1. MS-CLAM: Mixed Supervision for the classification and localization of tumors in Whole Slide Images
- Author
-
Paul Tourniaire, Marius Ilie, Paul Hofman, Nicholas Ayache, Hervé Delingette, Université Côte d'Azur (UCA), E-Patient : Images, données & mOdèles pour la médeciNe numériquE (EPIONE), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), FHU OncoAge - Pathologies liées à l’âge [CHU Nice] (OncoAge), Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Pharmacologie Moléculaire et Cellulaire [UNIV Côte d'Azur] (UPMC)-Université Côte d'Azur (UCA), Centre Hospitalier Universitaire de Nice (CHU Nice), Laboratoire de Pathologie Clinique et Expérimentale. Hôpital Pasteur [Nice], Hôpital Pasteur [Nice] (CHU), and ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019)
- Subjects
Camelyon16 ,Deep Learning ,Radiological and Ultrasound Technology ,Mixed Supervision ,DigestPath2019 ,Digital Pathology ,Health Informatics ,Radiology, Nuclear Medicine and imaging ,Computer Vision and Pattern Recognition ,Computer Graphics and Computer-Aided Design ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] - Abstract
International audience; Given the size of digitized Whole Slide Images (WSIs), it is generally laborious and time-consuming for pathologists to exhaustively delineate objects within them, especially with datasets containing hundreds of slides to annotate. Most of the time, only slide-level labels are available, giving rise to the development of weakly-supervised models. However, it is often difficult to obtain from such models accurate object localization, e.g., patches with tumor cells in a tumor detection task, as they are mainly designed for slide-level classification. Using the attention-based deep Multiple Instance Learning (MIL) model as our base weakly-supervised model, we propose to use mixed supervision-i.e., the use of both slide-level and patch-level labels-to improve both the classification and the localization performances of the original model, using only a limited amount of patch-level labeled slides. In addition, we propose an attention loss term to regularize the attention between key instances, and a paired batch method to create balanced batches for the model. First, we show that the changes made to the model already improve its performance and interpretability in the weakly-supervised setting. Furthermore, when using only between 12 and 62% of the total available patch-level annotations, we can reach performance close to fully-supervised models on the tumor classification datasets DigestPath2019 and Camelyon16.
- Published
- 2023