Cervical cancer still has high incidence and mortality rates worldwide. This study aimed to evaluate the prognostic value of anoikis-related genes (ARGs) and develop a risk scoring model for accurate survival prediction in cervical cancer patients.

The expression profiles of cervical cancer tissue and survival data were downloaded from TCGA-CESC and CGCI-HTMCP-CC. We identified 83 ARGs significantly associated with patients' survival. Subsequently, we developed a risk-scoring model based on 10 key genes. We assessed the predictive performance of our model by survival analysis, ROC curve analysis, and a nomogram that incorporated clinical factors. Additionally, we validated the expression of Granzyme B (GZMB) by immunohistochemical staining. Furthermore, we compared the biological processes and pathway enrichment in high-risk and low-risk patient groups, using differential gene expression and functional enrichment analysis. Finally, we investigated the immune microenvironment of patients in both high-risk and low-risk groups.

Patients in the high-risk group had significantly poorer survival compared to those in the low-risk group. The immunohistochemical results suggested that GZMB was associated with the prognosis of cervical cancer patients. The risk scoring model showed high accuracy in predicting the prognosis of cervical cancer patients. Differential gene expression analysis revealed enriched pathways related to tumor invasion and metastasis in the high-risk group. Conversely, the low-risk group showed a strong association with the activation of immune response pathways.

This study concluded that anoikis-related genes played a crucial role in determining the prognosis of individuals with cervical cancer. This discovery not only presented potential biomarkers but also provided valuable insights for informing treatment strategies. The risk scoring model may assist clinicians in better identifying high-risk patients and personalizing treatment plans.

Cancer continues to pose significant challenges in healthcare due to the complex nature of tumor progression. In this digital era, artificial intelligence has emerged as a powerful tool that can potentially transform multiple aspects of cancer care.

In the current study, we conducted a comprehensive literature search across databases such as PubMed, Scopus, and IEEE Xplore. Studies published between 2014 and 2024 were considered. The selection process involved a systematic screening based on predefined inclusion and exclusion criteria. Studies were included if they focused on applying machine learning techniques for tumor progression modeling, diagnosis, or prognosis, were published in peer-reviewed journals or conference proceedings, were available in English, and presented experimental results, simulations, or real-world applications. In total, 87 papers were included in this review, ensuring a diverse and representative analysis of the field. A workflow is included to illustrate the procedure followed to achieve this aim.

This review delves into the cutting-edge applications of machine learning (ML), including supervised learning methods like Support Vector Machines and Random Forests, as well as advanced deep learning (DL). It focuses on the integration of ML into oncological research, particularly its application in tumor progression through the tumor microenvironment, genetic data, histopathological data, and radiological data. This work provides a critical analysis of the challenges associated with the reliability and accuracy of ML models, which limit their clinical integration.

This review offers expert insights and strategies to address these challenges in order to improve the robustness and applicability of ML in real-world oncology settings. By emphasizing the potential for personalized cancer treatment and bridging gaps between technology and clinical needs, this review serves as a comprehensive resource for advancing the integration of ML models into clinical oncology.

Radiologists are witnessing astonishing innovation and advancement of CT technologies and their clinical applications. This review highlights how photon-counting CT (PCCT), upright CT, and artificial intelligence (AI) may impact cardiothoracic CT applications for imaging and diagnosis. PCCT relies on new detectors that can bin the separate photon energies and allow for lower radiation dose and better spatial resolution. The clinical applications of PCCT in the coronary arteries are becoming the new standard for cardiac CT imaging. New upright CT has shown the benefits of imaging in the upright position and offers new insight into how the upright position affects biomechanics and physiology. Four-dimensional CT, which can be used to directly image perfusion, is challenging MRI and MR angiography for primacy in this area. The burgeoning role of AI and informatics is changing the way radiologists interpret and report many imaging examinations. The future is bright and promises lower radiation and intravenous contrast agent doses and higher spatial resolution, and will further incorporate deep learning to improve the effectiveness of CT.

Genetic studies have revealed hundreds of loci associated with bone-related phenotypes, including bone mineral density (BMD) and fracture risk. However, translating discovered loci into effective new therapies remains challenging. We review success stories including PCSK9-related drugs in cardiovascular disease and evidence supporting the use of human genetics to guide drug discovery, while highlighting advances in artificial intelligence and machine learning with the potential to improve target discovery in skeletal biology. These strategies are poised to improve how we integrate diverse data types, from genetic and electronic health records data to single-cell profiles and knowledge graphs. Such emerging computational methods can position bone genomics for a future of more precise, effective treatments, ultimately improving the outcomes for patients with common and rare skeletal disorders.

In principle, ML/AI-based algorithms should enable rapid and accurate cell segmentation in high-throughput settings. However, reliance on large training datasets, human input, computational expertise, and limited generalizability has prevented this goal of completely automated, high-throughput segmentation from being achieved. To overcome these roadblocks, we introduce an innovative self-supervised learning method (SSL) for pixel classification that does not require parameter tuning or curated data sets, and instead trains itself on the end-users' own data in a completely automated fashion, thus providing a more efficient cell segmentation approach for high-throughput, high-content image analysis. We demonstrate that our algorithm meets the criteria of being fully automated with versatility across various magnifications, optical modalities, and cell types. Moreover, our SSL algorithm is capable of identifying complex cellular structures and organelles, which are otherwise easily missed, thereby broadening the machine learning applications to high-content imaging. Our SSL technique displayed consistently high F1 scores across segmented cell images, with scores ranging from 0.771 to 0.888, matching or outperforming the popular Cellpose algorithm, which showed a greater F1 variance of 0.454 to 0.882, primarily due to more false negatives.

The investigation and diagnosis of hematologic malignancy using blood cell image analysis are major and emerging subjects that lie at the intersection of artificial intelligence and medical research. This survey systematically examines the state-of-the-art in blood cancer detection through image-based analysis, aimed at identifying the most effective computational strategies and highlighting emerging trends. This review focuses on three principal objectives, namely, to categorize and compare traditional machine learning (ML), deep learning (DL), and hybrid learning approaches; to evaluate performance metrics such as accuracy, precision, recall, and area under the ROC curve; and to identify methodological gaps and propose directions for future research. Methodologically, we organize the literature by categorizing the malignancy types-leukemia, lymphoma, and multiple myeloma-and particularizing the preprocessing steps, feature extraction techniques, network architectures, and ensemble strategies employed. For ML methods, we discuss classical classifiers including support vector machines and random forests; for DL, we analyze convolutional neural networks (e.g., AlexNet, VGG, and ResNet) and transformer-based models; and for hybrid systems, we examine combinations of CNNs with attention mechanisms or traditional classifiers. Our synthesis reveals that DL models consistently outperform ML baselines, achieving classification accuracies above 95% in benchmark datasets, with hybrid models pushing peak accuracy to 99.7%. However, challenges remain in data scarcity, class imbalance, and generalizability to clinical settings. We conclude by recommending the integration of multimodal data, semisupervised learning, and rigorous external validation to advance toward deployable diagnostic tools. This survey also provides a comprehensive roadmap for researchers and clinicians striving to harness AI for reliable hematologic cancer detection.

