelligence: a historical perspective. Natl Sci Rev 2025; 12:nwaf050. [PMID: 40191253 PMCID: PMC11970245 DOI: 10.1093/nsr/nwaf050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2024] [Revised: 02/05/2025] [Accepted: 02/09/2025] [Indexed: 04/09/2025] Open
Abstract
Generative artificial intelligence (GAI) has recently achieved significant success, enabling anyone to create texts, images, videos and even computer codes while providing insights that might not be possible with traditional tools. To stimulate future research, this work provides a brief summary of the ongoing and historical developments in GAI over the past 70 years. The achievements are grouped into four categories: (i) rule-based generative systems that follow specialized rules and instructions, (ii) model-based generative algorithms that produce new content based on statistical or graphical models, (iii) deep generative methodologies that utilize deep neural networks to learn how to generate new content from data and (iv) foundation models that are trained on extensive datasets and capable of performing a variety of generative tasks. This paper also reviews successful generative applications and identifies open challenges posed by remaining issues. In addition, this paper describes potential research directions aimed at better utilizing, understanding and harnessing GAI technologies.
Collapse
Affiliation(s)
- Ran He
- New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
- School of Intelligence Science and Technology, Nanjing University, Nanjing 210008, China
| | - Jie Cao
- New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Tieniu Tan
- New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
- School of Intelligence Science and Technology, Nanjing University, Nanjing 210008, China
| |
Collapse
|
3
|
Ming C, Lee GJ, Teo YN, Teo YH, Zhou X, Ho ES, Toh EM, Ong MEH, Tan BY, Ho AF. Deep learning modelling to forecast emergency department visits using calendar, meteorological, internet search data and stock market price. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025; 267:108808. [PMID: 40315688 DOI: 10.1016/j.cmpb.2025.108808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/16/2024] [Revised: 02/26/2025] [Accepted: 04/23/2025] [Indexed: 05/04/2025]
Abstract
BACKGROUND Accurate prediction of hospital emergency department (ED) patient visits and acuity levels have potential to improve resource allocation including manpower planning and hospital bed allocation. Internet search data have been used in medical applications like disease pattern prediction and forecasting ED volume. Past studies have also found stock market price positively correlated with ED volume. OBJECTIVE To determine whether incorporating Internet search data and stock market price to calendar and meteorological data can improve deep learning prediction of ED patient volumes, and whether hybrid deep learning architectures are better in prediction. METHODS Permutations of various input variables namely calendar, meteorological, Google Trends online search data, Standard and Poor's (S&P) 500 index, and Straits Times Index (STI) data were incorporated into deep learning models long short-term memory (LSTM), one-dimensional convolutional neural network (1D CNN), stacked 1D CNN-LSTM, and five CNN-LSTM hybrid modules to predict daily Singapore General Hospital ED patient volume from 2010-2012. RESULTS Incorporating STI to calendar and meteorological data improved performance of CNN-LSTM hybrid models. Addition of queried absolute Google Trends search terms to calendar and meteorological data improved performance of two out of five hybrid models. The best LSTM model across all predictor permutations had mean absolute percentage error of 4.8672 %. CONCLUSION LSTM provides strong predictive ability for daily ED patient volume. Local stock market index has potential to predict ED visits. Amongst predictors evaluated, calendar and meteorological data was sufficient for a relatively accurate prediction.
Collapse
Affiliation(s)
- Chua Ming
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Geraldine Jw Lee
- Department of Statistics and Data Science, Faculty of Science, National University of Singapore, Singapore
| | - Yao Neng Teo
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Yao Hao Teo
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Xinyan Zhou
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Elizabeth Sy Ho
- Department of Computer Science and Technology, University of Cambridge, United Kingdom
| | - Emma Ms Toh
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Marcus Eng Hock Ong
- Department of Emergency Medicine, Singapore General Hospital, Singapore; Health Services and Systems Research, Duke-NUS Medical School, Singapore
| | - Benjamin Yq Tan
- Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Division of Neurology, Department of Medicine, National University Hospital, Singapore
| | - Andrew Fw Ho
- Department of Emergency Medicine, Singapore General Hospital, Singapore; Pre-Hospital and Emergency Research Centre, Duke-NUS Medical School, Singapore.
| |
Collapse
|
4
|
Mao M, Hong M. YOLO Object Detection for Real-Time Fabric Defect Inspection in the Textile Industry: A Review of YOLOv1 to YOLOv11. SENSORS (BASEL, SWITZERLAND) 2025; 25:2270. [PMID: 40218782 PMCID: PMC11990965 DOI: 10.3390/s25072270] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/12/2025] [Revised: 04/01/2025] [Accepted: 04/02/2025] [Indexed: 04/14/2025]
Abstract
Automated fabric defect detection is crucial for improving quality control, reducing manual labor, and optimizing efficiency in the textile industry. Traditional inspection methods rely heavily on human oversight, which makes them prone to subjectivity, inefficiency, and inconsistency in high-speed manufacturing environments. This review systematically examines the evolution of the You Only Look Once (YOLO) object detection framework from YOLO-v1 to YOLO-v11, emphasizing architectural advancements such as attention-based feature refinement and Transformer integration and their impact on fabric defect detection. Unlike prior studies focusing on specific YOLO variants, this work comprehensively compares the entire YOLO family, highlighting key innovations and their practical implications. We also discuss the challenges, including dataset limitations, domain generalization, and computational constraints, proposing future solutions such as synthetic data generation, federated learning, and edge AI deployment. By bridging the gap between academic advancements and industrial applications, this review is a practical guide for selecting and optimizing YOLO models for fabric inspection, paving the way for intelligent quality control systems.
Collapse
Affiliation(s)
- Makara Mao
- Department of Software Convergence, Soonchunhyang University, Asan-si 31538, Republic of Korea;
| | - Min Hong
- Department of Computer Software Engineering, Soonchunhyang University, Asan-si 31538, Republic of Korea
| |
Collapse
|
5
|
Janse RJ, Abu-Hanna A, Vagliano I, Stel VS, Jager KJ, Tripepi G, Zoccali C, Dekker FW, van Diepen M. When the whole is greater than the sum of its parts: why machine learning and conventional statistics are complementary for predicting future health outcomes. Clin Kidney J 2025; 18:sfaf059. [PMID: 40276681 PMCID: PMC12019231 DOI: 10.1093/ckj/sfaf059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2024] [Indexed: 04/26/2025] Open
Abstract
An artificial intelligence boom is currently ongoing, mainly due to large language models, leading to significant interest in artificial intelligence and subsequently also in machine learning (ML). One area where ML is often applied, prediction modelling, has also long been a focus of conventional statistics. As a result, multiple studies have aimed to prove superiority of one of the two scientific disciplines over the other. However, we argue that ML and conventional statistics should not be competing fields. Instead, both fields are intertwined and complementary to each other. To illustrate this, we discuss some essentials of prediction modelling, elaborate on prediction modelling using techniques from conventional statistics, and explain prediction modelling using common ML techniques such as support vector machines, random forests, and artificial neural networks. We then showcase that conventional statistics and ML are in fact similar in many aspects, including underlying statistical concepts and methods used in model development and validation. Finally, we argue that conventional statistics and ML can and should be seen as a single integrated field. This integration can further improve prediction modelling for both disciplines (e.g. regarding fairness and reporting standards) and will support the ultimate goal: developing the best performing prediction models for the patient and healthcare provider.
Collapse
Affiliation(s)
- Roemer J Janse
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, the Netherlands
| | - Ameen Abu-Hanna
- Department of Medical Informatics, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
- Amsterdam Public Health Research Institute, Methodology, Amsterdam, the Netherlands
| | - Iacopo Vagliano
- Department of Medical Informatics, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
- Amsterdam Public Health Research Institute, Methodology, Amsterdam, the Netherlands
| | - Vianda S Stel
- ERA Registry, Department of Medical Informatics, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
- Amsterdam Public Health Research Institute, Quality of Care, Amsterdam, the Netherlands
| | - Kitty J Jager
- ERA Registry, Department of Medical Informatics, Amsterdam UMC location University of Amsterdam, Amsterdam, the Netherlands
- Amsterdam Public Health Research Institute, Quality of Care, Amsterdam, the Netherlands
| | - Giovanni Tripepi
- CNR-IFC, Clinical Epidemiology and Physiopathology of Renal Diseases and Hypertension, Reggio Calabria, Italy
| | - Carmine Zoccali
- CNR-IFC, Clinical Epidemiology and Physiopathology of Renal Diseases and Hypertension, Reggio Calabria, Italy
| | - Friedo W Dekker
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, the Netherlands
| | - Merel van Diepen
- Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, the Netherlands
| |
Collapse
|
6
|
Mohammadiazni M, Alfaro JGC, Trejos AL. Mitigate the Effect of Arm Posture on Electromyography Pattern Recognition. IEEE J Biomed Health Inform 2025; 29:2413-2424. [PMID: 40030701 DOI: 10.1109/jbhi.2024.3518978] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/05/2025]
Abstract
The real-time use of electromyography (EMG)-based mechatronic rehabilitation devices aiming to detect stroke patients' hand grasping intention is hindered by a significant concern: the lack of robustness against variations in EMG signal patterns due to arm posture changes. This problem results in degraded EMG signal measurements and inaccurate recognition of muscle patterns. Several studies have aimed at tracking changes in EMG patterns by placing multiple EMG sensors around the forearm and developing a classifier using data collected from various arm postures recorded by all sensors. Although these methods show promise, the significant computational resources required for real-time data processing become notable concerns when using multiple EMG sensors. To address these challenges, this study introduces a novel approach that aims to reduce the number of EMG channels that need to be processed. The study proposes a new optimal-channel-selection technique, coupled with a convolutional neural network (CNN), which selects two out of eight EMG channels within an armband based on the arm posture and individual demographics. As a result of using only two channels rather than the entire array (eight channels), the user's grasping intention prediction time took only 2.3 seconds with a classification accuracy of around 81%. In comparison, the commonly used eight-channel method took 8.6 seconds for grasping intention detection with an accuracy level of 79%. These findings show potential in tackling the challenge of EMG measurement degradation caused by arm motion, offering a path towards enhanced accuracy and quicker responsiveness in EMG-based mechatronic rehabilitation devices.
Collapse
|
7
|
Casile A, Cordier A, Kim JG, Cometa A, Madsen JR, Stone S, Ben-Yosef G, Ullman S, Anderson W, Kreiman G. Neural correlates of minimal recognizable configurations in the human brain. Cell Rep 2025; 44:115429. [PMID: 40096088 PMCID: PMC12045337 DOI: 10.1016/j.celrep.2025.115429] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 07/24/2024] [Accepted: 02/21/2025] [Indexed: 03/19/2025] Open
Abstract
Inferring object identity from incomplete information is a ubiquitous challenge for the visual system. Here, we study the neural mechanisms underlying processing of minimally recognizable configurations (MIRCs) and their subparts, which are unrecognizable (sub-MIRCs). MIRCs and sub-MIRCs are very similar at the pixel level, yet they lead to a dramatic gap in recognition performance. To evaluate how the brain processes such images, we invasively record human neurophysiological responses. Correct identification of MIRCs is associated with a dynamic interplay of feedback and feedforward mechanisms between frontal and temporal areas. Interpretation of sub-MIRC images improves dramatically after exposure to the corresponding full objects. This rapid and unsupervised learning is accompanied by changes in neural responses in the temporal cortex. These results are at odds with purely feedforward models of object recognition and suggest a role for the frontal lobe in providing top-down signals related to object identity in difficult visual tasks.
Collapse
Affiliation(s)
- Antonino Casile
- Department of Biomedical and Dental Sciences and Morphofunctional Imaging, University of Messina, 98122 Messina, Italy
| | - Aurelie Cordier
- Children's Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Jiye G Kim
- Children's Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Andrea Cometa
- MoMiLab, IMT School for Advanced Studies, 55100 Lucca, Italy
| | - Joseph R Madsen
- Children's Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Scellig Stone
- Children's Hospital, Harvard Medical School, Boston, MA 02115, USA
| | | | - Shimon Ullman
- Weizmann Institute, Rehovot, Israel; Center for Brains, Minds and Machines, Cambridge, MA 02142, USA
| | - William Anderson
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA
| | - Gabriel Kreiman
- Children's Hospital, Harvard Medical School, Boston, MA 02115, USA; Center for Brains, Minds and Machines, Cambridge, MA 02142, USA.
| |
Collapse
|
8
|
Marino R, Buffoni L, Chicchi L, Patti FD, Febbe D, Giambagli L, Fanelli D. Learning in Wilson-Cowan Model for Metapopulation. Neural Comput 2025; 37:701-741. [PMID: 40030137 DOI: 10.1162/neco_a_01744] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2024] [Accepted: 12/05/2024] [Indexed: 03/19/2025]
Abstract
The Wilson-Cowan model for metapopulation, a neural mass network model, treats different subcortical regions of the brain as connected nodes, with connections representing various types of structural, functional, or effective neuronal connectivity between these regions. Each region comprises interacting populations of excitatory and inhibitory cells, consistent with the standard Wilson-Cowan model. In this article, we show how to incorporate stable attractors into such a metapopulation model's dynamics. By doing so, we transform the neural mass network model into a biologically inspired learning algorithm capable of solving different classification tasks. We test it on MNIST and Fashion MNIST in combination with convolutional neural networks, as well as on CIFAR-10 and TF-FLOWERS, and in combination with a transformer architecture (BERT) on IMDB, consistently achieving high classification accuracy.
