Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
Development and validation of a multimodal MRI habitat-based deep learning fusion model for predicting 252Cf neutron therapy response in cervical cancer
Shu-Peng Wang, Radiology Imaging Center, The Third Affiliated Hospital of Qiqihar Medical University, Qiqihar 161002, Heilongjiang Province, China
Zhi-Guo Chen, Xi-Jing Shan, Miao Jin, Xin Meng, Department of Magnetic Resonance Imaging, The Third Affiliated Hospital of Qiqihar Medical University, Qiqihar 161002, Heilongjiang Province, China
Wei Zhao, Department of Obstetrics and Gynecology, The Third Affiliated Hospital of Qiqihar Medical University, Qiqihar 161002, Heilongjiang Province, China
Xu Tong, Department of Radiation Oncology, The Third Affiliated Hospital of Qiqihar Medical University, Qiqihar 161002, Heilongjiang Province, China
Author contributions: Wang SP conceived the study, developed the model, performed validation, and wrote the original manuscript; Meng X and Chen ZG collected the data; Shan XJ and Jin M conducted image analysis and lesion delineation; Zhao W and Tong X performed statistical analyses; and all authors reviewed and revised the manuscript and approved the final version.
AI contribution statement: The main body of the manuscript, including the abstract, introduction, materials and methods, results, discussion, or conclusion, was not generated by artificial intelligence. Artificial intelligence-assisted tools were only used for language polishing, grammar checking, and translation support. They were not used for data analysis or scientific writing assistance.
Institutional review board statement: The Ethics Committee of the Third Affiliated Hospital of Qiqihar Medical University has reviewed and approved this study (Approval No. 2025 LL-208).
Informed consent statement: All study participants or their legal guardian provided informed written consent about personal and medical data collection prior to study enrolment.
Conflict-of-interest statement: All the authors have no conflict of interest related to the manuscript.
Data sharing statement: No additional data are available.
Corresponding author: Xin Meng, Chief Physician, Department of Magnetic Resonance Imaging, The Third Affiliated Hospital of Qiqihar Medical University, No. 3 Taishun Street, Tiefeng District, Qiqihar 161002, Heilongjiang Province, China. 8203717@qq.com
Received: June 2, 2026
Revised: July 27, 2026
Accepted: August 17, 2026
Published online: September 28, 2026
Processing time: 117 Days and 19 Hours
Revised: July 27, 2026
Accepted: August 17, 2026
Published online: September 28, 2026
Processing time: 117 Days and 19 Hours
Core Tip
Core Tip: The present study developed a multimodal fusion predictive model integrating MRI habitat atlas, deep learning, and radiomics to fill the current gap in early and non-invasive prediction of treatment efficacy of californium-252 (252Cf) neutron therapy for cervical cancer, thereby provide decisive evidence and a powerful imaging tool for individualized precision radiotherapy decision-making.