We developed and validated a magnetic resonance imaging (MRI)-based radiomics model for the classification of high-grade glioma (HGG) and determined the optimal machine learning (ML) approach. This retrospective analysis included 184 patients (59 grade III lesions and 125 grade IV lesions). Radiomics features were extracted from MRI with T1-weighted imaging (T1WI). The least absolute shrinkage and selection operator (LASSO) feature selection method and seven classification methods including logistic regression, XGBoost, Decision Tree, Random Forest (RF), Adaboost, Gradient Boosting Decision Tree, and Stacking fusion model were used to differentiate HGG. Performance was compared on AUC, sensitivity, accuracy, precision and specificity. In the non-fusion models, the best performance was achieved by using the XGBoost classifier, and using SMOTE to deal with the data imbalance to improve the performance of all the classifiers. The Stacking fusion model performed the best, with an AUC = 0.95 (sensitivity of 0.84; accuracy of 0.85; F1 score of 0.85). MRI-based quantitative radiomics features have good performance in identifying the classification of HGG. The XGBoost method outperforms the classifiers in the non-fusion model and the Stacking fusion model outperforms the non-fusion model.

We aimed to develop a machine learning (ML) model to preoperatively predict surgical difficulty for pheochromocytomas and paragangliomas (PPGLs) using clinical and radiomic features.

In this study, 212 patients with pathologically confirmed PPGLs were retrospectively enrolled and divided into training (n = 148) and validation cohorts (n = 64). Seven ML models (Classification and Regression Tree, K-Nearest Neighbors, Least Absolute Shrinkage and Selection Operator, Naïve Bayes, Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting) were trained using clinical parameters alone or combined with radiomics. Model performance was evaluated and compared through accuracy, sensitivity, specificity, F1 score, area under the curve (AUC), calibration curves, and decision curve analysis. Through comprehensive assessment, the optimal integrated model (clinical + radiomics) was identified and its predictive efficacy was subsequently compared with that of the clinical parameter model. Finally, SHapley Additive exPlanations (SHAP) was applied to enhance the interpretability of the optimal model by visualizing feature contributions.

Among all integrated models, the SVM model exhibited the most prominent performance, achieving AUC values of 0.96 in the training cohort and 0.85 in the validation cohort, while demonstrating statistically significant superiority over the clinical parameter model (p < 0.05). The SHAP analysis revealed that radiomic signature (Rad score) exerted the most substantial influence on the predictive outcomes, with age, body mass index, maximum tumor diameter, and preoperative heart rate also demonstrating statistically significant contributions to the model predictions.

The SVM model integrating clinical and radiomic features effectively predicts PPGL surgical difficulty, aiding preoperative risk stratification and personalized surgical planning to reduce operative risks.

The integration of artificial intelligence and personalized medicine is transforming HIV management by enhancing diagnostics, treatment optimization, and disease monitoring. Advances in machine learning, deep neural networks, and multi-omics data analysis enable precise prognostication, tailored antiretroviral therapy, and early detection of drug resistance. AI-driven models analyze vast genomic, proteomic, and clinical datasets to refine treatment strategies, predict disease progression, and pre-empt therapy failures. Additionally, AI-powered diagnostic tools, including deep learning imaging and natural language processing, improve screening accuracy, particularly in resource-limited settings. Despite these innovations, challenges such as data privacy, algorithmic bias, and the need for clinical validation remain. Successful integration of AI into HIV care requires robust regulatory frameworks, interdisciplinary collaboration, and equitable technology access. This review explores both the potential and limitations of AI in HIV management, emphasizing the need for ethical implementation and expanded research to maximize its impact. AI-driven approaches hold great promise for a more personalized, efficient, and effective future in HIV treatment and care.

The ingredients of traditional Chinese medicine (TCM) are complex and diverse and are often identified using the TCM systems pharmacology (TCMSP) database. However, the ingredients in this database exhibit significant homogeneity, which limits the comprehensive understanding of TCM's ingredient diversity and biological activity. Consequently, liquid chromatography-mass spectrometry (LC-MS) has become a key tool for the precise identification of TCM components.

In this study, the LC-MS was used to identify the components of a TCM herb. The identified components were then compared with the component data in the TCMSP database. A network pharmacological prediction of the components was subsequently performed.

An analysis of the four herb formula prescriptions (Ganmai Dazao decoction, Bazhen granule, Shaoyao Gancao decoction, and Zixue san) was conducted, revealing significant discrepancies between the LC-MS identification results and the components in the TCMSP database. The database components were found to be highly homogeneous.

This study underscores the pivotal function of LC-MS in the analysis of components of TCM, particularly in addressing issues of database homogeneity. The employment of LC-MS technology enhances the precision of ingredient identification and streamlines the identification of potential pharmacodynamic ingredients, thereby propelling TCM toward a more contemporary standing.

The field of artificial intelligence (AI) is expanding quickly. To mimic the structure and biological evolution of the human brain, AI was developed to enable computers to acquire knowledge and manipulate their surroundings. There have been notable developments in the use of AI in healthcare; it can enhance diagnosis and treatment in various medical specialties. The cost of prompt diagnosis and treatment is hampered by the absence of efficient, dependable, and reasonably priced detection and real-time monitoring. Smart health tracking systems integrating AI and nanoscience are an emerging frontier that solves these obstacles. Targeted delivery of drug systems, biosensing, imaging, and other diagnostic and therapeutic fields can widely benefit abundantly from nanoscience in healthcare. AI technology has the potential to expand biomedical applications by analyzing and interpreting biological data, speeding up drug discovery, and identifying novel molecules with predictive behavior. This review outlines the current obstacles and potential opportunities for delivering personal healthcare using AI-assisted clinical decision support systems.

