1. A multimodal transformer system for noninvasive diabetic nephropathy diagnosis via retinal imaging
- Author
-
Zheyi Dong, Xiaofei Wang, Sai Pan, Taohan Weng, Xiaoniao Chen, Shuangshuang Jiang, Ying Li, Zonghua Wang, Xueying Cao, Qian Wang, Pu Chen, Lai Jiang, Guangyan Cai, Li Zhang, Yong Wang, Jinkui Yang, Yani He, Hongli Lin, Jie Wu, Li Tang, Jianhui Zhou, Shengxi Li, Zhaohui Li, Yibing Fu, Xinyue Yu, Yanqiu Geng, Yingjie Zhang, Liqiang Wang, Mai Xu, and Xiangmei Chen
- Subjects
Computer applications to medicine. Medical informatics ,R858-859.7 - Abstract
Abstract Differentiating between diabetic nephropathy (DN) and non-diabetic renal disease (NDRD) without a kidney biopsy remains a major challenge, often leading to missed opportunities for targeted treatments that could greatly improve NDRD outcomes. To reform the traditional biopsy-all diagnostic paradigm and avoid unnecessary biopsy, we developed a transformer-based deep learning (DL) system for detecting DN and NDRD upon non-invasive multi-modal data of fundus images and clinical characteristics. Our Trans-MUF achieved an AUC of 0.980 (95% CI: 0.979 to 0.980) over the internal retrospective set and also had superior generalizability over a prospective dataset (AUC: 0.989, 95% CI: 0.987 to 0.990) and a multicenter, cross-machine and multi-operator dataset (AUC: 0.932, 95% CI: 0.931 to 0.939). Moreover, the nephrologists‘ diagnosis accuracy can be improved by 21%, through visualization assistance of the DL system. This paper lays a foundation for automatically differentiating DN and NDRD without biopsy. (Registry name: Correlation Study Between Clinical Phenotype and Pathology of Type 2 Diabetic Nephropathy. ID: NCT03865914. Date: 2017-11-30).
- Published
- 2025
- Full Text
- View/download PDF