Collapse
Affiliation(s)
- Raffaele Marino
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy
| | - Lorenzo Buffoni
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy
| | - Lorenzo Chicchi
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy
| | - Francesca Di Patti
- Department of Mathematics and Computer Science, University of Florence, 50134 Florence, Italy
| | - Diego Febbe
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy
| | - Lorenzo Giambagli
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy
| | - Duccio Fanelli
- Department of Physics and Astronomy, University of Florence, 50019 Sesto Fiorentino, Florence, Italy
| |
Collapse
|
9
|
May L, Dauphin A, Gjorgjieva J. Pre-training artificial neural networks with spontaneous retinal activity improves motion prediction in natural scenes. PLoS Comput Biol 2025; 21:e1012830. [PMID: 40096645 DOI: 10.1371/journal.pcbi.1012830] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2024] [Accepted: 01/27/2025] [Indexed: 03/19/2025] Open
Abstract
The ability to process visual stimuli rich with motion represents an essential skill for animal survival and is largely already present at the onset of vision. Although the exact mechanisms underlying its maturation remain elusive, spontaneous activity patterns in the retina, known as retinal waves, have been shown to contribute to this developmental process. Retinal waves exhibit complex spatio-temporal statistics and contribute to the establishment of circuit connectivity and function in the visual system, including the formation of retinotopic maps and the refinement of receptive fields in downstream areas such as the thalamus and visual cortex. Recent work in mice has shown that retinal waves have statistical features matching those of natural visual stimuli, such as optic flow, suggesting that they could prime the visual system for motion processing upon vision onset. Motivated by these findings, we examined whether artificial neural network (ANN) models trained on natural movies show improved performance if pre-trained with retinal waves. We employed the spatio-temporally complex task of next-frame prediction, in which the ANN was trained to predict the next frame based on preceding input frames of a movie. We found that pre-training ANNs with retinal waves enhances the processing of real-world visual stimuli and accelerates learning. Strikingly, when we merely replaced the initial training epochs on naturalistic stimuli with retinal waves, keeping the total training time the same, we still found that an ANN trained on retinal waves temporarily outperforms one trained solely on natural movies. Similar to observations made in biological systems, we also found that pre-training with spontaneous activity refines the receptive field of ANN neurons. Overall, our work sheds light on the functional role of spatio-temporally patterned spontaneous activity in the processing of motion in natural scenes, suggesting it acts as a training signal to prepare the developing visual system for adult visual processing.
Collapse
Affiliation(s)
- Lilly May
- School of Life Sciences, Technical University of Munich, Freising, Germany
| | - Alice Dauphin
- School of Life Sciences, Technical University of Munich, Freising, Germany
- Institute of Machine Learning and Neural Computation, Graz University of Technology, Graz, Austria
| | | |
Collapse
|
10
|
Mostafavi M, Ko SB, Shokouhi SB, Ayatollahi A. Transfer learning and self-distillation for automated detection of schizophrenia using single-channel EEG and scalogram images. Phys Eng Sci Med 2025; 48:3-18. [PMID: 38652347 DOI: 10.1007/s13246-024-01420-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Accepted: 03/25/2024] [Indexed: 04/25/2024]
Abstract
Schizophrenia (SZ) has been acknowledged as a highly intricate mental disorder for a long time. In fact, individuals with SZ experience a blurred line between fantasy and reality, leading to a lack of awareness about their condition, which can pose significant challenges during the treatment process. Due to the importance of the issue, timely diagnosis of this illness can not only assist patients and their families in managing the condition but also enable early intervention, which may help prevent its advancement. EEG is a widely utilized technique for investigating mental disorders like SZ due to its non-invasive nature, affordability, and wide accessibility. In this study, our main goal is to develop an optimized system that can achieve automatic diagnosis of SZ with minimal input information. To optimize the system, we adopted a strategy of using single-channel EEG signals and integrated knowledge distillation and transfer learning techniques into the model. This approach was designed to improve the performance and efficiency of our proposed method for SZ diagnosis. Additionally, to leverage the pre-trained models effectively, we converted the EEG signals into images using Continuous Wavelet Transform (CWT). This transformation allowed us to harness the capabilities of pre-trained models in the image domain, enabling automatic SZ detection with enhanced efficiency. To achieve a more robust estimate of the model's performance, we employed fivefold cross-validation. The accuracy achieved from the 5-s records of the EEG signal, along with the combination of self-distillation and VGG16 for the P4 channel, is 97.81. This indicates a high level of accuracy in diagnosing SZ using the proposed method.
Collapse
Affiliation(s)
- Mohammadreza Mostafavi
- Department of Electrical Engineering, Electronic Engineering, Iran University of Science and Technology, Tehran, Iran
| | - Seok-Bum Ko
- Division of Biomedical Engineering, Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada.
| | - Shahriar Baradaran Shokouhi
- Department of Electrical Engineering, Electronic Engineering, Iran University of Science and Technology, Tehran, Iran
| | - Ahmad Ayatollahi
- Department of Electrical Engineering, Electronic Engineering, Iran University of Science and Technology, Tehran, Iran
| |
Collapse
|
11
|
Arslan B, Nuhoglu C, Satici MO, Altinbilek E. Evaluating LLM-based generative AI tools in emergency triage: A comparative study of ChatGPT Plus, Copilot Pro, and triage nurses. Am J Emerg Med 2025; 89:174-181. [PMID: 39731895 DOI: 10.1016/j.ajem.2024.12.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2024] [Revised: 11/08/2024] [Accepted: 12/09/2024] [Indexed: 12/30/2024] Open
Abstract
BACKGROUND The number of emergency department (ED) visits has been on steady increase globally. Artificial Intelligence (AI) technologies, including Large Language Model (LLMs)-based generative AI models, have shown promise in improving triage accuracy. This study evaluates the performance of ChatGPT and Copilot in triage at a high-volume urban hospital, hypothesizing that these tools can match trained physicians' accuracy and reduce human bias amidst ED crowding challenges. METHODS This single-center, prospective observational study was conducted in an urban ED over one week. Adult patients were enrolled through random 24-h intervals. Exclusions included minors, trauma cases, and incomplete data. Triage nurses assessed patients while an emergency medicine (EM) physician documented clinical vignettes and assigned emergency severity index (ESI) levels. These vignettes were then introduced to ChatGPT and Copilot for comparison with the triage nurse's decision. RESULTS The overall triage accuracy was 65.2 % for nurses, 66.5 % for ChatGPT, and 61.8 % for Copilot, with no significant difference (p = 0.000). Moderate agreement was observed between the EM physician and ChatGPT, triage nurses, and Copilot (Cohen's Kappa = 0.537, 0.477, and 0.472, respectively). In recognizing high-acuity patients, ChatGPT and Copilot outperformed triage nurses (87.8 % and 85.7 % versus 32.7 %, respectively). Compared to ChatGPT and Copilot, nurses significantly under-triaged patients (p < 0.05). The analysis of predictive performance for ChatGPT, Copilot, and triage nurses demonstrated varying discrimination abilities across ESI levels, all of which were statistically significant (p < 0.05). ChatGPT and Copilot exhibited consistent accuracy across age, gender, and admission time, whereas triage nurses were more likely to mistriage patients under 45 years old. CONCLUSION ChatGPT and Copilot outperform traditional nurse triage in identifying high-acuity patients, but real-time ED capacity data is crucial to prevent overcrowding and ensure high-quality of emergency care.
Collapse
Affiliation(s)
- B Arslan
- Department of Emergency Medicine, Sisli Hamidiye Etfal Training and Research Hospital, Istanbul, Turkey.
| | - C Nuhoglu
- Department of Emergency Medicine, Sisli Hamidiye Etfal Training and Research Hospital, Istanbul, Turkey
| | - M O Satici
- Department of Emergency Medicine, Sisli Hamidiye Etfal Training and Research Hospital, Istanbul, Turkey
| | - E Altinbilek
- Department of Emergency Medicine, Sisli Hamidiye Etfal Training and Research Hospital, Istanbul, Turkey
| |
Collapse
|
12
|
Ye Z, Ai Q, Liu Y, de Rijke M, Zhang M, Lioma C, Ruotsalo T. Generative language reconstruction from brain recordings. Commun Biol 2025; 8:346. [PMID: 40025160 PMCID: PMC11873242 DOI: 10.1038/s42003-025-07731-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2024] [Accepted: 02/12/2025] [Indexed: 03/04/2025] Open
Abstract
Language reconstruction from non-invasive brain recordings has been a long-standing challenge. Existing research has addressed this challenge with a classification setup, where a set of language candidates are pre-constructed and then matched with the representation decoded from brain recordings. Here, we propose a method that addresses language reconstruction through auto-regressive generation, which directly uses the representation decoded from functional magnetic resonance imaging (fMRI) as the input for a large language model (LLM), mitigating the need for pre-constructed candidates. While an LLM can already generate high-quality content, our approach produces results more closely aligned with the visual or auditory language stimuli in response to which brain recordings are sampled, especially for content deemed "surprising" for the LLM. Furthermore, we show that the proposed approach can be used in an auto-regressive manner to reconstruct a 10 min-long language stimulus. Our method outperforms or is comparable to previous classification-based methods under different task settings, with the added benefit of estimating the likelihood of generating any semantic content. Our findings demonstrate the effectiveness of employing brain language interfaces in a generative setup and delineate a powerful and efficient means for mapping functional representations of language perception in the brain.
Collapse
Affiliation(s)
- Ziyi Ye
- Tsinghua University, Beijing, China
| | | | - Yiqun Liu
- Tsinghua University, Beijing, China.
| | | | | | | | - Tuukka Ruotsalo
- University of Copenhagen, Copenhagen, Denmark
- Lappeenranta-Lahti University of Technology, Lappeenranta, Finland
| |
Collapse
|
13
|
Gan Y, Lan Q, Huang C, Su W, Huang Z. Dense convolution-based attention network for Alzheimer's disease classification. Sci Rep 2025; 15:5693. [PMID: 39962113 PMCID: PMC11832751 DOI: 10.1038/s41598-025-85802-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2024] [Accepted: 01/06/2025] [Indexed: 02/20/2025] Open
Abstract
Recently, deep learning-based medical image classification models have made substantial advancements. However, many existing models prioritize performance at the cost of efficiency, limiting their practicality in clinical use. Traditional Convolutional Neural Network (CNN)-based methods, Transformer-based methods, and hybrid approaches combining these two struggle to balance performance and model complexity. To achieve efficient predictions with a low parameter count, we propose DenseAttentionNetwork (DANet), a lightweight model for Alzheimer's disease detection in 3D MRI images. DANet leverages dense connections and a linear attention mechanism to enhance feature extraction and capture long-range dependencies. Its architecture integrates convolutional layers for localized feature extraction with linear attention for global context, enabling efficient multi-scale feature reuse across the network. By replacing traditional self-attention with a parameter-efficient linear attention mechanism, DANet overcomes some limitations of standard self-attention. Extensive experiments across multi-institutional datasets demonstrate that DANet achieves the best performance in area under the receiver operating characteristic curve (AUC), which underscores the model's robustness and effectiveness in capturing relevant features for Alzheimer's disease detection while also attaining a strong accuracy structure with fewer parameters. Visualizations based on activation maps further verify the model's ability to highlight AD-relevant regions in 3D MRI images, providing clinically interpretable insights into disease progression.
Collapse
Affiliation(s)
- Yingtong Gan
- Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, 361005, People's Republic of China
- Institute of Artifical Intelligence, Xiamen University, Xiamen, 361005, People's Republic of China
| | - Quan Lan
- Department of Neurology, First Affiliated Hospital of Xiamen University, Xiamen, 361003, People's Republic of China
| | - ChenXi Huang
- Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, 361005, People's Republic of China.
| | - Weichao Su
- Xiamen Xianyue Hospital, Xianyue Hospital Affiliated with Xiamen Medical College, Fujian Psychiatric Center, Fujian Clinical Research Center for Mental Disorders, Xiamen, 361012, People's Republic of China.
| | - Zhiyuan Huang
- The School of Clinical Medicine, Fujian Medical University, Fuzhou, 350122, People's Republic of China.
- Xiamen Xianyue Hospital, Xianyue Hospital Affiliated with Xiamen Medical College, Fujian Psychiatric Center, Fujian Clinical Research Center for Mental Disorders, Xiamen, 361012, People's Republic of China.
| |
Collapse
|
14
|
McVeigh K, Singh A, Erdogmus D, Feldman Barrett L, Satpute AB. Using deep generative models for simultaneous representational and predictive modeling of brain and behavior: A graded unsupervised-to-supervised modeling framework. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2025:2024.12.23.630166. [PMID: 39990349 PMCID: PMC11844378 DOI: 10.1101/2024.12.23.630166] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/25/2025]
Abstract
This paper uses a generative neural network architecture combining unsupervised (generative) and supervised (discriminative) models with a model comparison strategy to evaluate assumptions about the mappings between brain states and behavior. Most modeling in cognitive neuroscience publications assume a one-to-one brain-behavior relationship that is linear, but never test these assumptions or the consequences of violating them. We systematically varied these assumptions using simulations of four ground-truth brain-behavior mappings that involve progressively more complex relationships, ranging from one-to-one linear mappings to many-to-one nonlinear mappings. We then applied our Variational AutoEncoder-Classifier framework to the simulations to show how it accurately captured diverse brain-behavior mappings,provided evidence regarding which assumptions are supported by the data, and illustrated the problems that arise when assumptions are violated. This integrated approach offers a reliable foundation for cognitive neuroscience to effectively model complex neural and behavioral processes, allowing more justified conclusions about the nature of brain-behavior mappings.