BCS class II candidates pose challenges in drug development due to their low solubility and permeability. Researchers have explored various techniques; co-amorphous and solid dispersion are major approaches to enhance in-vitro drug solubility and dissolution. However, in-vivo oral bioavailability remains challenging. Physiologically based pharmacokinetic (PBPK) modeling with a detailed understanding of drug absorption, distribution, metabolism, and excretion (ADME) using a mechanistic approach is emerging. This review summarizes the fundamentals of the PBPK, dissolution-absorption models, parameterization of oral absorption for BCS class II drugs, and provides information about newly emerging artificial intelligence/machine learning (AI/ML) linked PBPK approaches with their advantages, disadvantages, challenges and areas of further exploration. Additionally, the fully integrated workflow for formulation design for investigational new drugs (INDs) and virtual bioequivalence for generic molecules falling under BCS-II are discussed.

Single-cell and spatial technologies have transformed our understanding of brain immunology, providing unprecedented insights into immune cell heterogeneity and spatial organisation within the central nervous system. These methods have uncovered complex cellular interactions, rare cell populations, and the dynamic immune landscape in neurological disorders. This review highlights recent advances in single-cell "omics" data analysis and discusses their applicability for brain immunology. Traditional statistical techniques, adapted for single-cell omics, have been crucial in categorizing cell types and identifying gene signatures, overcoming challenges posed by increasingly complex datasets. We explore how machine learning, particularly deep learning methods like autoencoders and graph neural networks, is addressing these challenges by enhancing dimensionality reduction, data integration, and feature extraction. Newly developed foundation models present exciting opportunities for uncovering gene expression programs and predicting genetic perturbations. Focusing on brain development, we demonstrate how single-cell analyses have resolved immune cell heterogeneity, identified temporal maturation trajectories, and uncovered potential therapeutic links to various pathologies, including brain malignancies and neurodegeneration. The integration of single-cell and spatial omics has elucidated the intricate cellular interplay within the developing brain. This mini-review is intended for wet lab biologists at all career stages, offering a concise overview of the evolving landscape of single-cell omics in the age of widely available artificial intelligence.

A holistic view on biological systems is today a reality with the application of multi-omic technologies. These technologies allow the profiling of genome, epigenome, transcriptome, proteome, metabolome as well as newly emerging 'omes.' While the multiple layers of data accumulate, their integration and reconciliation in a single system map is a cumbersome exercise that faces many challenges. Application to human health and disease requires large sample sizes, robust methodologies and high-quality standards.

We review the different methods used to integrate multi-omics, as recent ones including artificial intelligence. With proteomics as an anchor technology, we then present selected applications of its data combination with other omics layers in clinical research, mainly covering literature from the last five years in the Scopus and/or PubMed databases.

Multi-omics is powerful to comprehensively type molecular layers and link them to phenotype. Yet, technologies and data are very diverse and still strategies and methodologies to properly integrate these modalities are needed.

The aim was to fully automate molar teeth developmental staging and to comprehensively analyze a wide range of deep learning models' performances for molar tooth germ detection on panoramic radiographs.

The dataset consisted of 210 panoramic radiographies. The data were obtained from patients aged between 5 and 25 years. The stages of development of molar teeth were divided into 4 classes such as M1, M2, M3 and M4. 9 different convolutional neural network models, which were Cascade R-CNN, YOLOv3, Hybrid Task Cascade(HTC), DetectorRS, SSD, EfficientNet, NAS-FPN, Deformable DETR and Probabilistic Anchor Assignment(PAA), were used for automatic detection of these classes. Performances were evaluated by mAP for detection localization performance and confusion matrices, giving metrics of accuracy, precision, recall and F1-scores for classification part.

Localization performance of the models varied between 0.70 and 0.86 while average accuracy for all classes was between 0.71 and 0.82. The Deformable DETR model provided the best performance with mAP, accuracy, recall and F1-score as 0.86, 0.82, 0.86 and 0.86 respectively.

Molar teeth were automatically detected and categorized by modern artificial intelligence techniques. Findings demonstrated that detection and classification ability of deep learning models were promising for molar teeth development staging. Automated systems have a potential to alleviate the burden and assist dentists.

This is retrospectively registered with the number 2023-1216 by the university ethical committee.

Multiple organ dysfunction syndrome (MODS) is a critical complication in trauma-induced sepsis patients and is associated with a high mortality rate. This study aimed to develop and validate predictive models for MODS in this patient population using a nomogram and machine learning approaches.

This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care-IV 2.2 database, focusing on trauma patients diagnosed with sepsis within the first day of intensive care unit (ICU) admission. Predictive variables were extracted from the initial 24 h of ICU data. The dataset (2008-2019) was divided into a training set (2008-2016) and a temporal validation set (2017-2019). Feature selection was conducted using the Boruta algorithm. Predictive models were developed and validated using a nomogram and various machine learning techniques. Model performance was evaluated based on discrimination, calibration, and decision curve analysis.

Among 1295 trauma patients with sepsis, 349 (26.95%) developed MODS. The 28-day mortality rates were 11.21% for non-MODS patients and 23.82% for MODS patients. Key predictors of MODS included the simplified acute physiology score II score, use of mechanical ventilation, and vasopressor administration. In temporal validation, all models significantly outperformed traditional scoring systems (all P <0.05). The nomogram achieved an area under the curve (AUC) of 0.757 (95% confidence interval [CI]: 0.700 to 0.814), while the random forest model demonstrated the highest performance with an AUC of 0.769 (95% CI: 0.712 to 0.826). Calibration plots showed excellent agreement between predicted and observed probabilities, and decision curve analysis indicated a consistently higher net benefit for the newly developed models.

The nomogram and machine learning models provide enhanced predictive accuracy for MODS in trauma-induced sepsis patients compared to traditional scoring systems. These tools, accessible via web-based applications, have the potential to improve early risk stratification and guide clinical decision-making, ultimately enhancing outcomes for trauma patients. Further external validation is recommended to confirm their generalizability.

