BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizability

• URL: http://arxiv.org/abs/2303.01710v1
• Date: Fri, 3 Mar 2023 04:48:37 GMT
• Title: BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizability
• Authors: Shangqi Gao and Hangqi Zhou and Yibo Gao and Xiahai Zhuang
• Abstract summary: We propose an interpretable Bayesian framework (BayeSeg) to enhance model generalizability for medical image segmentation. Specifically, we first decompose an image into a spatial-correlated variable and a spatial-variant variable, assigning hierarchical Bayesian priors to explicitly force them to model the domain-stable shape and domain-specific appearance information respectively. Finally, we develop a variational Bayesian framework to infer the posterior distributions of these explainable variables.
• Score: 15.410162313242958
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the cross-domain distribution shift aroused from diverse medical imaging systems, many deep learning segmentation methods fail to perform well on unseen data, which limits their real-world applicability. Recent works have shown the benefits of extracting domain-invariant representations on domain generalization. However, the interpretability of domain-invariant features remains a great challenge. To address this problem, we propose an interpretable Bayesian framework (BayeSeg) through Bayesian modeling of image and label statistics to enhance model generalizability for medical image segmentation. Specifically, we first decompose an image into a spatial-correlated variable and a spatial-variant variable, assigning hierarchical Bayesian priors to explicitly force them to model the domain-stable shape and domain-specific appearance information respectively. Then, we model the segmentation as a locally smooth variable only related to the shape. Finally, we develop a variational Bayesian framework to infer the posterior distributions of these explainable variables. The framework is implemented with neural networks, and thus is referred to as deep Bayesian segmentation. Quantitative and qualitative experimental results on prostate segmentation and cardiac segmentation tasks have shown the effectiveness of our proposed method. Moreover, we investigated the interpretability of BayeSeg by explaining the posteriors and analyzed certain factors that affect the generalization ability through further ablation studies. Our code will be released via https://zmiclab.github.io/projects.html, once the manuscript is accepted for publication.

Related papers

• FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms [60.195642571004804]
  We propose FlowSDF, an image-guided conditional flow matching framework to represent the signed distance function (SDF) By learning a vector field that is directly related to the probability path of a conditional distribution of SDFs, we can accurately sample from the distribution of segmentation masks.
  arXiv  Detail & Related papers  (2024-05-28T11:47:12Z)
• RaffeSDG: Random Frequency Filtering enabled Single-source Domain Generalization for Medical Image Segmentation [41.50001361938865]
  Deep learning models often encounter challenges in making accurate inferences when there are domain shifts between the source and target data. We propose a Random frequency filtering enabled Single-source Domain Generalization algorithm (RaffeSDG) RaffeSDG promises robust out-of-domain inference with segmentation models trained on a single-source domain.
  arXiv  Detail & Related papers  (2024-05-02T12:13:00Z)
• DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus Segmentation [68.43628183890007]
  We argue that domain gaps can also be caused by different foreground (nucleus)-background ratios. First, we introduce a re-coloring method that relieves dramatic image color variations between different domains. Second, we propose a new instance normalization method that is robust to the variation in the foreground-background ratios.
  arXiv  Detail & Related papers  (2023-09-01T01:01:13Z)
• VesselMorph: Domain-Generalized Retinal Vessel Segmentation via Shape-Aware Representation [12.194439938007672]
  Domain shift is an inherent property of medical images and has become a major obstacle for large-scale deployment of learning-based algorithms. We propose a method named VesselMorph which generalizes the 2D retinal vessel segmentation task by synthesizing a shape-aware representation. VesselMorph achieves superior generalization performance compared with competing methods in different domain shift scenarios.
  arXiv  Detail & Related papers  (2023-07-01T06:02:22Z)
• Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary [64.5632303184502]
  Domain generalization typically requires data from multiple source domains for model learning. This paper studies the important yet challenging single domain generalization problem, in which a model is learned under the worst-case scenario with only one source domain to directly generalize to different unseen target domains. We present a novel approach to address this problem in medical image segmentation, which extracts and integrates the semantic shape prior information of segmentation that are invariant across domains.
  arXiv  Detail & Related papers  (2022-06-29T08:46:27Z)
• Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classification [5.6512908295414]
  We propose an unsupervised domain adaptation approach that uses graph neural networks and, disentangled semantic and domain invariant structural features. We test the proposed method for classification on two challenging medical image datasets with distribution shifts. Experiments show our method achieves state-of-the-art results compared to other domain adaptation methods.
  arXiv  Detail & Related papers  (2022-06-27T09:02:16Z)
• Joint Modeling of Image and Label Statistics for Enhancing Model Generalizability of Medical Image Segmentation [14.106339318764372]
  We propose a deep learning-based Bayesian framework, which jointly models image and label statistics. We develop a variational Bayesian framework to infer the posterior distributions of these variables, including the contour, the basis, and the label. Results on the task of cross-sequence cardiac MRI segmentation show that our method set a new state of the art for model generalizability.
  arXiv  Detail & Related papers  (2022-06-09T08:31:14Z)
• Causality-inspired Single-source Domain Generalization for Medical Image Segmentation [12.697945585457441]
  We propose a simple data augmentation approach to expose a segmentation model to synthesized domain-shifted training examples. Specifically, 1) to make the deep model robust to discrepancies in image intensities and textures, we employ a family of randomly-weighted shallow networks. We remove spurious correlations among objects in an image that might be taken by the network as domain-specific clues for making predictions, and they may break on unseen domains.
  arXiv  Detail & Related papers  (2021-11-24T14:45:17Z)
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty [111.22588110362705]
  Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference. We derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network.
  arXiv  Detail & Related papers  (2021-05-09T21:33:27Z)
• 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)
• Phase Consistent Ecological Domain Adaptation [76.75730500201536]
  We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor.
  arXiv  Detail & Related papers  (2020-04-10T06:58:03Z)

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.