Collapse
|
15
|
Chen S, Sakai S, Matsuo-Ueda M, Umemura K. Investigation of multi-input convolutional neural networks for the prediction of particleboard mechanical properties. Sci Rep 2025; 15:4162. [PMID: 39905184 PMCID: PMC11794689 DOI: 10.1038/s41598-025-88301-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2024] [Accepted: 01/28/2025] [Indexed: 02/06/2025] Open
Abstract
This study explored the potential of building an image-based quality control system for particleboard manufacturing. Single-layer particleboards were manufactured under 27 operating conditions and their modulus of elasticity (MOE) and the modulus of rupture (MOR) were determined. Subsequently, images of the upper surface, lower surface, and cross-section of each specimen were collected. Two types of convolutional neural networks (CNNs) were designed: a single-input CNN processing one image and a multi-input CNN capable of analyzing multiple images simultaneously. Their prediction accuracies were then compared. Among the single-input CNNs, the cross-sectional image yielded the best prediction accuracy for both the MOE and MOR. For multi-input CNNs, the combination of the upper surface and cross-sectional images produced the highest scores when the model merged the information from each image at early stage, outperforming single-input CNNs. Adding density information to multi-input CNNs significantly improved prediction accuracy for both MOE and MOR, achieving optimal results. Regression activation maps were constructed to visualize the image features that were strongly correlated with the predicted results. For MOE prediction, the precise location of phenol formaldehyde (PF) resin and particle alignment were crucial. For MOR prediction, the interface between particles and PF resin was the key.
Collapse
Affiliation(s)
- Shuoye Chen
- Research Institute for Sustainable Humanosphere, Kyoto University, Gokasho, Uji, 611-0011, Japan.
| | - Shunsuke Sakai
- Research Institute for Sustainable Humanosphere, Kyoto University, Gokasho, Uji, 611-0011, Japan
| | - Miyuki Matsuo-Ueda
- Graduate School of Agriculture, Kyoto University, Kitashirakawa Oiwaka-Cho, Sakyo-Ku, Kyoto, 606-8502, Japan
| | - Kenji Umemura
- Research Institute for Sustainable Humanosphere, Kyoto University, Gokasho, Uji, 611-0011, Japan
| |
Collapse
|
16
|
Stegemüller L, Caccavale F, Valverde-Pérez B, Angelidaki I. Online monitoring of Haematococcus lacustris cell cycle using machine and deep learning techniques. BIORESOURCE TECHNOLOGY 2025; 418:131976. [PMID: 39675638 DOI: 10.1016/j.biortech.2024.131976] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/24/2024] [Revised: 12/07/2024] [Accepted: 12/11/2024] [Indexed: 12/17/2024]
Abstract
Optimal control and process optimization of astaxanthin production from Haematococcuslacustris is directly linked to its complex cell cycle ranging from vegetative green cells to astaxanthin-rich cysts. This study developed an automated online monitoring system classifying four different cell cycle stages using a scanning microscope. Decision-tree based machine learning and deep learning convolutional neural network algorithms were developed, validated, and evaluated. SHapley Additive exPlanations was used to examine the most important system requirements for accurate image classification. The models achieved accuracies on unseen data of 92.4 and 90.9%, respectively. Furthermore, both models were applied to a photobioreactor culturing H.lacustris, effectively monitoring the transition from a green culture in the exponential growth phase to a stationary red culture. Therefore, online image analysis using artificial intelligence models has great potential for process optimization and as a data-driven decision support tool during microalgae cultivation.
Collapse
Affiliation(s)
- Lars Stegemüller
- Department of Chemical Engineering, Technical University of Denmark, DTU, Søltofts Plads 228A, Lyngby 2800, Denmark.
| | - Fiammetta Caccavale
- Department of Chemical Engineering, Technical University of Denmark, DTU, Søltofts Plads 228A, Lyngby 2800, Denmark
| | - Borja Valverde-Pérez
- Department of Environmental and Resource Engineering, Technical University of Denmark, DTU, Bygningstorvet 115, Lyngby 2800, Denmark
| | - Irini Angelidaki
- Department of Chemical Engineering, Technical University of Denmark, DTU, Søltofts Plads 228A, Lyngby 2800, Denmark
| |
Collapse
|
17
|
Karimi-Sani I, Sharifi M, Abolpour N, Lotfi M, Atapour A, Takhshid MA, Sahebkar A. Drug repositioning for Parkinson's disease: An emphasis on artificial intelligence approaches. Ageing Res Rev 2025; 104:102651. [PMID: 39755176 DOI: 10.1016/j.arr.2024.102651] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2024] [Revised: 12/09/2024] [Accepted: 12/26/2024] [Indexed: 01/06/2025]
Abstract
Parkinson's disease (PD) is one of the most incapacitating neurodegenerative diseases (NDDs). PD is the second most common NDD worldwide which affects approximately 1-2 percent of people over 65 years. It is an attractive pursuit for artificial intelligence (AI) to contribute to and evolve PD treatments through drug repositioning by repurposing existing drugs, shelved drugs, or even candidates that do not meet the criteria for clinical trials. A search was conducted in three databases Web of Science, Scopus, and PubMed. We reviewed the data related to the last years (1975-present) to identify those drugs currently being proposed for repositioning in PD. Moreover, we reviewed the present status of the computational approach, including AI/Machine Learning (AI/ML)-powered pharmaceutical discovery efforts and their implementation in PD treatment. It was found that the number of drug repositioning studies for PD has increased recently. Repositioning of drugs in PD is taking off, and scientific communities are increasingly interested in communicating its results and finding effective treatment alternatives for PD. A better chance of success in PD drug discovery has been made possible due to AI/ML algorithm advancements. In addition to the experimentation stage of drug discovery, it is also important to leverage AI in the planning stage of clinical trials to make them more effective. New AI-based models or solutions that increase the success rate of drug development are greatly needed.
Collapse
Affiliation(s)
- Iman Karimi-Sani
- Department of Medical Biotechnology, School of Advanced Medical Sciences and Technologies, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Mehrdad Sharifi
- Emergency Medicine Department, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran; Artificial Intelligence Department, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Nahid Abolpour
- Artificial Intelligence Department, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Mehrzad Lotfi
- Artificial Intelligence Department, Shiraz University of Medical Sciences, Shiraz, Iran; Medical Imaging Research Center, Department of Radiology, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Amir Atapour
- Department of Medical Biotechnology, School of Advanced Medical Sciences and Technologies, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Mohammad-Ali Takhshid
- Division of Medical Biotechnology, Department of Laboratory Sciences, School of Paramedical Sciences, Shiraz University of Medical Sciences, Shiraz, Iran; Diagnostic Laboratory Sciences and Technology Research Center, School of Paramedical Sciences, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Amirhossein Sahebkar
- Center for Global Health Research, Saveetha Medical College & Hospitals, Saveetha Institute of Medical & Technical Sciences, Saveetha University, Chennai, India; Biotechnology Research Center, Pharmaceutical Technology Institute, Mashhad University of Medical Sciences, Mashhad, Iran; Applied Biomedical Research Center, Mashhad University of Medical Sciences, Mashhad, Iran.
| |
Collapse
|
18
|
Ruffini G, Castaldo F, Vohryzek J. Structured Dynamics in the Algorithmic Agent. ENTROPY (BASEL, SWITZERLAND) 2025; 27:90. [PMID: 39851710 PMCID: PMC11765005 DOI: 10.3390/e27010090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/16/2024] [Revised: 01/10/2025] [Accepted: 01/14/2025] [Indexed: 01/26/2025]
Abstract
In the Kolmogorov Theory of Consciousness, algorithmic agents utilize inferred compressive models to track coarse-grained data produced by simplified world models, capturing regularities that structure subjective experience and guide action planning. Here, we study the dynamical aspects of this framework by examining how the requirement of tracking natural data drives the structural and dynamical properties of the agent. We first formalize the notion of a generative model using the language of symmetry from group theory, specifically employing Lie pseudogroups to describe the continuous transformations that characterize invariance in natural data. Then, adopting a generic neural network as a proxy for the agent dynamical system and drawing parallels to Noether's theorem in physics, we demonstrate that data tracking forces the agent to mirror the symmetry properties of the generative world model. This dual constraint on the agent's constitutive parameters and dynamical repertoire enforces a hierarchical organization consistent with the manifold hypothesis in the neural network. Our findings bridge perspectives from algorithmic information theory (Kolmogorov complexity, compressive modeling), symmetry (group theory), and dynamics (conservation laws, reduced manifolds), offering insights into the neural correlates of agenthood and structured experience in natural systems, as well as the design of artificial intelligence and computational models of the brain.
Collapse
Affiliation(s)
- Giulio Ruffini
- Brain Modeling Department, Neuroelectrics, 08035 Barcelona, Spain;
| | | | - Jakub Vohryzek
- Computational Neuroscience Group, Universitat Pompeu Fabra, 08005 Barcelona, Spain;
- Centre for Eudaimonia and Human Flourishing, Linacre College, Oxford OX3 9BX, UK
| |
Collapse
|
19
|
Oleskiw TD, Lieber JD, Simoncelli EP, Movshon JA. FOUNDATIONS OF VISUAL FORM SELECTIVITY IN MACAQUE AREAS V1 AND V2. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2025:2024.03.04.583307. [PMID: 38496618 PMCID: PMC10942284 DOI: 10.1101/2024.03.04.583307] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/19/2024]
Abstract
Neurons early in the primate visual cortical pathway generate responses by combining signals from other neurons: some from downstream areas, some from within the same area, and others from areas upstream. Here we develop a model that selectively combines afferents derived from a population model of V1 cells. We use this model to account for responses we recorded of both V1 and V2 neurons in awake fixating macaque monkeys to stimuli composed of a sparse collection of locally oriented features ("droplets") designed to drive subsets of V1 neurons. The first stage computes the rectified responses of a fixed population of oriented filters at different scales that cover the visual field. The second stage computes a weighted combination of these first-stage responses, followed by a final nonlinearity, with parameters optimized to fit data from physiological recordings and constrained to encourage sparsity and locality. The fitted model accounts for the responses of both V1 and V2 neurons, capturing an average of 43% of the explainable variance for V1 and 38% for V2. The models fitted to droplet recordings predict responses to classical stimuli, such as gratings of different orientations and spatial frequencies, as well as to textures of different spectral content, which are known to be especially effective in driving V2. The models are less effective, however, at capturing the selectivity of responses to textures that include naturalistic image statistics. The pattern of afferents - defined by their weights over the 4 dimensions of spatial position, orientation, and spatial frequency - provides a common and interpretable characterization of the origin of many neuronal response properties in the early visual cortex.
Collapse
Affiliation(s)
- Timothy D Oleskiw
- Center for Neural Science, New York University
- Center for Computational Neuroscience, Flatiron Institute
| | | | - Eero P Simoncelli
- Center for Computational Neuroscience, Flatiron Institute
- Center for Neural Science, New York University
| | | |
Collapse
|
20
|
Xiong J, Dai W, Wang Q, Dong X, Ye B, Yang J. A review of deep learning in blink detection. PeerJ Comput Sci 2025; 11:e2594. [PMID: 39896005 PMCID: PMC11784707 DOI: 10.7717/peerj-cs.2594] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2024] [Accepted: 11/18/2024] [Indexed: 02/04/2025]
Abstract
Blink detection is a highly concerned research direction in the field of computer vision, which plays a key role in various application scenes such as human-computer interaction, fatigue detection and emotion perception. In recent years, with the rapid development of deep learning, the application of deep learning techniques for precise blink detection has emerged as a significant area of interest among researchers. Compared with traditional methods, the blink detection method based on deep learning offers superior feature learning ability and higher detection accuracy. However, the current research on blink detection based on deep learning lacks systematic summarization and comparison. Therefore, the aim of this article is to comprehensively review the research progress in deep learning-based blink detection methods and help researchers to have a clear understanding of the various approaches in this field. This article analyzes the progress made by several classical deep learning models in practical applications of eye blink detection while highlighting their respective strengths and weaknesses. Furthermore, it provides a comprehensive summary of commonly used datasets and evaluation metrics for blink detection. Finally, it discusses the challenges and future directions of deep learning for blink detection applications. Our analysis reveals that deep learning-based blink detection methods demonstrate strong performance in detection. However, they encounter several challenges, including training data imbalance, complex environment interference, real-time processing issues and application device limitations. By overcoming the challenges identified in this study, the application prospects of deep learning-based blink detection algorithms will be significantly enhanced.
Collapse
Affiliation(s)
- Jianbin Xiong
- School of Automation, Guangdong Polytechnic Normal University, Guangzhou, Guangdong, China
| | - Weikun Dai
- School of Automation, Guangdong Polytechnic Normal University, Guangzhou, Guangdong, China
| | - Qi Wang
- School of Automation, Guangdong Polytechnic Normal University, Guangzhou, Guangdong, China
| | - Xiangjun Dong
- School of Automation, Guangdong Polytechnic Normal University, Guangzhou, Guangdong, China
| | - Baoyu Ye
- School of Aircraft Maintenance Engineering, Guangzhou Civil Aviation College, Guangzhou, Guangdong, China
| | - Jianxiang Yang
- School of Automation, Guangdong Polytechnic Normal University, Guangzhou, Guangdong, China
| |
Collapse
|
21
|
Li B, Todo Y, Tang Z. Artificial Visual System for Stereo-Orientation Recognition Based on Hubel-Wiesel Model. Biomimetics (Basel) 2025; 10:38. [PMID: 39851754 PMCID: PMC11762170 DOI: 10.3390/biomimetics10010038] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2024] [Revised: 12/26/2024] [Accepted: 01/06/2025] [Indexed: 01/26/2025] Open
Abstract
Stereo-orientation selectivity is a fundamental neural mechanism in the brain that plays a crucial role in perception. However, due to the recognition process of high-dimensional spatial information commonly occurring in high-order cortex, we still know little about the mechanisms underlying stereo-orientation selectivity and lack a modeling strategy. A classical explanation for the mechanism of two-dimensional orientation selectivity within the primary visual cortex is based on the Hubel-Wiesel model, a cascading neural connection structure. The local-to-global information aggregation thought within the Hubel-Wiesel model not only contributed to neurophysiology but also inspired the development of computer vision fields. In this paper, we provide a clear and efficient conceptual understanding of stereo-orientation selectivity and propose a quantitative explanation for its generation based on the thought of local-to-global information aggregation within the Hubel-Wiesel model and develop an artificial visual system (AVS) for stereo-orientation recognition. Our approach involves modeling depth selective cells to receive depth information, simple stereo-orientation selective cells for combining distinct depth information inputs to generate various local stereo-orientation selectivity, and complex stereo-orientation selective cells responsible for integrating the same local information to generate global stereo-orientation selectivity. Simulation results demonstrate that our AVS is effective in stereo-orientation recognition and robust against spatial noise jitters. AVS achieved an overall over 90% accuracy on noise data in orientation recognition tasks, significantly outperforming deep models. In addition, the AVS contributes to enhancing deep models' performance, robustness, and stability in 3D object recognition tasks. Notably, AVS enhanced the TransNeXt model in improving its overall performance from 73.1% to 97.2% on the 3D-MNIST dataset and from 56.1% to 86.4% on the 3D-Fashion-MNIST dataset. Our explanation for the generation of stereo-orientation selectivity offers a reliable, explainable, and robust approach for extracting spatial features and provides a straightforward modeling method for neural computation research.
