Deep learning-based framework for the distinction of membranous nephropathy: a new approach through hyperspectral imagery

BMC Nephrology

Xueling Wei¹  Wenge Li²  Yue Yang²  Nianrong Zhang²  Xiaowen Tu³  Tianqi Tu⁴  Wei Li⁵ 

[1] Department of Biomedical Engineering, Tsinghua University, Beijing, China;Department of Nephrology, China-Japan Friendship Hospital, Beijing, China;Department of Nephrology, PLA Rocket Force Characteristic Medical Center, Beijing, China;Peking University China-Japan Friendship School of Clinical Medicine, Beijing, China;Department of Nephrology, China-Japan Friendship Hospital, Beijing, China;School of Information and Electronics, Beijing Institute of Technology, Beijing, China;

关键词: Membranous nephropathy;    Idiopathic membranous nephropathy;    Hepatitis B virus;    Hyperspectral imagery;    Deep learning;   

DOI  :  10.1186/s12882-021-02421-y

来源: Springer

【 摘 要 】

BackgroundCommon subtypes seen in Chinese patients with membranous nephropathy (MN) include idiopathic membranous nephropathy (IMN) and hepatitis B virus-related membranous nephropathy (HBV-MN). However, the morphologic differences are not visible under the light microscope in certain renal biopsy tissues.MethodsWe propose here a deep learning-based framework for processing hyperspectral images of renal biopsy tissue to define the difference between IMN and HBV-MN based on the component of their immune complex deposition.ResultsThe proposed framework can achieve an overall accuracy of 95.04% in classification, which also leads to better performance than support vector machine (SVM)-based algorithms.ConclusionIMN and HBV-MN can be correctly separated via the deep learning framework using hyperspectral imagery. Our results suggest the potential of the deep learning algorithm as a new method to aid in the diagnosis of MN.

【 授权许可】

CC BY