Phenotypic and prognostic insights through unbiased self-supervised learning on kidney histology
Pandit, K.; Coudray, N.; Quiros, A. C.; Surapaneni, A.; Upadhyay, D.; Vanguri, R. S.; Hirohama, D.; Mohandes, S.; Schlosser, P.; Thiessen-Philbrook, H.; Wen, Y.; Parikh, C. R.; Rhee, E. P.; Waikar, S.; Schmidt, I. M.; Rosenberg, A. Z.; Palmer, M. B.; Susztak, K.; Grams, M. E.; Tsirigos, A.
Show 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.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Urine Test Predicts Kidney Injury and Death in COVID-19 95%
- Urine single cell RNA-sequencing in focal segmental glomerulosclerosis reveals inflammatory signatures in immune cells and podocytes 95%
- A precision medicine approach uncovers a unique signature of neutrophils in patients with brushite kidney stones 94%
Similar papers in this journal
- Computational characterization of lymphocyte topology on whole slide images of glomerular diseases 95%
- 3D mapping reveals a complex and transient interstitial matrix during murine renal development 94%
- Clonal hematopoiesis of indeterminate potential contributes to accelerated chronic kidney disease progression 94%
Similar papers in this journal
- Highly Multiplexed Immunofluorescence of the Human Kidney using Co-Detection by Indexing (CODEX) 95%
- Genetically engineering endothelial niche in human kidney organoids enables multilineage maturation, vascularization, and de novo cell types 95%
- Urinary single-cell sequencing captures intrarenal injury and repair processes in human acute kidney injury 94%
Similar papers in this journal
- Three Dimensional Multiscalar Neurovascular Nephron Connectivity Map of the Human Kidney Across the Lifespan 95%
- Defining cellular complexity in human autosomal dominant polycystic kidney disease by multimodal single cell analysis 95%
- Single-cell profiling of healthy human kidney reveals features of sex-based transcriptional programs and tissue-specific immunity 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.