Self-supervised learning with large-scale web image mining for characterizing glomerular lesions

Tianyuan Yao; Yuzhe Lu; Ruining Deng; Zheyu Zhu; Zuhayr Asad; Haichun Yang; Lee E. Wheless; Agnes B. Fogo; Yuankai Huo

doi:10.1117/12.2611903

4 April 2022 Self-supervised learning with large-scale web image mining for characterizing glomerular lesions

Tianyuan Yao, Yuzhe Lu, Ruining Deng, Zheyu Zhu, Zuhayr Asad, Haichun Yang, Lee E. Wheless, Agnes B. Fogo, Yuankai Huo

Proceedings Volume 12039, Medical Imaging 2022: Digital and Computational Pathology; 120390R (2022) https://doi.org/10.1117/12.2611903
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

Glomeruli are clusters of capillaries that are responsible for filtering the blood to form urine, thus excreting waste and maintaining fluid and acid-base balance. The detection and characterization of glomeruli are key elements in diagnostic and experimental nephropathology. Although the field of machine vision has already advanced the detection, classification, and prognostication of diseases in the specialties of radiology and oncology, renal pathology is just entering the digital imaging era. However, developing quantitative machine learning approaches (e.g., self-supervised deep learning) that characterize glomerular lesions (e.g., global glomerulosclerosis (GGS)) from whole slide images (WSIs) typically requires large-scale heterogeneous images, which is resource extensive for individual labs. In this study, we assess the feasibility of leveraging fine-grained GGS characterization via large-scale web image mining (e.g., from journals, search engines, websites) and self-supervised deep learning. Three types of GGS were assessed-solidified (S-GGS, associated with hypertension-related injury), disappearing (D-GGS, a further end result of the SGGS becoming contiguous with fibrotic interstitium), and obsolescent (O-GGS, nonspecific GGS increasing with aging). We employed the SimSiam network as the baseline method of self-supervised contrastive learning. By deploying our previously developed compound figure separation approach, we provided 30,000 unannotated glomerular images via web image mining to train the SimSiam network. From the results, the GGS fine-grained classification model achieved superior performance compared with baseline methods. The segmentation networks evaluated across six different resolutions

Conference Presentation

Citation Download Citation

Tianyuan Yao, Yuzhe Lu, Ruining Deng, Zheyu Zhu, Zuhayr Asad, Haichun Yang, Lee E. Wheless, Agnes B. Fogo, and Yuankai Huo "Self-supervised learning with large-scale web image mining for characterizing glomerular lesions", Proc. SPIE 12039, Medical Imaging 2022: Digital and Computational Pathology, 120390R (4 April 2022); https://doi.org/10.1117/12.2611903

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available