Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology

TL;DR

This paper introduces PANTHER, an unsupervised, prototype-based method for learning generalizable, task-agnostic slide representations from pathology images, leveraging morphological redundancy for improved interpretability and performance.

Contribution

The paper proposes PANTHER, a novel unsupervised approach using Gaussian mixture models to create morphological prototypes for slide representation learning in pathology.

Findings

PANTHER outperforms supervised MIL baselines in multiple tasks.

The method provides new insights into tissue morphology.

PANTHER achieves comparable results across 13 datasets.

Abstract

Representation learning of pathology whole-slide images (WSIs) has been has primarily relied on weak supervision with Multiple Instance Learning (MIL). However, the slide representations resulting from this approach are highly tailored to specific clinical tasks, which limits their expressivity and generalization, particularly in scenarios with limited data. Instead, we hypothesize that morphological redundancy in tissue can be leveraged to build a task-agnostic slide representation in an unsupervised fashion. To this end, we introduce PANTHER, a prototype-based approach rooted in the Gaussian mixture model that summarizes the set of WSI patches into a much smaller set of morphological prototypes. Specifically, each patch is assumed to have been generated from a mixture distribution, where each mixture component represents a morphological exemplar. Utilizing the estimated mixture parameters, we then construct a compact slide representation that can be readily used for a wide range of downstream tasks. By performing an extensive evaluation of PANTHER on subtyping and survival tasks using 13 datasets, we show that 1) PANTHER outperforms or is on par with supervised MIL baselines and 2) the analysis of morphological prototypes brings new qualitative and quantitative insights into model interpretability.