Joint breast neoplasm detection and subtyping using multi-resolution network trained on large-scale H&E whole slide images with weak labels Conference Paper

  


Authors: Casson, A.; Liu, S.; Godrich, R. A.; Aghdam, H.; Lee, D.; Malfroid, K.; Rothrock, B.; Kanan, C.; Retamero, J.; Hanna, M.; Millar, E.; Klimstra, D.; Fuchs, T.
Title: Joint breast neoplasm detection and subtyping using multi-resolution network trained on large-scale H&E whole slide images with weak labels
Conference Title: Medical Imaging with Deep Learning (MIDL 2023)
Abstract: Breast cancer is the most commonly diagnosed cancer in the world. The use of artificial intelligence (AI) to help diagnose the disease from digital pathology images has the potential to greatly improve patient outcomes. However, methods for training these models for detecting, segmenting, and subtyping breast neoplasms and other proliferative lesions often rely on costly and time-consuming manual annotation, which can be infeasible for large-scale datasets. In this work, we propose a weakly supervised learning framework to jointly detect, segment, and subtype breast neoplasms. Our approach leverages top-k multiple instance learning to train an initial neoplasm detection backbone network from weakly-labeled whole slide images, which is then used to automatically generate pixel-level pseudo-labels for whole slides. A second network is trained using these pseudo-labels, and slide-level classification is performed by training an aggregator network that fuses the embeddings from both backbone networks. We trained and validated our framework on large-scale datasets with more than 125k whole slide images and demonstrate its effectiveness on tasks including breast neoplasms detection, segmentation, and subtyping. © 2023 CC-BY 4.0, A. Casson et al.
Keywords: pathology; image enhancement; medical imaging; tumors; urology; diseases; image segmentation; digital pathology; breast neoplasm; learning systems; digital pathologies; whole slide images; e-learning; large datasets; large-scale datasets; breast neoplasm detection; multiple instance learning; formal languages; back-bone network; large-scales; multiple-instance learning; neoplasm detection; subtypings
Journal Title Proceedings of Machine Learning Research
Volume: 227
Conference Dates: 2023 Jul 10-12
Conference Location: Nashville, TN
ISBN: 2640-3498
Publisher: Journal Machine Learning Research  
Date Published: 2023-01-01
Start Page: 18
End Page: 38
Language: English
PROVIDER: scopus
DOI/URL:

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189322532&partnerID=40&md5=7fa389d52d1671cdc8b2bc817d446ea6
Notes: Conference paper -- Source: Scopus