Lupus Nephritis Subtype Classification with only Slide Level Labels

Amit Sharma, Ekansh Chauhan, Megha S Uppin, Liza Rajasekhar, C.V. Jawahar, P K Vinod
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1401-1411, 2024.

Abstract

Lupus Nephritis classification has historically relied on labor-intensive and meticulous glomerular-level labeling of renal structures in whole slide images (WSIs). However, this approach presents a formidable challenge due to its tedious and resource-intensive nature, limiting its scalability and practicality in clinical settings. In response to this challenge, our work introduces a novel methodology that utilizes only slide-level labels, eliminating the need for granular glomerular-level labeling. A comprehensive multi-stained lupus nephritis digital histopathology WSI dataset was created from the Indian population, which is the largest of its kind. LupusNet, a deep learning MIL-based model, was developed for the sub- type classification of LN. The results underscore its effectiveness, achieving an AUC score of 91.0%, an F1-score of 77.3%, and an accuracy of 81.1% on our dataset in distinguishing membranous and diffused classes of LN.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-sharma24a, title = {Lupus Nephritis Subtype Classification with only Slide Level Labels}, author = {Sharma, Amit and Chauhan, Ekansh and Uppin, Megha S and Rajasekhar, Liza and Jawahar, C.V. and Vinod, P K}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1401--1411}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/sharma24a/sharma24a.pdf}, url = {https://proceedings.mlr.press/v250/sharma24a.html}, abstract = {Lupus Nephritis classification has historically relied on labor-intensive and meticulous glomerular-level labeling of renal structures in whole slide images (WSIs). However, this approach presents a formidable challenge due to its tedious and resource-intensive nature, limiting its scalability and practicality in clinical settings. In response to this challenge, our work introduces a novel methodology that utilizes only slide-level labels, eliminating the need for granular glomerular-level labeling. A comprehensive multi-stained lupus nephritis digital histopathology WSI dataset was created from the Indian population, which is the largest of its kind. LupusNet, a deep learning MIL-based model, was developed for the sub- type classification of LN. The results underscore its effectiveness, achieving an AUC score of 91.0%, an F1-score of 77.3%, and an accuracy of 81.1% on our dataset in distinguishing membranous and diffused classes of LN.} }
Endnote
%0 Conference Paper %T Lupus Nephritis Subtype Classification with only Slide Level Labels %A Amit Sharma %A Ekansh Chauhan %A Megha S Uppin %A Liza Rajasekhar %A C.V. Jawahar %A P K Vinod %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-sharma24a %I PMLR %P 1401--1411 %U https://proceedings.mlr.press/v250/sharma24a.html %V 250 %X Lupus Nephritis classification has historically relied on labor-intensive and meticulous glomerular-level labeling of renal structures in whole slide images (WSIs). However, this approach presents a formidable challenge due to its tedious and resource-intensive nature, limiting its scalability and practicality in clinical settings. In response to this challenge, our work introduces a novel methodology that utilizes only slide-level labels, eliminating the need for granular glomerular-level labeling. A comprehensive multi-stained lupus nephritis digital histopathology WSI dataset was created from the Indian population, which is the largest of its kind. LupusNet, a deep learning MIL-based model, was developed for the sub- type classification of LN. The results underscore its effectiveness, achieving an AUC score of 91.0%, an F1-score of 77.3%, and an accuracy of 81.1% on our dataset in distinguishing membranous and diffused classes of LN.
APA
Sharma, A., Chauhan, E., Uppin, M.S., Rajasekhar, L., Jawahar, C. & Vinod, P.K.. (2024). Lupus Nephritis Subtype Classification with only Slide Level Labels. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1401-1411 Available from https://proceedings.mlr.press/v250/sharma24a.html.

Related Material