Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learning

• URL: http://arxiv.org/abs/2508.07539v1
• Date: Mon, 11 Aug 2025 01:38:31 GMT
• Title: Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learning
• Authors: Yuki Shigeyasu, Shota Harada, Akihiko Yoshizawa, Kazuhiro Terada, Naoki Nakazima, Mariyo Kurata, Hiroyuki Abe, Tetsuo Ushiku, Ryoma Bise,
• Abstract summary: We focus on domain shifts in pathological images by focusing on shifts within whole slide images(WSIs), such as patient characteristics and tissue thickness.<n>Traditional approaches rely on multi-hospital data, but data collection challenges often make this impractical.<n>The proposed method introduces a two-stage contrastive learning approach WSI-level and patch-level contrastive learning to minimize these gaps effectively.
• Score: 4.140534091544092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we address domain shifts in pathological images by focusing on shifts within whole slide images~(WSIs), such as patient characteristics and tissue thickness, rather than shifts between hospitals. Traditional approaches rely on multi-hospital data, but data collection challenges often make this impractical. Therefore, the proposed domain generalization method captures and leverages intra-hospital domain shifts by clustering WSI-level features from non-tumor regions and treating these clusters as domains. To mitigate domain shift, we apply contrastive learning to reduce feature gaps between WSI pairs from different clusters. The proposed method introduces a two-stage contrastive learning approach WSI-level and patch-level contrastive learning to minimize these gaps effectively.

Related papers

• Open-Vocabulary Domain Generalization in Urban-Scene Segmentation [83.15573353963235]
  Domain Generalization in Semantic Domain (DG-SS) aims to enable segmentation models to perform robustly in unseen environments.<n>Recent progress in Vision-Language Models (VLMs) has advanced Open-Vocabulary Semantic (OV-SS) by enabling models to recognize a broader range of concepts.<n>Yet, these models remain sensitive to domain shifts and struggle to maintain robustness when deployed in unseen environments.<n>We propose S2-Corr, a state-space-driven text-image correlation refinement mechanism that produces more consistent text-image correlations under distribution changes.
  arXiv  Detail & Related papers  (2026-02-21T14:32:27Z)
• Unsupervised Domain Adaptation via Content Alignment for Hippocampus Segmentation [5.118486547573804]
  This paper presents a novel unsupervised domain adaptation framework that addresses domain shifts encountered in cross-domain hippocampus segmentation from MRI.<n>Our approach combines efficient style harmonisation through z-normalisation with a bidirectional deformable image registration (DIR) strategy.<n>We validate our approach through comprehensive evaluations on both a synthetic dataset and three MRI hippocampus datasets representing populations with varying degrees of atrophy.
  arXiv  Detail & Related papers  (2025-10-15T01:34:41Z)
• HASD: Hierarchical Adaption for pathology Slide-level Domain-shift [41.62754003105711]
  We propose a Hierarchical Adaptation framework for Slide-level Domain-shift (HASD)<n>HASD achieves multi-scale feature consistency and computationally efficient slide-level domain adaptation.<n>We validate our method on two slide-level tasks across five datasets.
  arXiv  Detail & Related papers  (2025-06-30T09:52:01Z)
• Glioma subtype classification from histopathological images using in-domain and out-of-domain transfer learning: An experimental study [9.161480191416551]
  We compare various transfer learning strategies and deep learning architectures for computer-aided classification of adult-type diffuse gliomas. A semi-supervised learning approach is proposed, where the fine-tuned models are utilized to predict the labels of unannotated regions of the whole slide images. The models are subsequently retrained using the ground-truth labels and weak labels determined in the previous step, providing superior performance in comparison to standard in-domain transfer learning.
  arXiv  Detail & Related papers  (2023-09-29T13:22:17Z)
• A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
  Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
  arXiv  Detail & Related papers  (2023-08-02T03:16:12Z)
• Cluster Entropy: Active Domain Adaptation in Pathological Image Segmentation [7.500364675640502]
  We propose a cluster entropy for selecting an effective whole slide image (WSI) that is used for semi-supervised domain adaptation. This approach can measure how the image features of the WSI cover the entire distribution of the target domain. Our approach achieved competitive results against the prior arts on datasets collected from two hospitals.
  arXiv  Detail & Related papers  (2023-04-26T12:53:41Z)
• Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
  In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme. Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor. The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
  arXiv  Detail & Related papers  (2021-05-17T10:11:45Z)
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation [51.93711960601973]
  We propose a novel margin preserving self-paced contrastive Learning model for cross-modal medical image segmentation. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. Experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance.
  arXiv  Detail & Related papers  (2021-03-15T15:23:10Z)
• Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation [74.3349233035632]
  Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) do not consider an inter-class variation within the target domain itself or estimated category. We introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. Our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.
  arXiv  Detail & Related papers  (2020-12-15T11:36:21Z)
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation [73.84166499988443]
  We present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA) Our proposed SIFA conducts synergistic alignment of domains from both image and feature perspectives. Experimental results on two different tasks demonstrate that our SIFA method is effective in improving segmentation performance on unlabeled target images.
  arXiv  Detail & Related papers  (2020-02-06T13:49:47Z)
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation [109.89213619785676]
  Few-shot classification aims to recognize novel categories with only few labeled images in each class. Existing metric-based few-shot classification algorithms predict categories by comparing the feature embeddings of query images with those from a few labeled images. While promising performance has been demonstrated, these methods often fail to generalize to unseen domains.
  arXiv  Detail & Related papers  (2020-01-23T18:55:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.