In most eukaryotes, mitochondrial organelles contain their own genome, usually circular, which is the remnant of the genome of the ancestral bacterial endosymbiont that gave rise to modern mitochondria. Mitochondrial genomes are dramatically reduced in their gene content due to the process of endosymbiotic gene transfer to the nucleus; as a result most mitochondrial proteins are encoded in the nucleus and imported into mitochondria. This includes the components of the dedicated mitochondrial transcription and replication systems and regulatory factors, which are entirely distinct from the information processing systems in the nucleus. However, since the 1990s several nuclear transcription factors have been reported to act in mitochondria, and previously we identified 8 human and 3 mouse transcription factors (TFs) with strong localized enrichment over the mitochondrial genome using ChIP-seq (Chromatin Immunoprecipitation) datasets from the second phase of the ENCODE (Encyclopedia of DNA Elements) Project Consortium. Here, we analyze the greatly expanded in the intervening decade ENCODE compendium of TF ChIP-seq datasets (a total of 6,153 ChIP experiments for 942 proteins, of which 763 are sequence-specific TFs) combined with interpretative deep learning models of TF occupancy to create a comprehensive compendium of nuclear TFs that show evidence of association with the mitochondrial genome. We find some evidence for chrM occupancy for 50 nuclear TFs and two other proteins, with bZIP TFs emerging as most likely to be playing a role in mitochondria. However, we also observe that in cases where the same TF has been assayed with multiple antibodies and ChIP protocols, evidence for its chrM occupancy is not always reproducible. In the light of these findings, we discuss the evidential criteria for establishing chrM occupancy and reevaluate the overall compendium of putative mitochondrial-acting nuclear TFs.

Influenza viruses cause seasonal epidemics almost every year, and it is difficult to diagnose quickly and accurately. Machine learning and peripheral blood protein omics have brought new ideas to the research of clinical markers.

Prediction of key molecular marker of influenza virus infection by the established machine learning model and peripheral blood protein omics.

This study used the testing data of 850 patients (including influenza, COVID-19 and mixed infections) and 265 healthy individuals, to establish and validate a diagnostic prediction model for influenza infection and verified the potential value of this model in the differential diagnosis of influenza, COVID-19 and healthy people.

The overall analysis showed that there were significant differences in 9 clinical features in the influenza group. Principal component analysis can effectively group samples based on these clinical features. Based on the random forest model and LASSO regression model found that the selected features are clinical indicators that can accurately distinguish influenza patients. We performed proteome sequencing combined with machine learning and found a total of 26 DEPs. Through PPI and WGCNA analysis, we identified several genes related to the proportion of monocytes. We then analyzed the correlation of these factors with immune cell proportions and found that SAA1 and SAA2 were highly correlated with various vital immunocyte. ROC curve analysis shows that SERPINA3 can distinguish influenza, COVID-19, mixed infection and healthy people; SAA1 can distinguish COVID-19, mixed infection and healthy people; SAA2 can distinguish influenza and healthy people. In influenza, high expression of SERPINA3, SAA1, and SAA2 is associated with higher risk. Finally, we used the ELISA method to confirm that SAA2 protein can be used as an auxiliary diagnostic indicator for influenza infection.

Preliminary results showed that SAA2 is an important molecular marker specific to influenza infection.

Group A Streptococcus (GAS) is a major pathogen with diverse clinical outcomes linked to its genetic variability, making accurate phenotype prediction essential. While previous studies have identified many GAS-associated genetic factors, translating these findings into predictive models remains challenging due to data complexity. The current study aimed to integrate deep learning models with genome-wide association study-derived genetic variants to predict pathogenic phenotypes in GAS. We evaluated the performance of several deep neural network models, including CNN, ResNet18, LSTM, and their ensemble approach in predicting GAS phenotypes. It was found that the ensemble model consistently achieved the highest prediction accuracy across phenotypes. Models trained on the full 4722-genotype set outperformed those trained on a reduced 175-genotype set, underscoring the importance of comprehensive variant data in capturing complex genotype-phenotype interactions. Performance changes in the reduced 175-genotype set compared to the full-set genotype scenarios revealed the impact of data dimensionality on model effectiveness, with CNN remaining robust, while ResNet18 and LSTM underperformed. Our findings emphasized the potential of deep learning in phenotype prediction and the critical role of data-model compatibility.

The successful approval of peptide-based drugs can be attributed to a collaborative effort across multiple disciplines. The integration of novel drug design and synthesis techniques, display library technology, delivery systems, bioengineering advancements, and artificial intelligence have significantly expedited the development of groundbreaking peptide-based drugs, effectively addressing the obstacles associated with their character, such as the rapid clearance and degradation, necessitating subcutaneous injection leading to increasing patient discomfort, and ultimately advancing translational research efforts. Peptides are presently employed in the management and diagnosis of a diverse array of medical conditions, such as diabetes mellitus, weight loss, oncology, and rare diseases, and are additionally garnering interest in facilitating targeted drug delivery platforms and the advancement of peptide-based vaccines. This paper provides an overview of the present market and clinical trial progress of peptide-based therapeutics, delivery platforms, and vaccines. It examines the key areas of research in peptide-based drug development through a literature analysis and emphasizes the structural modification principles of peptide-based drugs, as well as the recent advancements in screening, design, and delivery technologies. The accelerated advancement in the development of novel peptide-based therapeutics, including peptide-drug complexes, new peptide-based vaccines, and innovative peptide-based diagnostic reagents, has the potential to promote the era of precise customization of disease therapeutic schedule.

Accurate sample classification using transcriptomics data is crucial for advancing personalized medicine. Achieving this goal necessitates determining a suitable sample size that ensures adequate classification accuracy without undue resource allocation. Current sample size calculation methods rely on assumptions and algorithms that may not align with supervised machine learning techniques for sample classification. Addressing this critical methodological gap, we present a novel computational approach that establishes the accuracy-versus-sample size relationship by employing a data augmentation strategy followed by fitting a learning curve. We comprehensively evaluated its performance for microRNA and RNA sequencing data, considering diverse data characteristics and algorithm configurations, based on a spectrum of evaluation metrics. To foster accessibility and reproducibility, the Python and R code for implementing our approach is available on GitHub. Its deployment will significantly facilitate the adoption of machine learning in transcriptomics studies and accelerate their translation into clinically useful classifiers for personalized treatment.

Although deep learning has demonstrated substantial potential in automatic quantification of joint damage in RA, evidence for detecting longitudinal changes at an individual patient level is lacking. Here, we introduce and externally validate our automated RA scoring algorithm (AuRA), and demonstrate its utility for monitoring radiographic progression in a real-world setting.

The algorithm, originally developed during the Rheumatoid Arthritis 2-Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM) challenge, was trained to predict expert-curated Sharp-van der Heijde total scores in hand and foot radiographs from two previous clinical studies (n = 367). We externally validated AuRA against data (n = 205) from Turku University Hospital and compared the performance against two top-performing RA2-DREAM solutions. Finally, for 54 patients, we extracted additional radiograph sets from another control visit to the clinic (average time interval of 4.6 years).

