Hospital-Agnostic Image Representation Learning in Digital Pathology

TL;DR

This paper proposes a hospital-agnostic domain generalization method for digital pathology images to improve the robustness of deep learning models across diverse acquisition sources, addressing variability and domain shift.

Contribution

It introduces a novel domain generalization approach that enhances deep neural network performance on unseen hospital data in digital pathology.

Findings

Improved classification accuracy on unseen hospital data.

Enhanced low-dimensional latent space representation.

Supervised learning performs poorly across hospitals without domain generalization.

Abstract

Whole Slide Images (WSIs) in digital pathology are used to diagnose cancer subtypes. The difference in procedures to acquire WSIs at various trial sites gives rise to variability in the histopathology images, thus making consistent diagnosis challenging. These differences may stem from variability in image acquisition through multi-vendor scanners, variable acquisition parameters, and differences in staining procedure; as well, patient demographics may bias the glass slide batches before image acquisition. These variabilities are assumed to cause a domain shift in the images of different hospitals. It is crucial to overcome this domain shift because an ideal machine-learning model must be able to work on the diverse sources of images, independent of the acquisition center. A domain generalization technique is leveraged in this study to improve the generalization capability of a Deep Neural Network (DNN), to an unseen histopathology image set (i.e., from an unseen hospital/trial site) in the presence of domain shift. According to experimental results, the conventional supervised-learning regime generalizes poorly to data collected from different hospitals. However, the proposed hospital-agnostic learning can improve the generalization considering the low-dimensional latent space representation visualization, and classification accuracy results.