Authors:
Mohamad Mohamad
1
;
Francesco Ponzio
2
;
Maxime Gassier
3
;
Nicolas Pote
3
;
Damien Ambrosetti
4
and
Xavier Descombes
1
Affiliations:
1
Université Côte d’Azur, INRIA, CNRS, I3S, INSERM, IBV, Sophia Antipolis, France
;
2
Department of Control and Computer Engineering, Politecnico di Torino, Turin, Italy
;
3
Department of Pathology, Bichat Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France
;
4
Department of Pathology, CHU Nice, Université Côte d’Azur, Nice, France
Keyword(s):
Deep Reinforcement Learning, Computational Pathology, Whole Slide Images, Medical Image Analysis, Goal-Conditioned Reinforcement Learning.
Abstract:
In computational pathology, whole slide images represent the primary data source for AI-driven diagnostic algorithms. However, due to their high resolution and large size, these images undergo a patching phase. In this paper, we approach the diagnostic process from a pathologist’s perspective, modeling it as a Sequential decision-making problem using reinforcement learning. We build a foundational environment designed to support a range of whole slide applications. We showcase its capability by using it to construct a toy goal-conditioned Navigation environment. Finally, we present an agent trained within this environment and provide results that emphasize both the promise of reinforcement learning in histopathology and the distinct challenges it faces.