Histopathology Image Classification using Deep Manifold Contrastive Learning

TL;DR

This paper introduces a novel contrastive learning approach for histopathology image classification that uses geodesic distance on a feature manifold, improving performance over traditional cosine similarity methods.

Contribution

It proposes a geodesic-distance-based contrastive learning method with efficient prototype clustering for histopathology images, addressing limitations of cosine similarity.

Findings

Outperforms state-of-the-art contrastive learning methods

Effective on real-world histopathology datasets

Reduces computational overhead with prototype clustering

Abstract

Contrastive learning has gained popularity due to its robustness with good feature representation performance. However, cosine distance, the commonly used similarity metric in contrastive learning, is not well suited to represent the distance between two data points, especially on a nonlinear feature manifold. Inspired by manifold learning, we propose a novel extension of contrastive learning that leverages geodesic distance between features as a similarity metric for histopathology whole slide image classification. To reduce the computational overhead in manifold learning, we propose geodesic-distance-based feature clustering for efficient contrastive loss evaluation using prototypes without time-consuming pairwise feature similarity comparison. The efficacy of the proposed method is evaluated on two real-world histopathology image datasets. Results demonstrate that our method outperforms state-of-the-art cosine-distance-based contrastive learning methods.