ALFA -- Leveraging All Levels of Feature Abstraction for Enhancing the Generalization of Histopathology Image Classification Across Unseen Hospitals

TL;DR

This paper introduces a comprehensive approach that leverages multiple feature abstraction levels and domain alignment techniques to improve the generalization of histopathology image classification across unseen hospitals, demonstrating superior robustness in diverse datasets.

Contribution

The paper presents a novel methodology combining augmentation-based self-supervision, domain alignment, and feature disentanglement to enhance model generalization across different hospital sources.

Findings

Improved accuracy on PACS, synthetic, and TCGA datasets.

Enhanced robustness to out-of-distribution hospital images.

Effective disentanglement of semantic features across abstraction levels.

Abstract

We propose an exhaustive methodology that leverages all levels of feature abstraction, targeting an enhancement in the generalizability of image classification to unobserved hospitals. Our approach incorporates augmentation-based self-supervision with common distribution shifts in histopathology scenarios serving as the pretext task. This enables us to derive invariant features from training images without relying on training labels, thereby covering different abstraction levels. Moving onto the subsequent abstraction level, we employ a domain alignment module to facilitate further extraction of invariant features across varying training hospitals. To represent the highly specific features of participating hospitals, an encoder is trained to classify hospital labels, independent of their diagnostic labels. The features from each of these encoders are subsequently disentangled to minimize redundancy and segregate the features. This representation, which spans a broad spectrum of semantic information, enables the development of a model demonstrating increased robustness to unseen images from disparate distributions. Experimental results from the PACS dataset (a domain generalization benchmark), a synthetic dataset created by applying histopathology-specific jitters to the MHIST dataset (defining different domains with varied distribution shifts), and a Renal Cell Carcinoma dataset derived from four image repositories from TCGA, collectively indicate that our proposed model is adept at managing varying levels of image granularity. Thus, it shows improved generalizability when faced with new, out-of-distribution hospital images.