Unbiased self supervised learning of kidney histology reveals phenotypic and prognostic insights

Deep learning methods for image segmentation and classification in histopathology generally utilize supervised learning, relying on manually created labels for model development. Here, we applied a self-supervised framework to characterize kidney histology without the use of pathologist annotations, training on whole slide images to identify histomorphological phenotype clusters (HPCs) and create slide-level vector representations. HPCs developed in the training set were visually consistent when transferred to five diverse internal and external validation sets (1,421 WSIs in total). Specific HPCs were reproducibly associated with slide-level pathologist quantifications, such as interstitial fibrosis (AUC = 0.83). Additionally, hierarchical clustering of tissue patterns revealed patient groups related to kidney function and genotype, and specific HPCs predicted longitudinal kidney function decline. Overall, we demonstrated the translational application of a self-supervised framework to summarize distinct kidney tissue patterns with phenotypic and prognostic relevance.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2025-10-08
DOI
https://doi.org/10.1038/s41598-025-19193-2
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Unbiased self supervised learning of kidney histology reveals phenotypic and prognostic insights

Frank C. Brosius, Tamara Isakova, D. Upadhyay, Amy K. Mottl et al.
Scientific Reports
AI in cancer detection
article

Unbiased self supervised learning of kidney histology reveals phenotypic and prognostic insights

Frank C. Brosius, Tamara Isakova, D. Upadhyay, Amy K. Mottl, Oliver Lenz, Pietro A. Canetta, Heather Thiessen‐Philbrook, Kirk A. Campbell, Eugene P. Rhee, James Tumlin, Avi Z. Rosenberg, Manisha Singh, Morgan E. Grams, Michael D. Ross, Aditya Surapaneni, Rupali S. Avasare, Chirag R. Parikh, Christos Argyropoulos, Pascal Schlosser, Yumeng Wen, Nelson Kopyt, Aristotelis Tsirigos, Insa Marie Schmidt, Nicolas Coudray, Katalin Suszták, Randy L. Luciano, Salem Almaani, Daigoro Hirohama, Sushrut S. Waikar, Richard Lafayette, Matthias Kretzler, Samer Mohandes, Julia Scialla, Ankit Mehta, Jeffrey R. Schelling, Shweta Bansal, Adalberto Claudio Quiros, R. Vanguri, Krutika Pandit, Matthew B. Palmer
article en

Abstract

Deep learning methods for image segmentation and classification in histopathology generally utilize supervised learning, relying on manually created labels for model development. Here, we applied a self-supervised framework to characterize kidney histology without the use of pathologist annotations, training on whole slide images to identify histomorphological phenotype clusters (HPCs) and create slide-level vector representations. HPCs developed in the training set were visually consistent when transferred to five diverse internal and external validation sets (1,421 WSIs in total). Specific HPCs were reproducibly associated with slide-level pathologist quantifications, such as interstitial fibrosis (AUC = 0.83). Additionally, hierarchical clustering of tissue patterns revealed patient groups related to kidney function and genotype, and specific HPCs predicted longitudinal kidney function decline. Overall, we demonstrated the translational application of a self-supervised framework to summarize distinct kidney tissue patterns with phenotypic and prognostic relevance.

Scientific ReportsVol. 15(1)
Northwestern University (US), University of North Carolina at Chapel Hill (US), Boston Medical Center (US), MetroHealth (US), Albert Einstein College of Medicine (US), Lehigh Valley Hospital-Pocono (US), Harvard University (US), University of Arizona (US), Johns Hopkins University (US), University of Miami (US), Emory University (US), Baylor University (US), Oregon Health & Science University (US), The University of Texas at San Antonio Health Science Center (US), University of New Mexico (US), University of Michigan (US), Yale University (US), Massachusetts General Hospital (US), Lehigh Valley Health Network (US), University of Virginia (US), The Ohio State University (US), New York University (US), Columbia University (US), University of Glasgow (GB), University of Pennsylvania (US), University of Arkansas for Medical Sciences (US), Stanford University (US), Icahn School of Medicine at Mount Sinai (US)
Openalex Percentile: Top 85%
AI in cancer detection
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.