Collapse
Affiliation(s)
- Bin Li
- Division of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa-shi 920-1192, Japan;
| | - Yuki Todo
- Faculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa-shi 920-1192, Japan
| | - Zheng Tang
- Institute of AI for Industries, Chinese Academy of Sciences, 168 Tianquan Road, Nanjing 211100, China
- School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
| |
Collapse
|
22
|
Ao S, Xiang S, Yang J. A hyperparameter optimization-assisted deep learning method towards thermal error modeling of spindles. ISA TRANSACTIONS 2025; 156:434-445. [PMID: 39516098 DOI: 10.1016/j.isatra.2024.11.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/18/2024] [Revised: 10/31/2024] [Accepted: 11/01/2024] [Indexed: 11/16/2024]
Abstract
Spindle thermal errors significantly influence the machining accuracy of machine tools, necessitating precise modeling. While deep learning methods are commonly used for this purpose, their generalization ability and performance largely depend on design of the network structure and the selection of hyperparameters. To address these challenges, this study proposes a neural network model that integrates Bayesian optimization (BO) with dilated convolution neural network (DCNN). Dilated convolutions enhance traditional CNN models by using a dilation rate, which allows the convolutional kernel to cover a larger receptive field without increasing parameter count or computational cost. To prevent local optima during hyperparameter tuning, a Bayesian algorithm based on Gaussian processes (GP) is utilized, which optimizes 9 critical hyperparameters in the DCNN. Experimental results demonstrate that the proposed model achieves over 95 % accuracy in predicting radial thermal errors for both heating and cooling states in the X and Y directions.
Collapse
Affiliation(s)
- Shicun Ao
- Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China; Ningbo Key Laboratory of Micro-nano Motion and Intelligent Control, China.
| | - Sitong Xiang
- Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China; Ningbo Key Laboratory of Micro-nano Motion and Intelligent Control, China.
| | - Jianguo Yang
- School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
| |
Collapse
|
23
|
Lozano A, Nava E, García Méndez MD, Moreno-Torres I. Computing nasalance with MFCCs and Convolutional Neural Networks. PLoS One 2024; 19:e0315452. [PMID: 39739659 DOI: 10.1371/journal.pone.0315452] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2024] [Accepted: 11/25/2024] [Indexed: 01/02/2025] Open
Abstract
Nasalance is a valuable clinical biomarker for hypernasality. It is computed as the ratio of acoustic energy emitted through the nose to the total energy emitted through the mouth and nose (eNasalance). A new approach is proposed to compute nasalance using Convolutional Neural Networks (CNNs) trained with Mel-Frequency Cepstrum Coefficients (mfccNasalance). mfccNasalance is evaluated by examining its accuracy: 1) when the train and test data are from the same or from different dialects; 2) with test data that differs in dynamicity (e.g. rapidly produced diadochokinetic syllables versus short words); and 3) using multiple CNN configurations (i.e. kernel shape and use of 1 × 1 pointwise convolution). Dual-channel Nasometer speech data from healthy speakers from different dialects: Costa Rica, more(+) nasal, Spain and Chile, less(-) nasal, are recorded. The input to the CNN models were sequences of 39 MFCC vectors computed from 250 ms moving windows. The test data were recorded in Spain and included short words (-dynamic), sentences (+dynamic), and diadochokinetic syllables (+dynamic). The accuracy of a CNN model was defined as the Spearman correlation between the mfccNasalance for that model and the perceptual nasality scores of human experts. In the same-dialect condition, mfccNasalance was more accurate than eNasalance independently of the CNN configuration; using a 1 × 1 kernel resulted in increased accuracy for +dynamic utterances (p < .000), though not for -dynamic utterances. The kernel shape had a significant impact for -dynamic utterances (p < .000) exclusively. In the different-dialect condition, the scores were significantly less accurate than in the same-dialect condition, particularly for Costa Rica trained models. We conclude that mfccNasalance is a flexible and useful alternative to eNasalance. Future studies should explore how to optimize mfccNasalance by selecting the most adequate CNN model as a function of the dynamicity of the target speech data.
Collapse
Affiliation(s)
- Andrés Lozano
- Department of Communication Engineering, University of Málaga, Málaga, Spain
| | - Enrique Nava
- Department of Communication Engineering, University of Málaga, Málaga, Spain
| | | | | |
Collapse
|
24
|
Marczak-Czajka A, Redgrave T, Mitcheff M, Villano M, Czajka A. Assessment of human emotional reactions to visual stimuli "deep-dreamed" by artificial neural networks. Front Psychol 2024; 15:1509392. [PMID: 39776961 PMCID: PMC11703666 DOI: 10.3389/fpsyg.2024.1509392] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2024] [Accepted: 11/26/2024] [Indexed: 01/11/2025] Open
Abstract
Introduction While the fact that visual stimuli synthesized by Artificial Neural Networks (ANN) may evoke emotional reactions is documented, the precise mechanisms that connect the strength and type of such reactions with the ways of how ANNs are used to synthesize visual stimuli are yet to be discovered. Understanding these mechanisms allows for designing methods that synthesize images attenuating or enhancing selected emotional states, which may provide unobtrusive and widely-applicable treatment of mental dysfunctions and disorders. Methods The Convolutional Neural Network (CNN), a type of ANN used in computer vision tasks which models the ways humans solve visual tasks, was applied to synthesize ("dream" or "hallucinate") images with no semantic content to maximize activations of neurons in precisely-selected layers in the CNN. The evoked emotions of 150 human subjects observing these images were self-reported on a two-dimensional scale (arousal and valence) utilizing self-assessment manikin (SAM) figures. Correlations between arousal and valence values and image visual properties (e.g., color, brightness, clutter feature congestion, and clutter sub-band entropy) as well as the position of the CNN's layers stimulated to obtain a given image were calculated. Results Synthesized images that maximized activations of some of the CNN layers led to significantly higher or lower arousal and valence levels compared to average subject's reactions. Multiple linear regression analysis found that a small set of selected image global visual features (hue, feature congestion, and sub-band entropy) are significant predictors of the measured arousal, however no statistically significant dependencies were found between image global visual features and the measured valence. Conclusion This study demonstrates that the specific method of synthesizing images by maximizing small and precisely-selected parts of the CNN used in this work may lead to synthesis of visual stimuli that enhance or attenuate emotional reactions. This method paves the way for developing tools that stimulate, in a non-invasive way, to support wellbeing (manage stress, enhance mood) and to assist patients with certain mental conditions by complementing traditional methods of therapeutic interventions.
Collapse
Affiliation(s)
- Agnieszka Marczak-Czajka
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, United States
| | - Timothy Redgrave
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, United States
| | - Mahsa Mitcheff
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, United States
| | - Michael Villano
- Department of Psychology, University of Notre Dame, Notre Dame, IN, United States
| | - Adam Czajka
- Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, United States
| |
Collapse
|
25
|
Choudhary N, Gupta A, Gupta N. Artificial intelligence and robotics in regional anesthesia. World J Methodol 2024; 14:95762. [PMID: 39712560 PMCID: PMC11287539 DOI: 10.5662/wjm.v14.i4.95762] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/17/2024] [Revised: 06/03/2024] [Accepted: 06/13/2024] [Indexed: 07/26/2024] Open
Abstract
Artificial intelligence (AI) technology is vital for practitioners to incorporate AI and robotics in day-to-day regional anesthesia practice. Recent literature is encouraging on its applications in regional anesthesia, but the data are limited. AI can help us identify and guide the needle tip precisely to the location. This may help us reduce the time, improve precision, and reduce the associated side effects of improper distribution of drugs. In this article, we discuss the potential roles of AI and robotics in regional anesthesia.
Collapse
Affiliation(s)
- Nitin Choudhary
- Department of Anesthesiology, Pain Medicine and Critical Care, All India Institute of Medical Sciences, New Delhi 110029, Delhi, India
| | - Anju Gupta
- Department of Anesthesiology, Pain Medicine and Critical Care, All India Institute of Medical Sciences, New Delhi 110029, Delhi, India
| | - Nishkarsh Gupta
- Department of Onco-Anesthesiology and Palliative Medicine, All India Institute of Medical Sciences, New Delhi 110029, Delhi, India
| |
Collapse
|
26
|
Osswald A, Tsagakis K, Thielmann M, Lumsden AB, Ruhparwar A, Karmonik C. An Artificial Intelligence-Based Automatic Classifier for the Presence of False Lumen Thrombosis After Frozen Elephant Trunk Operation. Diagnostics (Basel) 2024; 14:2853. [PMID: 39767214 PMCID: PMC11675686 DOI: 10.3390/diagnostics14242853] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2024] [Revised: 12/11/2024] [Accepted: 12/17/2024] [Indexed: 01/11/2025] Open
Abstract
OBJECTIVE To develop an unsupervised artificial intelligence algorithm for identifying and quantifying the presence of false lumen thrombosis (FL) after Frozen Elephant Trunk (FET) operation in computed tomography angiographic (CTA) images in an interdisciplinary approach. METHODS CTA datasets were retrospectively collected from eight patients after FET operation for aortic dissection from a single center. Of those, five patients had a residual aortic dissection with partial false lumen thrombosis, and three patients had no false lumen or thrombosis. Centerlines of the aortic lumen were defined, and images were calculated perpendicular to the centerline. Lumen and thrombosis were outlined and used as input for a variational autoencoder (VAE) using 2D convolutional neural networks (2D CNN). A 2D latent space was chosen to separate images containing false lumen patency, false lumen thrombosis and no presence of false lumen. Classified images were assigned a thrombus score for the presence or absence of FL thrombosis and an average score for each patient. RESULTS Images reconstructed by the trained 2D CNN VAE corresponded well to original images with thrombosis. Average thrombus scores for the five patients ranged from 0.05 to 0.36 where the highest thrombus scores coincided with the location of the largest thrombus lesion. In the three patients without large thrombus lesions, average thrombus scores ranged from 0.002 to 0.01. CONCLUSIONS The presence and absence of a FL thrombus can be automatically classified by the 2D CNN VAE for patient-specific CTA image datasets. As FL thrombosis is an indication for positive aortic remodeling, evaluation of FL status is essential in follow-up examinations. The presented proof-of-concept is promising for the automated classification and quantification of FL thrombosis.
Collapse
Affiliation(s)
- Anja Osswald
- Department of Thoracic and Cardiovascular Surgery, West-German Heart and Vascular Centre, University Duisburg-Essen, 45122 Essen, Germany; (K.T.); (M.T.); (A.R.)
| | - Konstantinos Tsagakis
- Department of Thoracic and Cardiovascular Surgery, West-German Heart and Vascular Centre, University Duisburg-Essen, 45122 Essen, Germany; (K.T.); (M.T.); (A.R.)
| | - Matthias Thielmann
- Department of Thoracic and Cardiovascular Surgery, West-German Heart and Vascular Centre, University Duisburg-Essen, 45122 Essen, Germany; (K.T.); (M.T.); (A.R.)
| | - Alan B. Lumsden
- Department of Vascular Surgery, Houston Methodist DeBakey Heart & Vascular Center, Houston, TX 77030, USA;
| | - Arjang Ruhparwar
- Department of Thoracic and Cardiovascular Surgery, West-German Heart and Vascular Centre, University Duisburg-Essen, 45122 Essen, Germany; (K.T.); (M.T.); (A.R.)
| | - Christof Karmonik
- Translational Imaging Centre, Houston Methodist Research Institute, Houston, TX 77030, USA;
| |
Collapse
|
27
|
Bunne C, Roohani Y, Rosen Y, Gupta A, Zhang X, Roed M, Alexandrov T, AlQuraishi M, Brennan P, Burkhardt DB, Califano A, Cool J, Dernburg AF, Ewing K, Fox EB, Haury M, Herr AE, Horvitz E, Hsu PD, Jain V, Johnson GR, Kalil T, Kelley DR, Kelley SO, Kreshuk A, Mitchison T, Otte S, Shendure J, Sofroniew NJ, Theis F, Theodoris CV, Upadhyayula S, Valer M, Wang B, Xing E, Yeung-Levy S, Zitnik M, Karaletsos T, Regev A, Lundberg E, Leskovec J, Quake SR. How to build the virtual cell with artificial intelligence: Priorities and opportunities. Cell 2024; 187:7045-7063. [PMID: 39672099 DOI: 10.1016/j.cell.2024.11.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2024] [Revised: 11/02/2024] [Accepted: 11/12/2024] [Indexed: 12/15/2024]
Abstract
Cells are essential to understanding health and disease, yet traditional models fall short of modeling and simulating their function and behavior. Advances in AI and omics offer groundbreaking opportunities to create an AI virtual cell (AIVC), a multi-scale, multi-modal large-neural-network-based model that can represent and simulate the behavior of molecules, cells, and tissues across diverse states. This Perspective provides a vision on their design and how collaborative efforts to build AIVCs will transform biological research by allowing high-fidelity simulations, accelerating discoveries, and guiding experimental studies, offering new opportunities for understanding cellular functions and fostering interdisciplinary collaborations in open science.
