Segmentation and thickness calculation of glomerular basement membrane using RADS-Net in glomerular microscopic images

Yizhi Wang, Yiqing Liu, Yuqiu Fu, Xinrui Chen, Shuyan Zhao, Jing Ye, Yonghong He, Zhe Wang, Tian Guan, Jing Li

Abstract: Highlights•We introduce an automated algorithm for GBM segmentation, location, and thickness measurement.•We propose RADS-Net, combining the benefits of CNN and Vision Transformer for accurate segmentation in TEM images.•The U-E and Location modules identify valid GBM segments, providing dual benefits for model optimization and pathological diagnosis.