In the external validation cohort, with a root mean square error (RMSE) of 23.6, AuRA outperformed both top-performing RA2-DREAM algorithms (RMSEs 35.0 and 35.6). The improved performance was explained mostly by lower errors at higher expert-assessed scores. The longitudinal changes predicted by our algorithm were significantly correlated with changes in expert-assessed scores (Pearson's R = 0.74, P < 0.001).

AuRA had the best external validation performance and demonstrated potential for detecting longitudinal changes in joint damage. Available from https://hub.docker.com/r/elolab/aura, our algorithm can easily be applied for automatic detection of radiographic progression in the future, reducing the need for laborious manual scoring.

Intensive Care Units (ICUs) have undergone enhancements in patient safety, and artificial intelligence (AI) emerges as a disruptive technology offering novel opportunities. While the published evidence is limited and presents methodological issues, certain areas show promise, such as decision support systems, detection of adverse events, and prescription error identification. The application of AI in safety may pursue predictive or diagnostic objectives. Implementing AI-based systems necessitates procedures to ensure secure assistance, addressing challenges including trust in such systems, biases, data quality, scalability, and ethical and confidentiality considerations. The development and application of AI demand thorough testing, encompassing retrospective data assessments, real-time validation with prospective cohorts, and efficacy demonstration in clinical trials. Algorithmic transparency and explainability are essential, with active involvement of clinical professionals being crucial in the implementation process.

A thorough understanding of cell-line drug response mechanisms is crucial for drug development, repurposing, and resistance reversal. While targeted anticancer therapies have shown promise, not all cancers have well-established biomarkers to stratify drug response. Single-gene associations only explain a small fraction of the observed drug sensitivity, so a more comprehensive method is needed. However, while deep learning models have shown promise in predicting drug response in cell lines, they still face significant challenges when it comes to their application in clinical applications. Therefore, this study proposed a new strategy called DD-Response for cell-line drug response prediction. First, a limitation of narrow modeling horizons was overcome to expand the model training domain by integrating multiple datasets through source-specific label binarization. Second, a modified representation based on a two-dimensional structurized gridding map (SGM) was developed for cell lines & drugs, avoiding feature correlation neglect and potential information loss. Third, a dual-branch, multi-channel convolutional neural network-based model for pairwise response prediction was constructed, enabling accurate outcomes and improved exploration of underlying mechanisms. As a result, the DD-Response demonstrated superior performance, captured cell-line characteristic variations, and provided insights into key factors impacting cell-line drug response. In addition, DD-Response exhibited scalability in predicting clinical patient responses to drug therapy. Overall, because of DD-response's excellent ability to predict drug response and capture key molecules behind them, DD-response is expected to greatly facilitate drug discovery, repurposing, resistance reversal, and therapeutic optimization.

This comprehensive review explores the role of deep learning (DL) in glioma segmentation using multiparametric magnetic resonance imaging (MRI) data. The study surveys advanced techniques such as multiparametric MRI for capturing the complex nature of gliomas. It delves into the integration of DL with MRI, focusing on convolutional neural networks (CNNs) and their remarkable capabilities in tumor segmentation. Clinical applications of DL-based segmentation are highlighted, including treatment planning, monitoring treatment response, and distinguishing between tumor progression and pseudo-progression. Furthermore, the review examines the evolution of DL-based segmentation studies, from early CNN models to recent advancements such as attention mechanisms and transformer models. Challenges in data quality, gradient vanishing, and model interpretability are discussed. The review concludes with insights into future research directions, emphasizing the importance of addressing tumor heterogeneity, integrating genomic data, and ensuring responsible deployment of DL-driven healthcare technologies. EVIDENCE LEVEL: N/A TECHNICAL EFFICACY: Stage 2.

Inter-residue interactions in protein structures provide valuable insights into protein folding and stability. Understanding these interactions can be helpful in many crucial applications, including rational design of therapeutic small molecules and biologics, locating functional protein sites, and predicting protein-protein and protein-ligand interactions. The process of developing machine learning models incorporating inter-residue interactions has been improved recently. This review highlights the theoretical models incorporating inter-residue interactions in predicting folding and unfolding rates of proteins. Utilizing contact maps to depict inter-residue interactions aids researchers in developing computer models for detecting remote homologs and interface residues within protein-protein complexes which, in turn, enhances our knowledge of the relationship between sequence and structure of proteins. Further, the application of contact maps derived from inter-residue interactions is highlighted in the field of drug discovery. Overall, this review presents an extensive assessment of the significant models that use inter-residue interactions to investigate folding rates, unfolding rates, remote homology, and drug development, providing potential future advancements in constructing efficient computational models in structural biology.

Electroencephalography (EEG) is a widely used physiological signal to obtain information of brain activity, and its automatic detection holds significant research importance, which saves doctors' time, improves detection efficiency and accuracy. However, current automatic detection studies face several challenges: large EEG data volumes require substantial time and space for data reading and model training; EEG's long-term dependencies test the temporal feature extraction capabilities of models; and the dynamic changes in brain activity and the non-Euclidean spatial structure between electrodes complicate the acquisition of spatial information. The proposed method uses range-EEG (rEEG) to extract time-frequency features from EEG to reduce data volume and resource consumption. Additionally, the next-generation state-space model Mamba is utilized as a temporal feature extractor to effectively capture the temporal information in EEG data. To address the limitations of state space models (SSMs) in spatial feature extraction, Mamba is combined with Dynamic Graph Neural Networks, creating an efficient model called DG-Mamba for EEG event detection. Testing on seizure detection and sleep stage classification tasks showed that the proposed method improved training speed by 10 times and reduced memory usage to less than one-seventh of the original data while maintaining superior performance. On the TUSZ dataset, DG-Mamba achieved an AUROC of 0.931 for seizure detection and in the sleep stage classification task, the proposed model surpassed all baselines.

BackgroundDeep learning excels at processing raw data because it automatically extracts and classifies high-level features. Despite biology's low popularity in data analysis, incorporating computer technology can improve biological research.ObjectiveTo create a deep learning model that can identify nucleosomes from nucleotide sequences and to show that simpler models outperform more complicated ones in solving biological challenges.MethodsA classifier was created utilising deep learning and machine learning approaches. The final model consists of two convolutional layers, one max pooling layer, two fully connected layers, and a dropout regularisation layer. This structure was chosen on the basis of the 'less is frequently more' approach, which emphasises simple design without large hidden layers.ResultsExperimental results show that deep learning methods, specifically deep neural networks, outperform typical machine learning algorithms for recognising nucleosomes. The simplified network architecture proved suitable without the requirement for numerous hidden neurons, resulting in effective network performance.ConclusionThis study demonstrates that machine learning and other computational techniques may streamline and expedite the resolution of biological issues. The model helps identify nucleosomes and can be used in future research or labs. This study discusses the challenges of understanding and addressing simple biological problems with sophisticated computer technology and offers practical solutions for academic and economic sectors.

