Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology

TL;DR

This paper presents a simple yet effective method for improving out-of-domain cancer classification in histopathology by focusing on nuclear features and aligning representations of images and nuclear masks, enhancing robustness and generalisation.

Contribution

The authors introduce a novel approach that combines nuclear segmentation masks with original images and a regularisation technique to improve domain generalisation in histopathology cancer detection.

Findings

Improved out-of-domain generalisation across multiple datasets.

Enhanced robustness to image corruptions.

Better resistance to adversarial attacks.

Abstract

Domain generalisation in computational histopathology is challenging because the images are substantially affected by differences among hospitals due to factors like fixation and staining of tissue and imaging equipment. We hypothesise that focusing on nuclei can improve the out-of-domain (OOD) generalisation in cancer detection. We propose a simple approach to improve OOD generalisation for cancer detection by focusing on nuclear morphology and organisation, as these are domain-invariant features critical in cancer detection. Our approach integrates original images with nuclear segmentation masks during training, encouraging the model to prioritise nuclei and their spatial arrangement. Going beyond mere data augmentation, we introduce a regularisation technique that aligns the representations of masks and original images. We show, using multiple datasets, that our method improves OOD generalisation and also leads to increased robustness to image corruptions and adversarial attacks. The source code is available at https://github.com/undercutspiky/SFL/