Collapse
Affiliation(s)
- Charlotte Bunne
- Department of Computer Science, Stanford University, Stanford, CA, USA; Genentech, South San Francisco, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; School of Computer and Communication Sciences and School of Life Sciences, EPFL, Lausanne, Switzerland
| | - Yusuf Roohani
- Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; Arc Institute, Palo Alto, CA, USA
| | - Yanay Rosen
- Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA
| | - Ankit Gupta
- Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Protein Science, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden
| | - Xikun Zhang
- Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Bioengineering, Stanford University, Stanford, CA, USA
| | - Marcel Roed
- Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA
| | - Theo Alexandrov
- Department of Pharmacology, University of California, San Diego, San Diego, CA, USA; Department of Bioengineering, University of California, San Diego, San Diego, CA, USA
| | - Mohammed AlQuraishi
- Department of Bioengineering, University of California, San Diego, San Diego, CA, USA
| | | | | | - Andrea Califano
- Department of Systems Biology, Columbia University, New York, NY, USA; Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, NY, USA; Chan Zuckerberg Biohub, New York, NY, USA
| | - Jonah Cool
- Chan Zuckerberg Initiative, Redwood City, CA, USA
| | - Abby F Dernburg
- Department of Molecular and Cell Biology, University of California, Berkeley, Berkeley, CA, USA
| | - Kirsty Ewing
- Chan Zuckerberg Initiative, Redwood City, CA, USA
| | - Emily B Fox
- Department of Computer Science, Stanford University, Stanford, CA, USA; Department of Statistics, Stanford University, Stanford, CA, USA; Chan Zuckerberg Biohub, San Francisco, CA, USA
| | - Matthias Haury
- Chan Zuckerberg Institute for Advanced Biological Imaging, Redwood City, CA, USA
| | - Amy E Herr
- Chan Zuckerberg Biohub, San Francisco, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA
| | | | - Patrick D Hsu
- Arc Institute, Palo Alto, CA, USA; Department of Bioengineering, University of California, Berkeley, Berkeley, CA, USA; Center for Computational Biology, University of California, Berkeley, Berkeley, CA, USA
| | | | | | | | | | - Shana O Kelley
- Chan Zuckerberg Biohub, Chicago, IL, USA; Northwestern University, Evanston, IL, USA
| | - Anna Kreshuk
- Cell Biology and Biophysics Unit, European Molecular Biology Laboratory, Heidelberg, Germany
| | - Tim Mitchison
- Department of Systems Biology, Harvard Medical School, Boston, MA, USA
| | - Stephani Otte
- Chan Zuckerberg Institute for Advanced Biological Imaging, Redwood City, CA, USA
| | - Jay Shendure
- Department of Genome Sciences, University of Washington, Seattle, WA, USA; Brotman Baty Institute for Precision Medicine, Seattle, WA, USA; Seattle Hub for Synthetic Biology, Seattle, WA, USA; Howard Hughes Medical Institute, Seattle, WA, USA
| | | | - Fabian Theis
- Institute of Computational Biology, Helmholtz Center Munich, Munich, Germany; School of Computing, Information and Technology, Technical University of Munich, Munich, Germany; TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany
| | - Christina V Theodoris
- Gladstone Institute of Cardiovascular Disease, Gladstone Institute of Data Science and Biotechnology, San Francisco, CA, USA; Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA
| | - Srigokul Upadhyayula
- Department of Molecular and Cell Biology, University of California, Berkeley, Berkeley, CA, USA; Chan Zuckerberg Biohub, San Francisco, CA, USA; Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Marc Valer
- Chan Zuckerberg Initiative, Redwood City, CA, USA
| | - Bo Wang
- Department of Computer Science, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada
| | - Eric Xing
- Carnegie Mellon University, School of Computer Science, Pittsburgh, PA, USA; Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
| | - Serena Yeung-Levy
- Department of Computer Science, Stanford University, Stanford, CA, USA; Department of Biomedical Data Science, Stanford University, Stanford, CA, USA
| | - Marinka Zitnik
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA; Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA, USA; Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | | | - Aviv Regev
- Genentech, South San Francisco, CA, USA.
| | - Emma Lundberg
- Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Protein Science, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden; Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Pathology, Stanford University, Stanford, CA, USA.
| | - Jure Leskovec
- Department of Computer Science, Stanford University, Stanford, CA, USA; Chan Zuckerberg Initiative, Redwood City, CA, USA.
| | - Stephen R Quake
- Chan Zuckerberg Initiative, Redwood City, CA, USA; Department of Bioengineering, Stanford University, Stanford, CA, USA; Department of Applied Physics, Stanford University, Stanford, CA, USA.
| |
Collapse
|
28
|
Hao W, Jiang H, Song Q, Song Q, Sun S. A multi modal fusion coal gangue recognition method based on IBWO-CNN-LSTM. Sci Rep 2024; 14:30396. [PMID: 39638833 PMCID: PMC11621578 DOI: 10.1038/s41598-024-80811-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2024] [Accepted: 11/21/2024] [Indexed: 12/07/2024] Open
Abstract
Accurate identification of coal and gangue is a crucial guarantee for efficient and safe mining of top coal caving face. This article proposes a coal-gangue recognition method based on an improved beluga whale optimization algorithm (IBWO), convolutional neural network, and long short-term memory network (CNN-LSTM) multi-modal fusion model. First, the mutation and memory library mechanisms are introduced into the beluga whale optimization to explore the solution space fully, prevent falling into local optimum, and accelerate the convergence process. Subsequently, the image mapping of the audio signal and vibration signal is performed to extract Mel-Frequency Cepstral Coefficients (MFCC) features, generating rich sample data for CNN-LSTM. Then the multi-head attention mechanism is introduced into CNN-LSTM to speed up the training speed and improve the classification accuracy. Finally, the IBWO-CNN-LSTM coal-gangue recognition model is constructed by the optimal hyperparameter combination obtained by IBWO to realize the automatic recognition of coal-gangue. The benchmark function proves that IBWO is superior to other optimization algorithms. By building an experimental platform for the impact of coal and gangue falling on the tail beam of hydraulic support, multiple experimental data collection is carried out. The experimental results show that the proposed coal-gangue recognition model has better performance than other recognition models, and the accuracy rate reaches 95.238%. The multi-modal fusion strategy helps to improve the accuracy and robustness of coal-gangue recognition.
Collapse
Affiliation(s)
- Wenchao Hao
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, 271000, China
| | - Haiyan Jiang
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, 271000, China
| | - Qinghui Song
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, 271000, China
| | - Qingjun Song
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, 271000, China.
| | - Shirong Sun
- College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, 271000, China
| |
Collapse
|
29
|
Zhou X, Kedia S, Meng R, Gerstein M. Deep learning analysis of fMRI data for predicting Alzheimer's Disease: A focus on convolutional neural networks and model interpretability. PLoS One 2024; 19:e0312848. [PMID: 39630834 PMCID: PMC11616848 DOI: 10.1371/journal.pone.0312848] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2024] [Accepted: 10/14/2024] [Indexed: 12/07/2024] Open
Abstract
The early detection of Alzheimer's Disease (AD) is thought to be important for effective intervention and management. Here, we explore deep learning methods for the early detection of AD. We consider both genetic risk factors and functional magnetic resonance imaging (fMRI) data. However, we found that the genetic factors do not notably enhance the AD prediction by imaging. Thus, we focus on building an effective imaging-only model. In particular, we utilize data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), employing a 3D Convolutional Neural Network (CNN) to analyze fMRI scans. Despite the limitations posed by our dataset (small size and imbalanced nature), our CNN model demonstrates accuracy levels reaching 92.8% and an ROC of 0.95. Our research highlights the complexities inherent in integrating multimodal medical datasets. It also demonstrates the potential of deep learning in medical imaging for AD prediction.
Collapse
Affiliation(s)
- Xiao Zhou
- Department of Molecular Biophysics & Biochemistry, Yale University, New Haven, CT, United States of America
| | - Sanchita Kedia
- Department of Computer Science, Yale University, New Haven, CT, United States of America
| | - Ran Meng
- Department of Molecular Biophysics & Biochemistry, Yale University, New Haven, CT, United States of America
| | - Mark Gerstein
- Program in Computational Biology & Bioinformatics, Yale University, New Haven, CT, United States of America
- Department of Molecular Biophysics & Biochemistry, Yale University, New Haven, CT, United States of America
- Department of Computer Science, Yale University, New Haven, CT, United States of America
- Department of Statistics & Data Science, Yale University, New Haven, CT, United States of America
- Department of Biomedical Informatics & Data Science, Yale University, New Haven, CT, United States of America
| |
Collapse
|
30
|
Hegde A, Vijaysenan D, Mandava P, Menon G. The use of cloud based machine learning to predict outcome in intracerebral haemorrhage without explicit programming expertise. Neurosurg Rev 2024; 47:883. [PMID: 39625566 PMCID: PMC11614922 DOI: 10.1007/s10143-024-03115-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2024] [Revised: 10/06/2024] [Accepted: 11/14/2024] [Indexed: 12/06/2024]
Abstract
Machine Learning (ML) techniques require novel computer programming skills along with clinical domain knowledge to produce a useful model. We demonstrate the use of a cloud-based ML tool that does not require any programming expertise to develop, validate and deploy a prognostic model for Intracerebral Haemorrhage (ICH). The data of patients admitted with Spontaneous Intracerebral haemorrhage from January 2015 to December 2019 was accessed from our prospectively maintained hospital stroke registry. 80% of the dataset was used for training, 10% for validation, and 10% for testing. Seventeen input variables were used to predict the dichotomized outcomes (Good outcome mRS 0-3/ Bad outcome mRS 4-6), using machine learning (ML) and logistic regression (LR) models. The two different approaches were evaluated using Area Under the Curve (AUC) for Receiver Operating Characteristic (ROC), Precision recall and accuracy. Our data set comprised of a cohort of 1000 patients. The data was split 8:1 for training & testing respectively. The AUC ROC of the ML model was 0.86 with an accuracy of 75.7%. With LR AUC ROC was 0.74 with an accuracy of 73.8%. Feature importance chart showed that Glasgow coma score (GCS) at presentation had the highest relative importance, followed by hematoma volume and age in both approaches. Machine learning models perform better when compared to logistic regression. Models can be developed by clinicians possessing domain expertise and no programming experience using cloud based tools. The models so developed lend themselves to be incorporated into clinical workflow.
Collapse
Affiliation(s)
- Ajay Hegde
- Neurosurgery, Kasturba Medical College, Manipal Academy of Higher Education, 576104, Manipal, India
- Neurosurgery, Manipal Hospitals, Bangalore, India
| | - Deepu Vijaysenan
- Department of Electronics and Communication Engineering, National Institute of Technology, Surathkal, Karnataka, India
| | | | - Girish Menon
- Neurosurgery, Kasturba Medical College, Manipal Academy of Higher Education, Manipal, 576104, India.
| |
Collapse
|
31
|
Pandey L, Lee D, Wood SMW, Wood JN. Parallel development of object recognition in newborn chicks and deep neural networks. PLoS Comput Biol 2024; 20:e1012600. [PMID: 39621774 DOI: 10.1371/journal.pcbi.1012600] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2024] [Revised: 12/17/2024] [Accepted: 10/29/2024] [Indexed: 12/18/2024] Open
Abstract
How do newborns learn to see? We propose that visual systems are space-time fitters, meaning visual development can be understood as a blind fitting process (akin to evolution) in which visual systems gradually adapt to the spatiotemporal data distributions in the newborn's environment. To test whether space-time fitting is a viable theory for learning how to see, we performed parallel controlled-rearing experiments on newborn chicks and deep neural networks (DNNs), including CNNs and transformers. First, we raised newborn chicks in impoverished environments containing a single object, then simulated those environments in a video game engine. Second, we recorded first-person images from agents moving through the virtual animal chambers and used those images to train DNNs. Third, we compared the viewpoint-invariant object recognition performance of the chicks and DNNs. When DNNs received the same visual diet (training data) as chicks, the models developed common object recognition skills as chicks. DNNs that used time as a teaching signal-space-time fitters-also showed common patterns of successes and failures across the test viewpoints as chicks. Thus, DNNs can learn object recognition in the same impoverished environments as newborn animals. We argue that space-time fitters can serve as formal scientific models of newborn visual systems, providing image-computable models for studying how newborns learn to see from raw visual experiences.