Estimating the age of immature blow flies is of great importance for forensic entomology. However, no gold-standard technique for an accurate determination of the intra-puparial age has yet been established. Fourier transform infrared (FTIR) spectroscopy is a method to (bio-)chemically characterise material based on the absorbance of electromagnetic energy by functional groups of molecules. In recent years, it also has become a powerful tool in forensic and life sciences, as it is a fast and cost-effective way to characterise all kinds of material and biological traces. This study is the first to collect developmental reference data on the changes in absorption spectra during the intra-puparial period of the forensically important blow fly Calliphora vicina Robineau-Desvoidy (Diptera: Calliphoridae). Calliphora vicina was reared at constant 20°C and 25°C and specimens were killed every other day throughout their intra-puparial development. In order to investigate which part yields the highest detectable differences in absorption spectra throughout the intra-puparial development, each specimen was divided into two different subsamples: the pupal body and the former cuticle of the third instar, that is, the puparium. Absorption spectra were collected with a FTIR spectrometer coupled to an attenuated total reflection (ATR) unit. Classification accuracies of different wavenumber regions with two machine learning models, i.e., random forests (RF) and support vector machines (SVMs), were tested. The best age predictions for both temperature settings and machine learning models were obtained by using the full spectral range from 3700 to 600 cm-1. While SVMs resulted in better accuracies for C. vicina reared at 20°C, RFs performed almost as good as SVMs for data obtained from 25°C. In terms of sample type, the pupal body gave smoother spectra and usually better classification accuracies than the puparia. This study shows that FTIR spectroscopy is a promising technique in forensic entomology to support the estimation of the minimum post-mortem interval (PMImin), by estimating the age of a given insect specimen.

Single-cell RNA sequencing (scRNA-seq) is a groundbreaking technology extensively utilized in biological research, facilitating the examination of gene expression at the individual cell level within a given tissue sample. While numerous tools have been developed for scRNA-seq data analysis, the challenge persists in capturing the distinct features of such data and replicating virtual datasets that share analogous statistical properties. Our study introduces a generative approach termed scRNA-seq Diffusion Transformer (scRDiT). This method generates virtual scRNA-seq data by leveraging a real dataset. The method is a neural network constructed based on Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs). This involves subjecting Gaussian noises to the real dataset through iterative noise-adding steps and ultimately restoring the noises to form scRNA-seq samples. This scheme allows us to learn data features from actual scRNA-seq samples during model training. Our experiments, conducted on two distinct scRNA-seq datasets, demonstrate superior performance. Additionally, the model sampling process is expedited by incorporating Denoising Diffusion Implicit Models (DDIMs). scRDiT presents a unified methodology empowering users to train neural network models with their unique scRNA-seq datasets, enabling the generation of numerous high-quality scRNA-seq samples.

Cervical spinal cord injury is often catastrophic, frequently leading to irreversible impairment. MRI has become the gold standard for evaluating spinal cord injuries (SCI). Our study aimed to assess the accuracy of a radiomics approach, based on machine learning and utilizing conventional MRI, in predicting the prognosis of patients with SCI. In a retrospective analysis of 82 SCI patients from three hospitals, we categorized them into good (n = 49) and poor (n = 33) prognosis groups. Preoperative T2-weighted MRI images were segmented using 3D-Region of Interest (ROI) techniques, and both radiomic and deep transfer learning features were extracted. These features were normalized using Z-score and harmonized via ComBat. Feature selection was performed using a greedy algorithm and Least absolute shrinkage and selection operator (LASSO), and others, followed by the calculation of radiomics scores through linear regression. Machine learning was then used to identify the most predictive radiomic features. Model performance was evaluated by analyzing the area under the curve (AUC) and other indicators.Univariate analysis indicated that the demographic characteristics of cervical spinal cord injury were not statistically significant. In the test dataset, the random forest (RF) combined with radiomics and ResNet34 demonstrated better performance, with an accuracy of 0.800 and an AUC of 0.893.Using MRI, deep learning-based radiomics signals show promise in evaluating and predicting the postoperative prognosis of these patients.

Cancer is a manifestation of dysfunctional cell states. It emerges from an interplay of intrinsic and extrinsic factors that disrupt cellular dynamics, including genetic and epigenetic alterations, as well as the tumor microenvironment. This complexity can make it challenging to infer molecular causes for treating the disease. This may be addressed by system-wide computer models of cells, as they allow rapid generation and testing of hypotheses that would be too slow or impossible to perform in the laboratory and clinic. However, so far, such models have been impeded by both experimental and computational limitations. In this perspective, we argue that they can now be achieved using deep learning algorithms to integrate omics data and prior knowledge of molecular networks. Such models would have many applications in precision oncology, e.g., for identifying drug targets and biomarkers, predicting resistance mechanisms and toxicity effects of drugs, or simulating cell-cell interactions in the microenvironment.

This study explores the application of vision transformers to predict early responses to stereotactic radiosurgery in patients with brain metastases using minimally pre-processed magnetic resonance imaging scans. The objective is to assess the potential of vision transformers as a predictive tool for clinical decision-making, particularly in the context of imbalanced datasets.

We analyzed magnetic resonance imaging scans from 19 brain metastases patients, focusing on axial fluid-attenuated inversion recovery and high-resolution contrast-enhanced T1-weighted sequences. Patients were categorized into responders (complete or partial response) and non-responders (stable or progressive disease).

Despite the imbalanced nature of the dataset, our results demonstrate that vision transformers can predict early treatment responses with an overall accuracy of 99%. The model exhibited high precision (99% for progression and 100% for regression) and recall (99% for progression and 100% for regression). The use of the attention mechanism in the vision transformers allowed the model to focus on relevant features in the magnetic resonance imaging images, ensuring an unbiased performance even with the imbalanced data. Confusion matrix analysis further confirmed the model's reliability, with minimal misclassifications. Additionally, the model achieved a perfect area under the receiver operator characteristic curve (AUC = 1.00), effectively distinguishing between responders and non-responders.

