Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms

• URL: http://arxiv.org/abs/2411.05223v1
• Date: Thu, 07 Nov 2024 22:35:17 GMT
• Title: Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms
• Authors: Boqi Chen, Yuanzhi Zhu, Yunke Ao, Sebastiano Caprara, Reto Sutter, Gunnar Rätsch, Ender Konukoglu, Anna Susmelj,
• Abstract summary: Single-source domain generalization aims to learn a model from a single source domain that can generalize well on unseen target domains. This is an important task in computer vision, particularly relevant to medical imaging where domain shifts are common. We combine causality-inspired theoretical insights on learning domain-invariant representations with recent advancements in diffusion-based augmentation to improve generalization across diverse imaging modalities.
• Score: 16.699205051836657
• License:
• Abstract: Single-source domain generalization (SDG) aims to learn a model from a single source domain that can generalize well on unseen target domains. This is an important task in computer vision, particularly relevant to medical imaging where domain shifts are common. In this work, we consider a challenging yet practical setting: SDG for cross-modality medical image segmentation. We combine causality-inspired theoretical insights on learning domain-invariant representations with recent advancements in diffusion-based augmentation to improve generalization across diverse imaging modalities. Guided by the ``intervention-augmentation equivariant'' principle, we use controlled diffusion models (DMs) to simulate diverse imaging styles while preserving the content, leveraging rich generative priors in large-scale pretrained DMs to comprehensively perturb the multidimensional style variable. Extensive experiments on challenging cross-modality segmentation tasks demonstrate that our approach consistently outperforms state-of-the-art SDG methods across three distinct anatomies and imaging modalities. The source code is available at \href{https://github.com/ratschlab/ICMSeg}{https://github.com/ratschlab/ICMSeg}.

Related papers

• Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis [13.794335166617063]
  The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets. Traditional single-source domain generalization methods rely on stacking data augmentation techniques to minimize domain discrepancies. We propose Random Amplitude Spectrum Synthesis (RASS) as a training augmentation for medical images.
  arXiv  Detail & Related papers  (2024-09-07T08:58:04Z)
• Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation [20.97329150274455]
  We propose a multi-source domain generalization method called Treasure in Distribution (TriD) TriD constructs an unprecedented search space to obtain the model with strong robustness by randomly sampling from a uniform distribution. Experiments on two medical segmentation tasks demonstrate that our TriD achieves superior generalization performance on unseen target-domain data.
  arXiv  Detail & Related papers  (2023-05-31T15:33:57Z)
• M-GenSeg: Domain Adaptation For Target Modality Tumor Segmentation With Annotation-Efficient Supervision [4.023899199756184]
  M-GenSeg is a new semi-supervised generative training strategy for cross-modality tumor segmentation. We evaluate the performance on a brain tumor segmentation dataset composed of four different contrast sequences. Unlike the prior art, M-GenSeg also introduces the ability to train with a partially annotated source modality.
  arXiv  Detail & Related papers  (2022-12-14T15:19:06Z)
• CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation [38.44458104455557]
  We propose an efficient Contrastive Domain Disentanglement and Style Augmentation (CDDSA) framework for generalizable medical image segmentation. First, a disentangle network is proposed to decompose an image into a domain-invariant anatomical representation and a domain-specific style code. Second, to achieve better disentanglement, a contrastive loss is proposed to encourage the style codes from the same domain and different domains to be compact and divergent.
  arXiv  Detail & Related papers  (2022-11-22T08:25:35Z)
• Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization [29.470385509955687]
  We propose a novel dual-normalization module by leveraging the augmented source-similar and source-dissimilar images. Our method outperforms other state-of-the-art domain generalization methods.
  arXiv  Detail & Related papers  (2021-12-21T13:18:46Z)
• Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation [62.49837463676111]
  We propose a novel scheme of episodic training with task augmentation on medical imaging classification. Motivated by the limited number of source domains in real-world medical deployment, we consider the unique task-level overfitting.
  arXiv  Detail & Related papers  (2021-06-13T03:56:59Z)
• 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)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains [68.73614619875814]
  We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation. Experimental results show that our approach outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains.
  arXiv  Detail & Related papers  (2020-07-04T07:56:02Z)
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [84.7571086566595]
  We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
  arXiv  Detail & Related papers  (2020-03-31T11:50:43Z)
• 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)

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.