Collapse
Affiliation(s)
- Lalit Pandey
- Informatics Department, Indiana University, Bloomington, Indiana, United States of America
| | - Donsuk Lee
- Informatics Department, Indiana University, Bloomington, Indiana, United States of America
| | - Samantha M W Wood
- Informatics Department, Indiana University, Bloomington, Indiana, United States of America
- Cognitive Science Program, Indiana University, Bloomington, Indiana, United States of America
- Department of Neuroscience, Indiana University, Bloomington, Indiana, United States of America
| | - Justin N Wood
- Informatics Department, Indiana University, Bloomington, Indiana, United States of America
- Cognitive Science Program, Indiana University, Bloomington, Indiana, United States of America
- Department of Neuroscience, Indiana University, Bloomington, Indiana, United States of America
- Center for the Integrated Study of Animal Behavior, Indiana University, Bloomington, Indiana, United States of America
| |
Collapse
|
32
|
Khawar MM, Abdus Saboor H, Eric R, Arain NR, Bano S, Mohamed Abaker MB, Siddiqui BI, Figueroa RR, Koppula SR, Fatima H, Begum A, Anwar S, Khalid MU, Jamil U, Iqbal J. Role of artificial intelligence in predicting neurological outcomes in postcardiac resuscitation. Ann Med Surg (Lond) 2024; 86:7202-7211. [PMID: 39649879 PMCID: PMC11623902 DOI: 10.1097/ms9.0000000000002673] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2024] [Accepted: 10/07/2024] [Indexed: 12/11/2024] Open
Abstract
Being an extremely high mortality rate condition, cardiac arrest cases have rightfully been evaluated via various studies and scoring factors for effective resuscitative practices and neurological outcomes postresuscitation. This narrative review aims to explore the role of artificial intelligence (AI) in predicting neurological outcomes postcardiac resuscitation. The methodology involved a detailed review of all relevant recent studies of AI, different machine learning algorithms, prediction tools, and assessing their benefit in predicting neurological outcomes in postcardiac resuscitation cases as compared to more traditional prognostic scoring systems and tools. Previously, outcome determining clinical, blood, and radiological factors were prone to other influencing factors like limited accuracy and time constraints. Studies conducted also emphasized that to predict poor neurological outcomes, a more multimodal approach helped adjust for confounding factors, interpret diverse datasets, and provide a reliable prognosis, which only demonstrates the need for AI to help overcome challenges faced. Advanced machine learning algorithms like artificial neural networks (ANN) using supervised learning by AI have improved the accuracy of prognostic models outperforming conventional models. Several real-world cases of effective AI-powered algorithm models have been cited here. Studies comparing machine learning tools like XGBoost, AI Watson, hyperspectral imaging, ChatGPT-4, and AI-based gradient boosting have noted their beneficial uses. AI could help reduce workload, healthcare costs, and help personalize care, process vast genetic and lifestyle data and help reduce side effects from treatments. Limitations of AI have been covered extensively in this article, including data quality, bias, privacy issues, and transparency. Our objectives should be to use more diverse data sources, use interpretable data output giving process explanation, validation method, and implement policies to safeguard patient data. Despite the limitations, the advancements already made by AI and its potential in predicting neurological outcomes in postcardiac resuscitation cases has been quite promising and boosts a continually improving system, albeit requiring close human supervision with training and improving models, with plans to educate clinicians, the public and sharing collected data.
Collapse
Affiliation(s)
| | | | - Rahul Eric
- Nottingham University Hospitals NHS Trust, Nottingham, UK
| | | | - Saira Bano
- Evergreen Hospital Kirkland, Washington, USA
| | | | | | | | | | - Hira Fatima
- United Medical and Dental College, New Westminster, British Columbia, Canada
| | - Afreen Begum
- ESIC Medical College and Hospital, Telangana, Hyderabad
| | - Sana Anwar
- Lugansk State Medical University, Texas, Ukraine
| | | | | | - Javed Iqbal
- King Edward Medical University Lahore, Mayo Hospital, Lahore
| |
Collapse
|
33
|
Chen H, Lu D, Xiao Z, Li S, Zhang W, Luan X, Zhang W, Zheng G. Comprehensive applications of the artificial intelligence technology in new drug research and development. Health Inf Sci Syst 2024; 12:41. [PMID: 39130617 PMCID: PMC11310389 DOI: 10.1007/s13755-024-00300-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Accepted: 07/27/2024] [Indexed: 08/13/2024] Open
Abstract
Purpose Target-based strategy is a prevalent means of drug research and development (R&D), since targets provide effector molecules of drug action and offer the foundation of pharmacological investigation. Recently, the artificial intelligence (AI) technology has been utilized in various stages of drug R&D, where AI-assisted experimental methods show higher efficiency than sole experimental ones. It is a critical need to give a comprehensive review of AI applications in drug R &D for biopharmaceutical field. Methods Relevant literatures about AI-assisted drug R&D were collected from the public databases (Including Google Scholar, Web of Science, PubMed, IEEE Xplore Digital Library, Springer, and ScienceDirect) through a keyword searching strategy with the following terms [("Artificial Intelligence" OR "Knowledge Graph" OR "Machine Learning") AND ("Drug Target Identification" OR "New Drug Development")]. Results In this review, we first introduced common strategies and novel trends of drug R&D, followed by characteristic description of AI algorithms widely used in drug R&D. Subsequently, we depicted detailed applications of AI algorithms in target identification, lead compound identification and optimization, drug repurposing, and drug analytical platform construction. Finally, we discussed the challenges and prospects of AI-assisted methods for drug discovery. Conclusion Collectively, this review provides comprehensive overview of AI applications in drug R&D and presents future perspectives for biopharmaceutical field, which may promote the development of drug industry.
Collapse
Affiliation(s)
- Hongyu Chen
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Dong Lu
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Ziyi Xiao
- Johns Hopkins Bloomberg School of Public Health, Baltimore, MD USA
| | - Shensuo Li
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Wen Zhang
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Xin Luan
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Weidong Zhang
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Guangyong Zheng
- Shanghai Frontiers Science Center for Chinese Medicine Chemical Biology, Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| |
Collapse
|
34
|
Grossetête L, Marcelot C, Gatel C, Pauchet S, Hytch M. Principle of TEM alignment using convolutional neural networks: Case study on condenser aperture alignment. Ultramicroscopy 2024; 267:114047. [PMID: 39413637 DOI: 10.1016/j.ultramic.2024.114047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2024] [Revised: 08/07/2024] [Accepted: 09/11/2024] [Indexed: 10/18/2024]
Abstract
The possibility of automatically aligning the transmission electron microscope (TEM) is explored using an approach based on artificial intelligence (AI). After presenting the general concept, we test the method on the first step of the alignment process which involves centering the condenser aperture. We propose using a convolutional neural network (CNN) that learns to predict the x and y-shifts needed to realign the aperture in one step. The learning data sets were acquired automatically on the microscope by using a simplified digital twin. Different models were tested and analysed to choose the optimal design. We have developed a human-level estimator and intend to use it safely on all apertures. A similar process could be used for most steps of the alignment process with minimal changes, allowing microscopists to reduce the time and training required to perform this task. The method is also compatible with continuous correction of alignment drift during lengthy experiments or to ensure uniformity of illumination conditions during data acquisition.
Collapse
Affiliation(s)
- Loïc Grossetête
- CEMES-CNRS, 29 rue Jeanne Marvig, Toulouse, 31055, France; Fédération ENAC ISAE-SUPAERO ONERA, 7 Avenue Edouard Belin, Toulouse, 31055, France.
| | | | | | - Sylvain Pauchet
- Fédération ENAC ISAE-SUPAERO ONERA, 7 Avenue Edouard Belin, Toulouse, 31055, France
| | - Martin Hytch
- CEMES-CNRS, 29 rue Jeanne Marvig, Toulouse, 31055, France
| |
Collapse
|
35
|
Susan S. Neuroscientific insights about computer vision models: a concise review. BIOLOGICAL CYBERNETICS 2024; 118:331-348. [PMID: 39382577 DOI: 10.1007/s00422-024-00998-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/22/2024] [Accepted: 09/12/2024] [Indexed: 10/10/2024]
Abstract
The development of biologically-inspired computational models has been the focus of study ever since the artificial neuron was introduced by McCulloch and Pitts in 1943. However, a scrutiny of literature reveals that most attempts to replicate the highly efficient and complex biological visual system have been futile or have met with limited success. The recent state-of the-art computer vision models, such as pre-trained deep neural networks and vision transformers, may not be biologically inspired per se. Nevertheless, certain aspects of biological vision are still found embedded, knowingly or unknowingly, in the architecture and functioning of these models. This paper explores several principles related to visual neuroscience and the biological visual pathway that resonate, in some manner, in the architectural design and functioning of contemporary computer vision models. The findings of this survey can provide useful insights for building futuristic bio-inspired computer vision models. The survey is conducted from a historical perspective, tracing the biological connections of computer vision models starting with the basic artificial neuron to modern technologies such as deep convolutional neural network (CNN) and spiking neural networks (SNN). One spotlight of the survey is a discussion on biologically plausible neural networks and bio-inspired unsupervised learning mechanisms adapted for computer vision tasks in recent times.
Collapse
Affiliation(s)
- Seba Susan
- Department of Information Technology, Delhi Technological University, Delhi, India.
| |
Collapse
|
36
|
Hiramoto M, Cline HT. Identification of movie encoding neurons enables movie recognition AI. Proc Natl Acad Sci U S A 2024; 121:e2412260121. [PMID: 39560649 PMCID: PMC11621835 DOI: 10.1073/pnas.2412260121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2024] [Accepted: 09/12/2024] [Indexed: 11/20/2024] Open
Abstract
Natural visual scenes are dominated by spatiotemporal image dynamics, but how the visual system integrates "movie" information over time is unclear. We characterized optic tectal neuronal receptive fields using sparse noise stimuli and reverse correlation analysis. Neurons recognized movies of ~200-600 ms durations with defined start and stop stimuli. Movie durations from start to stop responses were tuned by sensory experience though a hierarchical algorithm. Neurons encoded families of image sequences following trigonometric functions. Spike sequence and information flow suggest that repetitive circuit motifs underlie movie detection. Principles of frog topographic retinotectal plasticity and cortical simple cells are employed in machine learning networks for static image recognition, suggesting that discoveries of principles of movie encoding in the brain, such as how image sequences and duration are encoded, may benefit movie recognition technology. We built and trained a machine learning network that mimicked neural principles of visual system movie encoders. The network, named MovieNet, outperformed current machine learning image recognition networks in classifying natural movie scenes, while reducing data size and steps to complete the classification task. This study reveals how movie sequences and time are encoded in the brain and demonstrates that brain-based movie processing principles enable efficient machine learning.
Collapse
Affiliation(s)
- Masaki Hiramoto
- Department of Neuroscience, Dorris Neuroscience Center, Scripps Research Institute, La Jolla, CA92037
| | - Hollis T. Cline
- Department of Neuroscience, Dorris Neuroscience Center, Scripps Research Institute, La Jolla, CA92037
| |
Collapse
|
37
|
Avanzo M, Stancanello J, Pirrone G, Drigo A, Retico A. The Evolution of Artificial Intelligence in Medical Imaging: From Computer Science to Machine and Deep Learning. Cancers (Basel) 2024; 16:3702. [PMID: 39518140 PMCID: PMC11545079 DOI: 10.3390/cancers16213702] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2024] [Revised: 10/26/2024] [Accepted: 10/29/2024] [Indexed: 11/16/2024] Open
Abstract
Artificial intelligence (AI), the wide spectrum of technologies aiming to give machines or computers the ability to perform human-like cognitive functions, began in the 1940s with the first abstract models of intelligent machines. Soon after, in the 1950s and 1960s, machine learning algorithms such as neural networks and decision trees ignited significant enthusiasm. More recent advancements include the refinement of learning algorithms, the development of convolutional neural networks to efficiently analyze images, and methods to synthesize new images. This renewed enthusiasm was also due to the increase in computational power with graphical processing units and the availability of large digital databases to be mined by neural networks. AI soon began to be applied in medicine, first through expert systems designed to support the clinician's decision and later with neural networks for the detection, classification, or segmentation of malignant lesions in medical images. A recent prospective clinical trial demonstrated the non-inferiority of AI alone compared with a double reading by two radiologists on screening mammography. Natural language processing, recurrent neural networks, transformers, and generative models have both improved the capabilities of making an automated reading of medical images and moved AI to new domains, including the text analysis of electronic health records, image self-labeling, and self-reporting. The availability of open-source and free libraries, as well as powerful computing resources, has greatly facilitated the adoption of deep learning by researchers and clinicians. Key concerns surrounding AI in healthcare include the need for clinical trials to demonstrate efficacy, the perception of AI tools as 'black boxes' that require greater interpretability and explainability, and ethical issues related to ensuring fairness and trustworthiness in AI systems. Thanks to its versatility and impressive results, AI is one of the most promising resources for frontier research and applications in medicine, in particular for oncological applications.
Collapse
Affiliation(s)
- Michele Avanzo
- Medical Physics Department, Centro di Riferimento Oncologico di Aviano (CRO) IRCCS, 33081 Aviano, Italy; (G.P.); (A.D.)
| | | | - Giovanni Pirrone
- Medical Physics Department, Centro di Riferimento Oncologico di Aviano (CRO) IRCCS, 33081 Aviano, Italy; (G.P.); (A.D.)
| | - Annalisa Drigo
- Medical Physics Department, Centro di Riferimento Oncologico di Aviano (CRO) IRCCS, 33081 Aviano, Italy; (G.P.); (A.D.)
| | - Alessandra Retico
- National Institute for Nuclear Physics (INFN), Pisa Division, 56127 Pisa, Italy;
| |
Collapse
|
38
|
Xu Y, Quan R, Xu W, Huang Y, Chen X, Liu F. Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches. Bioengineering (Basel) 2024; 11:1034. [PMID: 39451409 PMCID: PMC11505408 DOI: 10.3390/bioengineering11101034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2024] [Revised: 10/08/2024] [Accepted: 10/11/2024] [Indexed: 10/26/2024] Open
Abstract
Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.
Collapse
Affiliation(s)
- Yan Xu
- School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol BS8 1QU, UK; (Y.X.); (R.Q.); (W.X.)
| | - Rixiang Quan
- School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol BS8 1QU, UK; (Y.X.); (R.Q.); (W.X.)
| | - Weiting Xu
- School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol BS8 1QU, UK; (Y.X.); (R.Q.); (W.X.)
| | - Yi Huang
- Bristol Medical School, University of Bristol, Bristol BS8 1UD, UK;
| | - Xiaolong Chen
- Department of Mechanical, Materials and Manufacturing Engineering, University of Nottingham, Nottingham NG7 2RD, UK;
| | - Fengyuan Liu
- School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol BS8 1QU, UK; (Y.X.); (R.Q.); (W.X.)
| |
Collapse
|
39
|
Solé R, Kempes CP, Corominas-Murtra B, De Domenico M, Kolchinsky A, Lachmann M, Libby E, Saavedra S, Smith E, Wolpert D. Fundamental constraints to the logic of living systems. Interface Focus 2024; 14:20240010. [PMID: 39464646 PMCID: PMC11503024 DOI: 10.1098/rsfs.2024.0010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2024] [Revised: 06/12/2024] [Accepted: 08/21/2024] [Indexed: 10/29/2024] Open
Abstract
It has been argued that the historical nature of evolution makes it a highly path-dependent process. Under this view, the outcome of evolutionary dynamics could have resulted in organisms with different forms and functions. At the same time, there is ample evidence that convergence and constraints strongly limit the domain of the potential design principles that evolution can achieve. Are these limitations relevant in shaping the fabric of the possible? Here, we argue that fundamental constraints are associated with the logic of living matter. We illustrate this idea by considering the thermodynamic properties of living systems, the linear nature of molecular information, the cellular nature of the building blocks of life, multicellularity and development, the threshold nature of computations in cognitive systems and the discrete nature of the architecture of ecosystems. In all these examples, we present available evidence and suggest potential avenues towards a well-defined theoretical formulation.