These findings highlight the potential of vision transformers, aided by the attention mechanism, as a non-invasive, predictive tool for early response assessment in clinical oncology. The vision transformer (ViT) model employed in this study processes MRIs as sequences of patches, enabling the capture of localized tumor features critical for early response prediction. By leveraging patch-based feature learning, this approach enhances robustness, interpretability, and clinical applicability, addressing key challenges in tumor progression prediction following stereotactic radiosurgery (SRS). The model's robust performance, despite the dataset imbalance, underscores its ability to provide unbiased predictions. This approach could significantly enhance clinical decision-making and support personalized treatment strategies for brain metastases. Future research should validate these findings in larger, more diverse cohorts and explore the integration of additional data types to further optimize the model's clinical utility.

Artificial intelligence (AI) has emerged as a transformative force in precision medicine, revolutionizing the integration and analysis of health records, genetics, and immunology data. This comprehensive review explores the clinical applications of AI-driven analytics in unlocking personalized insights for patients with autoimmune rheumatic diseases. Through the synergistic approach of integrating AI across diverse data sets, clinicians gain a holistic view of patient health and potential risks. Machine learning models excel at identifying high-risk patients, predicting disease activity, and optimizing therapeutic strategies based on clinical, genomic, and immunological profiles. Deep learning techniques have significantly advanced variant calling, pathogenicity prediction, splicing analysis, and MHC-peptide binding predictions in genetics. AI-enabled immunology data analysis, including dimensionality reduction, cell population identification, and sample classification, provides unprecedented insights into complex immune responses. The review highlights real-world examples of AI-driven precision medicine platforms and clinical decision support tools in rheumatology. Evaluation of outcomes demonstrates the clinical benefits and impact of these approaches in revolutionizing patient care. However, challenges such as data quality, privacy, and clinician trust must be navigated for successful implementation. The future of precision medicine lies in the continued research, development, and clinical integration of AI-driven strategies to unlock personalized patient care and drive innovation in rheumatology.

Pulmonary embolism (PE) is a common and potentially fatal condition. Timely and accurate risk assessment in patients with acute deep vein thrombosis (DVT) is crucial. This study aims to develop a deep learning-based, precise, and efficient PE risk prediction model (PE-Mind) to overcome the limitations of current clinical tools and provide a more targeted risk evaluation solution.

We analyzed clinical data from patients by first simplifying and organizing the collected features. From these, 37 key clinical features were selected based on their importance. These features were categorized and analyzed to identify potential relationships. Our prediction model uses a convolutional neural network (CNN), enhanced with three custom-designed modules for better performance. To validate its effectiveness, we compared this model with five commonly used prediction models.

PE-Mind demonstrated the highest accuracy and reliability, achieving 0.7826 accuracy and an area under the receiver operating characteristic curve of 0.8641 on the prospective test set, surpassing other models. Based on this, we have also developed a Web server, PulmoRiskAI, for real-time clinician operation.

The PE-Mind model improves prediction accuracy and reliability for assessing PE risk in acute DVT patients. Its convolutional architecture and residual modules substantially enhance predictive performance.

The high frequency of genetic diseases compels the development of refined diagnostic and therapeutic systems. CRISPR is a precise genome editing tool that offers detection of genetic mutation with high sensitivity, specificity and flexibility for point-of-care testing in low resource environment. Advancements in CRISPR ushered new hope for the detection of genetic diseases. This review aims to explore the recent advances in CRISPR for the detection and treatment of genetic disorders. It delves into the advances like next-generation CRISPR diagnostics like nano-biosensors, digitalized CRISPR, and omics-integrated CRISPR technologies to enhance the detection limits and to facilitate the "lab-on-chip" technologies. Additionally, therapeutic potential of CRISPR technologies is reviewed to evaluate the implementation potential of CRISPR technologies for the treatment of hematological diseases, (sickle cell anemia and β-thalassemia), HIV, cancer, cardiovascular diseases, and neurological disorders, etc. Emerging CRISPR therapeutic approaches such as base/epigenetic editing and stem cells for the development of foreseen CRIPSR drugs are explored for the development of point-of-care testing. A combination of predictive models of artificial intelligence and machine learning with growing knowledge of genetic disorders has also been discussed to understand their role in acceleration of genetic detection. Ethical consideration are briefly discussed towards to end of review. This review provides the comprehensive insights into advances in the CRISPR diagnostics/therapeutics which are believed to pave the way for reliable, effective, and low-cost genetic testing.

Single-molecule localization microscopy (SMLM), which has revolutionized nanoscale imaging, faces challenges in densely labelled samples due to fluorophore clustering, leading to compromised localization accuracy. In this paper, we propose a novel convolutional neural network (CNN)-assisted approach to address the issue of locating the clustered fluorophores. Our CNN is trained on a diverse data set of simulated SMLM images where it learns to predict point spread function (PSF) locations by generating Gaussian blobs as output. Through rigorous evaluation, we demonstrate significant improvements in PSF localization accuracy, especially in densely labelled samples where traditional methods struggle. In addition, we employ blob detection as a post-processing technique to refine the predicted PSF locations and enhance localization precision. Our study underscores the efficacy of CNN in addressing clustering challenges in SMLM, thereby advancing spatial resolution and enabling deeper insights into complex biological structures.

The predictive intensive care unit (ICU) scoring system is crucial for predicting patient outcomes, particularly mortality. Traditional scoring systems rely mainly on structured clinical data from electronic health records, which can overlook important clinical information in narratives and images.

In this work, we build a deep learning-based survival prediction model that utilizes multimodality data for ICU mortality prediction. Four sets of features are investigated: (1) physiological measurements of Simplified Acute Physiology Score (SAPS) II, (2) common thorax diseases predefined by radiologists, (3) bidirectional encoder representations from transformers-based text representations, and (4) chest X-ray image features. The model was evaluated using the Medical Information Mart for Intensive Care IV dataset.

Our model achieves an average C-index of 0.7829 (95% CI, 0.7620-0.8038), surpassing the baseline using only SAPS-II features, which had a C-index of 0.7470 (95% CI: 0.7263-0.7676). Ablation studies further demonstrate the contributions of incorporating predefined labels (2.00% improvement), text features (2.44% improvement), and image features (2.82% improvement).

The deep learning model demonstrated superior performance to traditional machine learning methods under the same feature fusion setting for ICU mortality prediction. This study highlights the potential of integrating multimodal data into deep learning models to enhance the accuracy of ICU mortality prediction.

