Adaptive Prototype-based Interpretable Grading of Prostate Cancer

TL;DR

This paper introduces an interpretable, prototype-based deep learning framework for prostate cancer grading that enhances trustworthiness and aligns with pathologists' workflows, validated on benchmark datasets.

Contribution

The novel weakly-supervised prototype-based framework improves interpretability and performance in prostate cancer grading, incorporating a dynamic pruning mechanism for heterogeneity.

Findings

Achieves reliable grading on PANDA and SICAP datasets.

Provides interpretable reasoning similar to pathologist workflows.

Outperforms existing methods in accuracy and interpretability.

Abstract

Prostate cancer being one of the frequently diagnosed malignancy in men, the rising demand for biopsies places a severe workload on pathologists. The grading procedure is tedious and subjective, motivating the development of automated systems. Although deep learning has made inroads in terms of performance, its limited interpretability poses challenges for widespread adoption in high-stake applications like medicine. Existing interpretability techniques for prostate cancer classifiers provide a coarse explanation but do not reveal why the highlighted regions matter. In this scenario, we propose a novel prototype-based weakly-supervised framework for an interpretable grading of prostate cancer from histopathology images. These networks can prove to be more trustworthy since their explicit reasoning procedure mirrors the workflow of a pathologist in comparing suspicious regions with clinically validated examples. The network is initially pre-trained at patch-level to learn robust prototypical features associated with each grade. In order to adapt it to a weakly-supervised setup for prostate cancer grading, the network is fine-tuned with a new prototype-aware loss function. Finally, a new attention-based dynamic pruning mechanism is introduced to handle inter-sample heterogeneity, while selectively emphasizing relevant prototypes for optimal performance. Extensive validation on the benchmark PANDA and SICAP datasets confirms that the framework can serve as a reliable assistive tool for pathologists in their routine diagnostic workflows.