Improving Cross-Site Whole-Heart Segmentation

• URL: http://arxiv.org/abs/2608.25109v1
• Date: Tue, 25 Aug 2026 20:03:53 GMT
• Title: Improving Cross-Site Whole-Heart Segmentation
• Abstract summary: Whole-heart segmentation from CT and MRI is essential for quantitative cardiac image analysis.<n>We propose a modality-routed 3D cardiac segmentation pipeline that combines TotalSegmentator-componentd nnU-Netv2 models with site-characterized, label-preserving appearance augmentation.<n>Results suggest that site-motivated appearance augmentation is a practical strategy for improving cross-site robustness in limited-data whole-heart segmentation.
• Score: 6.716055961221493
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Whole-heart segmentation from CT and MRI is essential for quantitative cardiac image analysis, but remains challenging under multi-center and multi-modality distribution shift. In the CARE whole-heart segmentation task, models must generalize from limited labeled sites to unseen acquisition distributions, where variation in spacing, intensity, reconstruction texture, and anatomy can degrade out-of-distribution performance. We propose a modality-routed 3D cardiac segmentation pipeline that combines TotalSegmentator-initialized nnU-Netv2 models with site-characterized, label-preserving appearance augmentation. We first characterize the available sites using measurable image properties and use this analysis to motivate candidate data-space generalization routes. The final retained recipe applies Bias Field + Bezier appearance augmentation, combining smooth spatial intensity perturbation with nonlinear intensity remapping, followed by lightweight class-wise largest-connected-component cleanup. On the primary held-out-site validation splits, the final configuration improves CT mean Dice from 0.8350 to 0.9135 and MRI mean Dice from 0.7695 to 0.7830, while also reducing HD95. These results suggest that site-motivated appearance augmentation is a practical strategy for improving cross-site robustness in limited-data whole-heart segmentation. Our code can be found in https://github.com/Purdue-M2/Improving-Cross-Site-Whole-Heart-Segmentation

Related papers

• Towards Voxel Spacing Consistency for Medical Image Segmentation [56.992050146446495]
  We study the correlation between image resampling and segmentation, and propose Consispace, a semantic-aware resampling framework.<n> Consispace achieves consistent voxel spacing in the axial direction while preserving anatomical and semantic consistency.
  arXiv  Detail & Related papers  (2026-06-30T15:42:23Z)
• Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework [0.0]
  We train a single end-to-end network that goes directly from a raw 3D medical image to a smooth, simulation-ready cardiac surface mesh.<n>The core is a 3D Swin Transformer encoder-decoder that extracts volumetric features from CT or MRI volumes, paired with a Graph Attention Network head that iteratively deforms a template mesh to fit the patient's cardiac boundary.<n>Every mesh is produced in a single forward pass -- no Marching Cubes, no smoothing filters, no manual cleanup.
  arXiv  Detail & Related papers  (2026-06-11T10:55:55Z)
• Anatomy Guided Coronary Artery Segmentation from CCTA Using Spatial Frequency Joint Modeling [10.73944733412427]
  We propose a coronary artery segmentation framework that integrates myocardial anatomical priors, structure aware feature encoding, and three dimensional wavelet inverse wavelet transformations.<n> Experimental results demonstrate that the proposed method achieves a Dice coefficient of 0.8082, Sensitivity of 0.7946, Precision of 0.8471, and an HD95 of 9.77 mm, outperforming several mainstream segmentation models.
  arXiv  Detail & Related papers  (2025-12-14T04:12:40Z)
• Large Kernel MedNeXt for Breast Tumor Segmentation and Self-Normalizing Network for pCR Classification in Magnetic Resonance Images [0.0]
  We employ a large- kernel MedNeXt architecture with a two-stage training strategy that expands the receptive field from 3x3x3 to 5x5x5 kernels.<n>For pCR classification, we trained a self-normalizing network (SNN) on radiomic features extracted from the predicted segmentations.<n>Our findings highlight the benefits of combining larger receptive fields and radiomics-driven classification.
  arXiv  Detail & Related papers  (2025-08-03T16:37:14Z)
• Myocardial Region-guided Feature Aggregation Net for Automatic Coronary artery Segmentation and Stenosis Assessment using Coronary Computed Tomography Angiography [13.885760158090692]
  Myocardial Region-guided Feature Aggregation Net is a novel U-shaped dual-encoder architecture that integrates anatomical prior knowledge to enhance robustness in coronary artery segmentation.<n>Our framework incorporates three key innovations: (1) a Myocardial Region-guided Module that directs attention to coronary regions via bridging expansion and multi-scale feature fusion, (2) a Residual Feature Extraction Module that combines parallel spatial channel attention with residual blocks to enhance local-global feature discrimination, and (3) a Multi-scale Feature Fusion Module for adaptive aggregation of hierarchical vascular features.
  arXiv  Detail & Related papers  (2025-04-27T16:43:52Z)
• KaLDeX: Kalman Filter based Linear Deformable Cross Attention for Retina Vessel Segmentation [46.57880203321858]
  We propose a novel network (KaLDeX) for vascular segmentation leveraging a Kalman filter based linear deformable cross attention (LDCA) module. Our approach is based on two key components: Kalman filter (KF) based linear deformable convolution (LD) and cross-attention (CA) modules. The proposed method is evaluated on retinal fundus image datasets (DRIVE, CHASE_BD1, and STARE) as well as the 3mm and 6mm of the OCTA-500 dataset.
  arXiv  Detail & Related papers  (2024-10-28T16:00:42Z)
• Y-CA-Net: A Convolutional Attention Based Network for Volumetric Medical Image Segmentation [47.12719953712902]
  discriminative local features are key components for the performance of attention-based VS methods. We incorporate the convolutional encoder branch with transformer backbone to extract local and global features in a parallel manner. Y-CT-Net achieves competitive performance on multiple medical segmentation tasks.
  arXiv  Detail & Related papers  (2024-10-01T18:50:45Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• Semi-Supervised Segmentation of Multi-vendor and Multi-center Cardiac MRI using Histogram Matching [0.0]
  We propose a semi-supervised segmentation setup for leveraging unlabeled data to segment Left-ventricle, Right-ventricle, and Myocardium. Handling the class imbalanced data issue using dice loss, the enhanced supervised model is able to achieve better dice scores. The model achieves average dice scores of 0.921, 0.926, and 0.891 for Left-ventricle, Right-ventricle, and Myocardium respectively.
  arXiv  Detail & Related papers  (2023-02-22T08:23:19Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Hepatic vessel segmentation based on 3Dswin-transformer with inductive biased multi-head self-attention [46.46365941681487]
  We propose a robust end-to-end vessel segmentation network called Indu BIased Multi-Head Attention Vessel Net. We introduce the voxel-wise embedding rather than patch-wise embedding to locate precise liver vessel voxels. On the other hand, we propose inductive biased multi-head self-attention which learns inductive biased relative positional embedding from absolute position embedding.
  arXiv  Detail & Related papers  (2021-11-05T10:17:08Z)

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.