The integration of artificial intelligence (AI), particularly, in oncology, has significantly shifted the paradigms of medical diagnostics and treatment planning. However, the utility of AI, specifically OpenAI's ChatGPT, in soft tissue sarcoma treatment, remains unclear.

We evaluated ChatGPT's alignment with the Japanese Orthopaedic Association (JOA) clinical practice guidelines on the management of soft tissue tumors 2020. Twenty-two clinical questions (CQs) were formulated to encompass various aspects of sarcoma diagnosis, treatment, and management. ChatGPT's responses were classified into "Complete Alignment," "Partial Alignment," or "Nonalignment" based on the recommendation and strength of evidence.

ChatGPT demonstrated an 86% alignment rate with the JOA guidelines. The AI provided two instances of complete alignment and 17 instances of partial alignment, indicating a strong capability to match guideline criteria for most questions. However, three discrepancies were identified in areas concerning the treatment of atypical lipomatous tumors, perioperative chemotherapy for synovial sarcoma, and treatment strategies for elderly patients with malignant soft tissue tumors. Reassessment with guideline input led to some adjustments, revealing both the potential and limitations of AI in complex sarcoma care.

Our study demonstrates that AI, specifically ChatGPT, can align with clinical guidelines for soft tissue sarcoma treatment. It also underscores the need for continuous refinement and cautious integration of AI in medical decision-making, particularly in the context of treatment for soft tissue sarcoma.

Nanozymes with multienzyme-like activity have sparked significant interest in anti-tumor therapy via responding to the tumor microenvironment (TME). However, the consequent induction of protective autophagy substantially compromises the therapeutic efficacy. Here, a targeted nanozyme system (Fe-Arg-CDs@ZIF-8/HAD, FZH) is shown, which enhances synergistic anti-tumor ferroptosis/apoptosis therapy by leveraging machine learning (ML). A novel ML model, termed the sequential backward Tree-Classifier for Gaussian Process Regression (TCGPR), is proposed to improve data pattern recognition following the divide-and-conquer principle. Based on this, a Bayesian optimization algorithm is employed to select candidates from the extensive search space. Leveraging this fresh material discovery framework, a novel strategy for enhancing nanozyme-based tumor therapy, has been developed. The results reveal that FZH effectively exerts anti-tumor effects by sequentially responding to the TME, having a cascade reaction to induce ferroptosis. Moreover, the endogenous elevation of high concentration nitric oxide (NO) serves as a direct mechanism for killing tumor cells while concurrently suppressing the protective autophagy induced by oxidative stress (OS), enhancing synergistic ferroptosis/apoptosis therapy. Overall, a novel strategy for improving nanozyme-based tumor therapy has been proposed, underlying the integration of ML, experiments, and biological applications.

Antimicrobial resistance (AMR) poses a critical global health threat, necessitating innovative approaches in antimicrobial stewardship (AMS). Artificial intelligence (AI) and machine learning (ML) have emerged as transformative tools in this domain, enabling data-driven interventions to optimize antibiotic use and combat resistance. This comprehensive review explores the multifaceted role of AI and ML models in enhancing antimicrobial stewardship efforts across healthcare systems. AI-powered predictive analytics can identify patterns of resistance, forecast outbreaks, and guide personalized antibiotic therapies by leveraging large-scale clinical and epidemiological data. ML algorithms facilitate rapid pathogen identification, resistance profiling, and real-time monitoring, enabling precise decision making. These technologies also support the development of advanced diagnostic tools, reducing the reliance on broad-spectrum antibiotics and fostering timely, targeted treatments. In public health, AI-driven surveillance systems improve the detection of AMR trends and enhance global monitoring capabilities. By integrating diverse data sources-such as electronic health records, laboratory results, and environmental data-ML models provide actionable insights to policymakers, healthcare providers, and public health officials. Additionally, AI applications in antimicrobial stewardship programs (ASPs) promote adherence to prescribing guidelines, evaluate intervention outcomes, and optimize resource allocation. Despite these advancements, challenges such as data quality, algorithm transparency, and ethical considerations must be addressed to maximize the potential of AI and ML in this field. Future research should focus on developing interpretable models and fostering interdisciplinary collaborations to ensure the equitable and sustainable integration of AI into antimicrobial stewardship initiatives.

The opioid crisis has disproportionately affected U.S. veterans, leading the Veterans Health Administration to implement opioid prescribing guidelines. Veterans who receive care from both VA and non-VA providers-known as dual-system users-have an increased risk of Opioid Use Disorder (OUD). The interaction between dual-system use and demographic and clinical factors, however, has not been previously explored. We conducted a retrospective study of 856,299 patient instances from the Washington DC and Baltimore VA Medical Centers (2012-2019), using a deep neural network (DNN) and explainable Artificial Intelligence to examine the impact of dual-system use on OUD and how demographic and clinical factors interact with it. Of the cohort, 146,688(17%) had OUD, determined through Natural Language Processing of clinical notes and ICD-9/10 diagnoses. The DNN model, with a 78% area under the curve, confirmed that dual-system use is a risk factor for OUD, along with prior opioid use or other substance use. Interestingly, a history of other drug use interacted negatively with dual-system use regarding OUD risk. In contrast, older age was associated with a lower risk of OUD but interacted positively with dual-system use. These findings suggest that within the dual-system users, patients with certain risk profiles warrant special attention.

To progress research into the biological mechanisms that link mammographic breast density to breast cancer risk, fibroglandular breast density can be used as a surrogate measure. This study aimed to develop a computational tool to classify fibroglandular breast density in hematoxylin and eosin (H&E)-stained breast tissue sections using deep learning approaches that would assist future mammographic density research.

Four different architectural configurations of transferred MobileNet-v2 convolutional neural networks (CNNs) and four different models of vision transformers were developed and trained on a database of H&E-stained normal human breast tissue sections (965 tissue blocks from 93 patients) that had been manually classified into one of five fibroglandular density classes, with class 1 being very low fibroglandular density and class 5 being very high fibroglandular density.

The MobileNet-Arc 1 and ViT model 1 achieved the highest overall F1 scores of 0.93 and 0.94, respectively. Both models exhibited the lowest false positive rate and highest true positive rate in class 5, while the most challenging classification was class 3, where images from classes 2 and 4 were mistakenly classified as class 3. The area under the curves (AUCs) for all classes were higher than 0.98.

Both the ViT and MobileNet models showed promising performance in the accurate classification of H&E-stained tissue sections across all five fibroglandular density classes, providing a rapid and easy-to-use computational tool for breast density analysis.