Collapse
Affiliation(s)
- Ricard Solé
- ICREA-Complex Systems Lab, Universitat Pompeu Fabra, Dr Aiguader 88, Barcelona08003, Spain
- Institut de Biologia Evolutiva, CSIC-UPF, Pg Maritim de la Barceloneta 37, Barcelona08003, Spain
- European Centre for Living Technology, Sestiere Dorsoduro, 3911, Venezia VE30123, Italy
- Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, NM87501, USA
| | | | | | - Manlio De Domenico
- Complex Multilayer Networks Lab, Department of Physics and Astronomy ‘Galileo Galilei’, University of Padua, Via Marzolo 8, Padova35131, Italy
- Padua Center for Network Medicine, University of Padua, Via Marzolo 8, Padova35131, Italy
| | - Artemy Kolchinsky
- ICREA-Complex Systems Lab, Universitat Pompeu Fabra, Dr Aiguader 88, Barcelona08003, Spain
- Universal Biology Institute, Graduate School of Science, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo113-0033, Japan
| | | | - Eric Libby
- Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, NM87501, USA
- Department of Mathematics and Mathematical Statistics, Umeå University, Umeå90187, Sweden
| | - Serguei Saavedra
- Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, NM87501, USA
- Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Eric Smith
- Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, NM87501, USA
- Department of Biology, Georgia Institute of Technology, Atlanta, GA30332, USA
- Earth-Life Science Institute, Tokyo Institute of Technology, Tokyo152-8550, Japan
| | - David Wolpert
- Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, NM87501, USA
| |
Collapse
|
40
|
Xu L, Li Y, Weng X, Shi J, Feng H, Liu X, Zhou G. A Monitoring Device and Grade Prediction System for Grain Mildew. SENSORS (BASEL, SWITZERLAND) 2024; 24:6556. [PMID: 39460037 PMCID: PMC11511114 DOI: 10.3390/s24206556] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/24/2024] [Revised: 10/01/2024] [Accepted: 10/08/2024] [Indexed: 10/28/2024]
Abstract
Mildew infestation is a significant cause of loss during grain storage. The growth and metabolism of mildew leads to changes in gas composition and temperature within granaries. Recent advances in sensor technology and machine learning enable the prediction of grain mildew during storage. Current research primarily focuses on predicting mildew occurrence or grading using simple machine learning methods, without in-depth exploration of the time series characteristics of mildew process data. A monitoring device was designed and developed to capture high-quality microenvironment parameters and image data during a simulated mildew process experiment. Using the "Yongyou 15" rice varieties from Zhejiang Province, five simulation experiments were conducted under varying temperature and humidity conditions between January and May 2023. Mildew grades were defined through manual analysis to construct a multimodal dataset for the rice mildew process. This study proposes a combined model (CNN-LSTM-A) that integrates convolutional neural networks (CNN), long short-term memory (LSTM) networks, and attention mechanisms to predict the mildew grade of stored rice. The proposed model was compared with LSTM, CNN-LSTM, and LSTM-Attention models. The results indicate that the proposed model outperforms the others, achieving a prediction accuracy of 98%. The model demonstrates superior accuracy and more stable performance. The generalization performance of the prediction model was evaluated using four experimental datasets with varying storage temperature and humidity conditions. The results show that the model achieves optimal prediction stability when the training set contains similar storage temperatures, with prediction accuracy exceeding 99.8%. This indicates that the model can effectively predict the mildew grades in rice under varying environmental conditions, demonstrating significant potential for grain mildew prediction and early warning systems.
Collapse
Affiliation(s)
- Lei Xu
- College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China; (L.X.); (Y.L.); (X.W.)
- Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou 311300, China
- China Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou 311300, China
| | - Yane Li
- College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China; (L.X.); (Y.L.); (X.W.)
- Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou 311300, China
- China Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou 311300, China
| | - Xiang Weng
- College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China; (L.X.); (Y.L.); (X.W.)
- Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou 311300, China
- China Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou 311300, China
| | - Jiankai Shi
- School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China
| | - Hailin Feng
- College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China; (L.X.); (Y.L.); (X.W.)
- Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province, Hangzhou 311300, China
- China Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment, Hangzhou 311300, China
| | - Xingquan Liu
- College of Food and Health, Zhejiang A&F University, Hangzhou 311300, China;
- National Grain Industry (High-Quality Rice Storage in Temperate and Humid Region) Technology Innovation Center, Zhejiang A&F University, Hangzhou 311300, China
| | - Guoxin Zhou
- College of Modern Agriculture, Zhejiang A&F University, Hangzhou 311300, China;
| |
Collapse
|
41
|
Zhang L, Deng T, Pan S, Zhang M, Zhang Y, Yang C, Yang X, Tian G, Mi J. DeepO-GlcNAc: a web server for prediction of protein O-GlcNAcylation sites using deep learning combined with attention mechanism. Front Cell Dev Biol 2024; 12:1456728. [PMID: 39450274 PMCID: PMC11500328 DOI: 10.3389/fcell.2024.1456728] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2024] [Accepted: 09/26/2024] [Indexed: 10/26/2024] Open
Abstract
Introduction Protein O-GlcNAcylation is a dynamic post-translational modification involved in major cellular processes and associated with many human diseases. Bioinformatic prediction of O-GlcNAc sites before experimental validation is a challenge task in O-GlcNAc research. Recent advancements in deep learning algorithms and the availability of O-GlcNAc proteomics data present an opportunity to improve O-GlcNAc site prediction. Objectives This study aims to develop a deep learning-based tool to improve O-GlcNAcylation site prediction. Methods We construct an annotated unbalanced O-GlcNAcylation data set and propose a new deep learning framework, DeepO-GlcNAc, using Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) combined with attention mechanism. Results The ablation study confirms that the additional model components in DeepO-GlcNAc, such as attention mechanisms and LSTM, contribute positively to improving prediction performance. Our model demonstrates strong robustness across five cross-species datasets, excluding humans. We also compare our model with three external predictors using an independent dataset. Our results demonstrated that DeepO-GlcNAc outperforms the external predictors, achieving an accuracy of 92%, an average precision of 72%, a MCC of 0.60, and an AUC of 92% in ROC analysis. Moreover, we have implemented DeepO-GlcNAc as a web server to facilitate further investigation and usage by the scientific community. Conclusion Our work demonstrates the feasibility of utilizing deep learning for O-GlcNAc site prediction and provides a novel tool for O-GlcNAc investigation.
Collapse
Affiliation(s)
- Liyuan Zhang
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
| | - Tingzhi Deng
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian, China
| | - Shuijing Pan
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
| | - Minghui Zhang
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
| | - Yusen Zhang
- School of Mathematics and Statistics, Shandong University, Weihai, Shandong, China
| | - Chunhua Yang
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
| | - Xiaoyong Yang
- Department of Comparative Medicine, Department of Cellular and Molecular Physiology, Yale University, New Haven, CT, United States
| | - Geng Tian
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
| | - Jia Mi
- Shandong Technology Innovation Center of Molecular Targeting and Intelligent Diagnosis and Treatment, Binzhou Medical University, Yantai, Shandong, China
| |
Collapse
|
42
|
Simony E, Grossman S, Malach R. Brain-machine convergent evolution: Why finding parallels between brain and artificial systems is informative. Proc Natl Acad Sci U S A 2024; 121:e2319709121. [PMID: 39356668 PMCID: PMC11474058 DOI: 10.1073/pnas.2319709121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/04/2024] Open
Abstract
Central nervous system neurons manifest a rich diversity of selectivity profiles-whose precise role is still poorly understood. Following the striking success of artificial networks, a major debate has emerged concerning their usefulness in explaining neuronal properties. Here we propose that finding parallels between artificial and neuronal networks is informative precisely because these systems are so different from each other. Our argument is based on an extension of the concept of convergent evolution-well established in biology-to the domain of artificial systems. Applying this concept to different areas and levels of the cortical hierarchy can be a powerful tool for elucidating the functional role of well-known cortical selectivities. Importantly, we further demonstrate that such parallels can uncover novel functionalities by showing that grid cells in the entorhinal cortex can be modeled to function as a set of basis functions in a lossy representation such as the well-known JPEG compression. Thus, contrary to common intuition, here we illustrate that finding parallels with artificial systems provides novel and informative insights, particularly in those cases that are far removed from realistic brain biology.
Collapse
Affiliation(s)
- Erez Simony
- Department of Brain Sciences, Weizmann Institute of Science, Rehovot76100, Israel
- Faculty of Electrical Engineering, Holon Institute of Technology, Holon5810201, Israel
| | - Shany Grossman
- Max Planck Institute for Human Development, Berlin14195, Germany
- Max Planck University College London Centre for Computational Psychiatry and Ageing Research, Berlin14195, Germany
- Institute of Psychology, Universitsät Hamburg, Hamburg20146, Germany
| | - Rafael Malach
- Department of Brain Sciences, Weizmann Institute of Science, Rehovot76100, Israel
| |
Collapse
|
43
|
Lu J, Zhu M, Qin K, Ma X. YOLO-LFPD: A Lightweight Method for Strip Surface Defect Detection. Biomimetics (Basel) 2024; 9:607. [PMID: 39451813 PMCID: PMC11506614 DOI: 10.3390/biomimetics9100607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2024] [Revised: 10/01/2024] [Accepted: 10/01/2024] [Indexed: 10/26/2024] Open
Abstract
Strip steel surface defect recognition research has important research significance in industrial production. Aiming at the problems of defect feature extraction, slow detection speed, and insufficient datasets, YOLOv5 is improved on the basis of YOLOv5, and the YOLO-LFPD (lightweight fine particle detection) model is proposed. By introducing the RepVGG (Re-param VGG) module, the robustness of the model is enhanced, and the expressive ability of the model is improved. FasterNet is used to replace the backbone network, which ensures accuracy and accelerates the inference speed, making the model more suitable for real-time monitoring. The use of pruning, a GA genetic algorithm with OTA loss function, further reduces the model size while better learning the strip steel defect feature information, thus improving the generalisation ability and accuracy of the model. The experimental results show that the introduction of the RepVGG module and the use of FasterNet can well improve the model performance, with a reduction of 48% in the number of parameters, a reduction of 13% in the number of GFLOPs, an inference time of 77% of the original, and an optimal accuracy compared with the network models in recent years. The experimental results on the NEU-DET dataset show that the accuracy of YOLO-LFPD is improved by 3% to 81.2%, which is better than other models, and provides new ideas and references for the lightweight strip steel surface defect detection scenarios and application deployment.
Collapse
Affiliation(s)
- Jianbo Lu
- Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal University, Nanning 530001, China;
| | - Mingrui Zhu
- Guangxi Zhuang Autonomous Region Forestry Survey and Design Institute, Nanning 530011, China;
| | - Kaixian Qin
- Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision, Nanning Normal University, Nanning 530001, China;
| | - Xiaoya Ma
- Department of Logistics Management and Engineering, Nanning Normal University, Nanning 530023, China;
| |
Collapse
|
44
|
Muller L, Churchland PS, Sejnowski TJ. Transformers and cortical waves: encoders for pulling in context across time. Trends Neurosci 2024; 47:788-802. [PMID: 39341729 PMCID: PMC11936488 DOI: 10.1016/j.tins.2024.08.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Revised: 06/07/2024] [Accepted: 08/09/2024] [Indexed: 10/01/2024]
Abstract
The capabilities of transformer networks such as ChatGPT and other large language models (LLMs) have captured the world's attention. The crucial computational mechanism underlying their performance relies on transforming a complete input sequence - for example, all the words in a sentence - into a long 'encoding vector' that allows transformers to learn long-range temporal dependencies in naturalistic sequences. Specifically, 'self-attention' applied to this encoding vector enhances temporal context in transformers by computing associations between pairs of words in the input sequence. We suggest that waves of neural activity traveling across single cortical areas, or multiple regions on the whole-brain scale, could implement a similar encoding principle. By encapsulating recent input history into a single spatial pattern at each moment in time, cortical waves may enable a temporal context to be extracted from sequences of sensory inputs, the same computational principle as that used in transformers.
Collapse
Affiliation(s)
- Lyle Muller
- Department of Mathematics, Western University, London, Ontario, Canada; Fields Laboratory for Network Science, Fields Institute, Toronto, Ontario, Canada.
| | - Patricia S Churchland
- Department of Philosophy, University of California at San Diego, San Diego, CA, USA.
| | - Terrence J Sejnowski
- Computational Neurobiology Laboratory, Salk Institute for Biological Studies, San Diego, CA, USA; Department of Neurobiology, University of California at San Diego, San Diego, CA, USA.
| |
Collapse
|
45
|
Deng Z, Yu Y, Zhou Y, Zhou J, Xie M, Tao B, Lai Y, Wen J, Fan Z, Liu X, Zhao D, Feng LW, Cheng Y, Huang CG, Yue W, Huang W. Ternary Logic Circuit and Neural Network Integration via Small Molecule-Based Antiambipolar Vertical Electrochemical Transistor. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2024; 36:e2405115. [PMID: 39136124 DOI: 10.1002/adma.202405115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/09/2024] [Revised: 07/09/2024] [Indexed: 10/11/2024]
Abstract
Circuits based on organic electrochemical transistors (OECTs) have great potential in the fields of biosensors and artificial neural computation due to their biocompatibility and neural similarity. However, the integration of OECT-based circuits lags far behind other emerging electronics. Here, ternary inverters based on antiambipolar vertical OECTs (vOECTs) and their integration with the establishment of neural networks are demonstrated. Specifically, by adopting a small molecule (t-gdiPDI) as the channel of vOECT, high antiambipolar performance, with current density of 33.9 ± 2.1 A cm-2 under drain voltage of 0.1 V, peak voltage ≈0 V, low driving voltage < ± 0.6 V, and current on/off ratio > 106, are realized. Consequently, vertically stacked ternary circuits based solely on OECTs are constructed for the first time, showing three distinct logical states and high integration density. By further developing inverter array as the internal fundamental units of ternary weight network hardware circuits for ternary processing and computation, it demonstrates excellent data classification and recognition capabilities. This work demonstrates the possibility of constructing multi-valued logic circuits by OECTs and promotes a new strategy for high-density integration and multivalued computing systems based on organic circuits.
