DFE-Net:基于不确定度场的脑卒中联合诊断与病灶定位深度学习模型
Learning uncertainty fields for joint brain stroke diagnosis and intrinsic lesion localization in CT and MRI
研究团队开发了动态模糊编码网络(DFE-Net),通过学习可微模糊隶属度场同时完成脑卒中对 CT 和 MRI 的分类诊断与病灶定位。
- Article
- Open access
- Published: 14 November 2026
- Zehao Jin1,2 na1,
- Shuzhen Xu3 na1,
- Xiaojun Dong4 na1,
- Jieyi Yang5,
- Xuanfeng Qin6,
- Hao Sun ORCID: orcid.org/0000-0002-0968-91297 &
- …
- Kangwei Wang1
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Early stroke changes can be difficult to detect and localize on neuroimaging, particularly when lesion boundaries are indistinct. We developed the Dynamic Fuzzy Encoder Network (DFE-Net), which uses learnable fuzzy membership fields to represent spatial uncertainty and jointly classify stroke and localize lesions. We evaluated the model on a multicentre computed tomography (CT) cohort comprising 6650 patients and 8873 images and a separate magnetic resonance imaging (MRI) cohort comprising 67 patients and 615 images. Training and testing were performed separately within each modality. DFE-Net achieved an area under the receiver operating characteristic curve of 0.974 and an F1 score of 0.897 on CT, and corresponding values of 0.978 and 0.879 on MRI. In the CT cohort, lesion localization against expert annotations yielded a Dice score of 0.70. MRI localization was assessed using gradient-derived pseudo-targets because expert lesion masks were unavailable. Expected calibration error was ~0.022 in both cohorts, and the model contained 0.20 million parameters. These results support joint diagnosis and spatial localization with a compact model, while prospective validation and expert-annotated MRI evaluation remain necessary.
Similar content being viewed by others



Acknowledgements
Not applicable.
Funding
The authors received no specific funding for this work.
Author information
Author notes
These authors contributed equally: Zehao Jin, Shuzhen Xu, Xiaojun Dong.
Authors and Affiliations
The Affiliated Yueqing Hospital, Wenzhou Medical University, Wenzhou, China
Zehao Jin & Kangwei Wang
Technical University of Munich, Munich, Germany
Zehao Jin
Core Laboratory, Fuzhou Hospital of Traditional Chinese Medicine Affiliated to Fujian University of Traditional Chinese Medicine, Fuzhou, Fujian, China
Shuzhen Xu
School of Medical Information and Engineering, Hunan Medical College, Huaihua, China
Xiaojun Dong
School of Artificial Intelligence, Ningbo University, Ningbo, China
Jieyi Yang
Department of Neurosurgery, National Center for Neurological Disorders,Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
Xuanfeng Qin
Wolfson Institute for Biomedical Research, UCL Division of Medicine, University College London, London, UK
Hao Sun
Authors
- Zehao Jin
- Shuzhen Xu
- Xiaojun Dong
- Jieyi Yang
- Xuanfeng Qin
- Hao Sun
- Kangwei Wang
Corresponding authors
Correspondence to Xuanfeng Qin, Hao Sun or Kangwei Wang.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Jin, Z., Xu, S., Dong, X. et al. Learning uncertainty fields for joint brain stroke diagnosis and intrinsic lesion localization in CT and MRI. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03458-9
Received: 22 July 2026
Accepted: 18 October 2026
Published: 14 November 2026
DOI: https://doi.org/10.1038/s41746-026-03458-9
来源:Nature 健康护理主题 · nature.com