AI-Based System for Analysis of Electron Microscope Images in Glomerular Disease

作者：Pengcheng Ma, Jinbang Li, Zhengyu Zhang, Weihao Qiu, Danyi Li, Jing Wang, Bingbing Li, Shujing Guo, Jin Zhang, Zhijian Cen, Jian Geng, Xiangsheng Huang, Xiaolei Xue, Aihetaimu Aimaier, Huanjiao Liu, Minyi Liang, Hao Chen, Qifeng Jiang, Xiaoyan Su, Tianjun Guan, Yu Tong, Weiyuan Lin, Li Liu, Jun Xu, Jie Lin, Yaping Ye, Liang Li · 发表于：JAMA Network Open · 年份：2025 · DOI：10.1001/jamanetworkopen.2025.34985 · 被引用次数：7 · 研究领域：Renal Diseases and Glomerulopathies、AI in cancer detection、Retinal Imaging and Analysis

Importance: Kidney biopsy pathology via transmission electron microscopy (TEM) is essential for diagnosing glomerular diseases, offering critical information on glomerular basement membrane (GBM) thickness, foot process (FP) number, and electron-dense deposits (EDDs). These tasks are laborious and time-consuming. Objective: To develop and validate an artificial intelligence (AI) diagnostic system, TEM image-based AI-assisted device (TEM-AID), that accurately segments and measures glomerular ultrastructures (including the GBM, FPs, and EDDs) and determines glomerular disease subtypes using TEM images. Design, Setting, and Participants: This diagnostic study used a large, multicenter cohort including 160 727 TEM images from 31 670 patients with chronic kidney disease across 6 medical centers from January 2021 to December 2023. TEM-AID was trained and validated on 26 650 patients from 1 center and tested externally on 5020 patients (5 test sets) plus a human-AI test set (454 patients representing 7 glomerular disease subtypes). Data were analyzed from January to December 2024. Exposures: TEM-AID integrates 4 modules. Segmentation combined YOLO-v8 detection, segment anything model, and human-in-the-loop refinement to segment GBMs, podocyte FPs, and EDDs. Measurement quantified GBM thickness, FP fusion degree, and EDD deposition sites. Classification used least absolute shrinkage and selection operator-selected deep learning and statistical features with a stacking classifier to d...