MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khan, Hikmat, Zaidi, Syed Farhan Alam, Shah, Pir Masoom, Balakrishnan, Kiruthika, Khan, Rabia, Waqas, Muhammad, Wu, Jia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912559990308864
author Khan, Hikmat
Zaidi, Syed Farhan Alam
Shah, Pir Masoom
Balakrishnan, Kiruthika
Khan, Rabia
Waqas, Muhammad
Wu, Jia
author_facet Khan, Hikmat
Zaidi, Syed Farhan Alam
Shah, Pir Masoom
Balakrishnan, Kiruthika
Khan, Rabia
Waqas, Muhammad
Wu, Jia
contents Domain generalization in computational histopathology is hindered by heterogeneity in whole slide images (WSIs), caused by variations in tissue preparation, staining, and imaging conditions across institutions. Unlike machine learning systems, pathologists rely on domain-invariant morphological cues such as nuclear atypia (enlargement, irregular contours, hyperchromasia, chromatin texture, spatial disorganization), structural atypia (abnormal architecture and gland formation), and overall morphological atypia that remain diagnostic across diverse settings. Motivated by this, we hypothesize that explicitly modeling biologically robust nuclear morphology and spatial organization will enable the learning of cancer representations that are resilient to domain shifts. We propose MorphGen (Morphology-Guided Generalization), a method that integrates histopathology images, augmentations, and nuclear segmentation masks within a supervised contrastive learning framework. By aligning latent representations of images and nuclear masks, MorphGen prioritizes diagnostic features such as nuclear and morphological atypia and spatial organization over staining artifacts and domain-specific features. To further enhance out-of-distribution robustness, we incorporate stochastic weight averaging (SWA), steering optimization toward flatter minima. Attention map analyses revealed that MorphGen primarily relies on nuclear morphology, cellular composition, and spatial cell organization within tumors or normal regions for final classification. Finally, we demonstrate resilience of the learned representations to image corruptions (such as staining artifacts) and adversarial attacks, showcasing not only OOD generalization but also addressing critical vulnerabilities in current deep learning systems for digital pathology. Code, datasets, and trained models are available at: https://github.com/hikmatkhan/MorphGen
format Preprint
id arxiv_https___arxiv_org_abs_2509_00311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification
Khan, Hikmat
Zaidi, Syed Farhan Alam
Shah, Pir Masoom
Balakrishnan, Kiruthika
Khan, Rabia
Waqas, Muhammad
Wu, Jia
Computer Vision and Pattern Recognition
Domain generalization in computational histopathology is hindered by heterogeneity in whole slide images (WSIs), caused by variations in tissue preparation, staining, and imaging conditions across institutions. Unlike machine learning systems, pathologists rely on domain-invariant morphological cues such as nuclear atypia (enlargement, irregular contours, hyperchromasia, chromatin texture, spatial disorganization), structural atypia (abnormal architecture and gland formation), and overall morphological atypia that remain diagnostic across diverse settings. Motivated by this, we hypothesize that explicitly modeling biologically robust nuclear morphology and spatial organization will enable the learning of cancer representations that are resilient to domain shifts. We propose MorphGen (Morphology-Guided Generalization), a method that integrates histopathology images, augmentations, and nuclear segmentation masks within a supervised contrastive learning framework. By aligning latent representations of images and nuclear masks, MorphGen prioritizes diagnostic features such as nuclear and morphological atypia and spatial organization over staining artifacts and domain-specific features. To further enhance out-of-distribution robustness, we incorporate stochastic weight averaging (SWA), steering optimization toward flatter minima. Attention map analyses revealed that MorphGen primarily relies on nuclear morphology, cellular composition, and spatial cell organization within tumors or normal regions for final classification. Finally, we demonstrate resilience of the learned representations to image corruptions (such as staining artifacts) and adversarial attacks, showcasing not only OOD generalization but also addressing critical vulnerabilities in current deep learning systems for digital pathology. Code, datasets, and trained models are available at: https://github.com/hikmatkhan/MorphGen
title MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.00311