Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
This addresses the problem of domain shifts in histopathology images for cancer classification, which is incremental as it builds on existing domain generalization methods.
The paper tackles the challenge of domain generalization in computational histopathology for cancer detection by focusing on nuclear morphology and organization as domain-invariant features. The result shows that integrating nuclear segmentation masks with original images during training improves out-of-domain generalization and increases robustness to image corruptions and adversarial attacks across multiple datasets.
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/