Collapse
Affiliation(s)
- Ziyi Deng
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Yaping Yu
- State Key Laboratory of Optoelectronic Materials and Technologies Key Laboratory for Polymeric Composite and Functional Materials of Ministry of Education, Guangzhou Key Laboratory of Flexible Electronic Materials and Wearable Devices, School of Materials and Engineering, Sun Yat-Sen University, Guangzhou, 510275, China
| | - Yixin Zhou
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Jinhao Zhou
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Miao Xie
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Baining Tao
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Yueping Lai
- Key Laboratory of Green Chemistry&Technology, Ministry of Education, College of Chemistry, Sichuan University, Chengdu, 610065, China
| | - Jinjie Wen
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Zefeng Fan
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Xiangjun Liu
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Dan Zhao
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Liang-Wen Feng
- Key Laboratory of Green Chemistry&Technology, Ministry of Education, College of Chemistry, Sichuan University, Chengdu, 610065, China
| | - Yuhua Cheng
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Cheng-Geng Huang
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| | - Wan Yue
- State Key Laboratory of Optoelectronic Materials and Technologies Key Laboratory for Polymeric Composite and Functional Materials of Ministry of Education, Guangzhou Key Laboratory of Flexible Electronic Materials and Wearable Devices, School of Materials and Engineering, Sun Yat-Sen University, Guangzhou, 510275, China
| | - Wei Huang
- School of Automation Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, 611700, China
| |
Collapse
|
46
|
Azhideh A, Pooyan A, Alipour E, Haseli S, Hosseini N, Chalian M. The Role of Artificial Intelligence in Osteoarthritis. Semin Roentgenol 2024; 59:518-525. [PMID: 39490044 DOI: 10.1053/j.ro.2024.07.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2024] [Revised: 07/11/2024] [Accepted: 07/12/2024] [Indexed: 11/05/2024]
Affiliation(s)
- Arash Azhideh
- Department of Radiology, Division of Muscluskeletal and Intervention, University of Washington, Seattle, WA
| | - Atefe Pooyan
- Department of Radiology, Division of Muscluskeletal and Intervention, University of Washington, Seattle, WA
| | - Ehsan Alipour
- Department of Radiology, Division of Muscluskeletal and Intervention, University of Washington, Seattle, WA
| | - Sara Haseli
- Department of Radiology, Division of Muscluskeletal and Intervention, University of Washington, Seattle, WA
| | - Nastaran Hosseini
- Department of Radiology, Division of Muscluskeletal and Intervention, University of Washington, Seattle, WA
| | - Majid Chalian
- Department of Radiology, Division of Muscluskeletal and Intervention, University of Washington, Seattle, WA.
| |
Collapse
|
47
|
Seung HS. Predicting visual function by interpreting a neuronal wiring diagram. Nature 2024; 634:113-123. [PMID: 39358524 PMCID: PMC11446822 DOI: 10.1038/s41586-024-07953-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Accepted: 08/15/2024] [Indexed: 10/04/2024]
Abstract
As connectomics advances, it will become commonplace to know far more about the structure of a nervous system than about its function. The starting point for many investigations will become neuronal wiring diagrams, which will be interpreted to make theoretical predictions about function. Here I demonstrate this emerging approach with the Drosophila optic lobe, analysing its structure to predict that three Dm3 (refs. 1-4) and three TmY (refs. 2,4) cell types are part of a circuit that serves the function of form vision. Receptive fields are predicted from connectivity, and suggest that the cell types encode the local orientation of a visual stimulus. Extraclassical5,6 receptive fields are also predicted, with implications for robust orientation tuning7, position invariance8,9 and completion of noisy or illusory contours10,11. The TmY types synapse onto neurons that project from the optic lobe to the central brain12,13, which are conjectured to compute conjunctions and disjunctions of oriented features. My predictions can be tested through neurophysiology, which would constrain the parameters and biophysical mechanisms in neural network models of fly vision14.
Collapse
Affiliation(s)
- H Sebastian Seung
- Neuroscience Institute and Computer Science Department, Princeton University, Princeton, NJ, USA.
| |
Collapse
|
48
|
Matsliah A, Yu SC, Kruk K, Bland D, Burke AT, Gager J, Hebditch J, Silverman B, Willie KP, Willie R, Sorek M, Sterling AR, Kind E, Garner D, Sancer G, Wernet MF, Kim SS, Murthy M, Seung HS. Neuronal parts list and wiring diagram for a visual system. Nature 2024; 634:166-180. [PMID: 39358525 PMCID: PMC11446827 DOI: 10.1038/s41586-024-07981-1] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Accepted: 08/21/2024] [Indexed: 10/04/2024]
Abstract
A catalogue of neuronal cell types has often been called a 'parts list' of the brain1, and regarded as a prerequisite for understanding brain function2,3. In the optic lobe of Drosophila, rules of connectivity between cell types have already proven to be essential for understanding fly vision4,5. Here we analyse the fly connectome to complete the list of cell types intrinsic to the optic lobe, as well as the rules governing their connectivity. Most new cell types contain 10 to 100 cells, and integrate information over medium distances in the visual field. Some existing type families (Tm, Li, and LPi)6-10 at least double in number of types. A new serpentine medulla (Sm) interneuron family contains more types than any other. Three families of cross-neuropil types are revealed. The consistency of types is demonstrated by analysing the distances in high-dimensional feature space, and is further validated by algorithms that select small subsets of discriminative features. We use connectivity to hypothesize about the functional roles of cell types in motion, object and colour vision. Connectivity with 'boundary types' that straddle the optic lobe and central brain is also quantified. We showcase the advantages of connectomic cell typing: complete and unbiased sampling, a rich array of features based on connectivity and reduction of the connectome to a substantially simpler wiring diagram of cell types, with immediate relevance for brain function and development.
Collapse
Affiliation(s)
- Arie Matsliah
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - Szi-Chieh Yu
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - Krzysztof Kruk
- Independent researcher, Kielce, Poland
- Eyewire, Boston, MA, USA
| | - Doug Bland
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - Austin T Burke
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - Jay Gager
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - James Hebditch
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - Ben Silverman
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | | | - Ryan Willie
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
| | - Marissa Sorek
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
- Eyewire, Boston, MA, USA
| | - Amy R Sterling
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA
- Eyewire, Boston, MA, USA
| | - Emil Kind
- Institut für Biologie-Neurobiologie, Freie Universität Berlin, Berlin, Germany
| | - Dustin Garner
- Molecular, Cellular and Developmental Biology, University of California, Santa Barbara, Santa Barbara, CA, USA
| | - Gizem Sancer
- Department of Neuroscience, Yale University, New Haven, CT, USA
| | - Mathias F Wernet
- Institut für Biologie-Neurobiologie, Freie Universität Berlin, Berlin, Germany
| | - Sung Soo Kim
- Molecular, Cellular and Developmental Biology, University of California, Santa Barbara, Santa Barbara, CA, USA
| | - Mala Murthy
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA.
| | - H Sebastian Seung
- Princeton Neuroscience Institute, Princeton University, Princeton, NJ, USA.
- Computer Science Department, Princeton University, Princeton, NJ, USA.
| |
Collapse
|
49
|
Sharma A, Lysenko A, Jia S, Boroevich KA, Tsunoda T. Advances in AI and machine learning for predictive medicine. J Hum Genet 2024; 69:487-497. [PMID: 38424184 PMCID: PMC11422165 DOI: 10.1038/s10038-024-01231-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 02/04/2024] [Accepted: 02/12/2024] [Indexed: 03/02/2024]
Abstract
The field of omics, driven by advances in high-throughput sequencing, faces a data explosion. This abundance of data offers unprecedented opportunities for predictive modeling in precision medicine, but also presents formidable challenges in data analysis and interpretation. Traditional machine learning (ML) techniques have been partly successful in generating predictive models for omics analysis but exhibit limitations in handling potential relationships within the data for more accurate prediction. This review explores a revolutionary shift in predictive modeling through the application of deep learning (DL), specifically convolutional neural networks (CNNs). Using transformation methods such as DeepInsight, omics data with independent variables in tabular (table-like, including vector) form can be turned into image-like representations, enabling CNNs to capture latent features effectively. This approach not only enhances predictive power but also leverages transfer learning, reducing computational time, and improving performance. However, integrating CNNs in predictive omics data analysis is not without challenges, including issues related to model interpretability, data heterogeneity, and data size. Addressing these challenges requires a multidisciplinary approach, involving collaborations between ML experts, bioinformatics researchers, biologists, and medical doctors. This review illuminates these complexities and charts a course for future research to unlock the full predictive potential of CNNs in omics data analysis and related fields.
Collapse
Affiliation(s)
- Alok Sharma
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Institute for Integrated and Intelligent Systems, Griffith University, Queensland, Australia.
| | - Artem Lysenko
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
| | - Shangru Jia
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan
| | - Keith A Boroevich
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan
| | - Tatsuhiko Tsunoda
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan.
| |
Collapse
|
50
|
Cho SB, Soleh HM, Choi JW, Hwang WH, Lee H, Cho YS, Cho BK, Kim MS, Baek I, Kim G. Recent Methods for Evaluating Crop Water Stress Using AI Techniques: A Review. SENSORS (BASEL, SWITZERLAND) 2024; 24:6313. [PMID: 39409355 PMCID: PMC11478660 DOI: 10.3390/s24196313] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/16/2024] [Revised: 09/26/2024] [Accepted: 09/26/2024] [Indexed: 10/20/2024]
Abstract
This study systematically reviews the integration of artificial intelligence (AI) and remote sensing technologies to address the issue of crop water stress caused by rising global temperatures and climate change; in particular, it evaluates the effectiveness of various non-destructive remote sensing platforms (RGB, thermal imaging, and hyperspectral imaging) and AI techniques (machine learning, deep learning, ensemble methods, GAN, and XAI) in monitoring and predicting crop water stress. The analysis focuses on variability in precipitation due to climate change and explores how these technologies can be strategically combined under data-limited conditions to enhance agricultural productivity. Furthermore, this study is expected to contribute to improving sustainable agricultural practices and mitigating the negative impacts of climate change on crop yield and quality.
Collapse
Affiliation(s)
- Soo Been Cho
- Department of Biosystems Engineering, College of Agricultural and Life Sciences, Gyeongsang National University, 501, Jinju-daero, Jinju-si 52828, Gyeongsangnam-do, Republic of Korea; (S.B.C.); (H.M.S.); (J.W.C.)
| | - Hidayat Mohamad Soleh
- Department of Biosystems Engineering, College of Agricultural and Life Sciences, Gyeongsang National University, 501, Jinju-daero, Jinju-si 52828, Gyeongsangnam-do, Republic of Korea; (S.B.C.); (H.M.S.); (J.W.C.)
| | - Ji Won Choi
- Department of Biosystems Engineering, College of Agricultural and Life Sciences, Gyeongsang National University, 501, Jinju-daero, Jinju-si 52828, Gyeongsangnam-do, Republic of Korea; (S.B.C.); (H.M.S.); (J.W.C.)
| | - Woon-Ha Hwang
- Division of Crop Production and Physiology, National Institute of Crop Science, Rural Development Administration, 100, Nongsaengmyeong-ro, Iseo-myeon, Wanju-gun 55365, Jeonbuk-do, Republic of Korea;
| | - Hoonsoo Lee
- Department of Biosystems Engineering, College of Agriculture, Life and Environment Sciences, Chungbuk National University, 1 Chungdae-ro, Seowon-gu, Cheongju-si 28644, Chungbuk-do, Republic of Korea
| | - Young-Son Cho
- Department of Smart Agro-Industry, College of Life Science, Gyeongsang National University, Dongjin-ro 33, Jinju-si 52725, Gyeongsangnam-do, Republic of Korea;
| | - Byoung-Kwan Cho
- Department of Biosystems Machinery Engineering, Chungnam National University, Daejeon 34134, Republic of Korea;
| | - Moon S. Kim
- Environmental Microbial and Food Safety Laboratory, Agricultural Research Service, Department of Agriculture, Powder Mill Road, BARC-East, Bldg 303, Beltsville, MD 20705, USA; (M.S.K.); (I.B.)
| | - Insuck Baek
- Environmental Microbial and Food Safety Laboratory, Agricultural Research Service, Department of Agriculture, Powder Mill Road, BARC-East, Bldg 303, Beltsville, MD 20705, USA; (M.S.K.); (I.B.)
| | - Geonwoo Kim
- Department of Biosystems Engineering, College of Agricultural and Life Sciences, Gyeongsang National University, 501, Jinju-daero, Jinju-si 52828, Gyeongsangnam-do, Republic of Korea; (S.B.C.); (H.M.S.); (J.W.C.)
- Institute of Agriculture and Life Sciences, Gyeongsang National University, 501, Jinju-daero, Jinju-si 52828, Gyeongsangnam-do, Republic of Korea
| |
Collapse
|