C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D Late Gadolinium-enhanced Magnetic Resonance

• URL: http://arxiv.org/abs/2603.24992v1
• Date: Thu, 26 Mar 2026 03:35:35 GMT
• Title: C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D Late Gadolinium-enhanced Magnetic Resonance
• Abstract summary: C2W-Tune is a two-stage cavity-to-wall transfer framework.<n>It uses a high-accuracy LA cavity model as an anatomical prior to improve thin-wall delineation.<n>C2W-Tune achieved a Dice score of 0.78 and an HD95 of 3.15 mm, exceeding multi-class benchmarks.
• Score: 1.452875650827562
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate segmentation of the left atrial (LA) wall in 3D late gadolinium-enhanced MRI (LGE-MRI) is essential for wall thickness mapping and fibrosis quantification, yet it remains challenging due to the wall's thinness, complex anatomy, and low contrast. We propose C2W-Tune, a two-stage cavity-to-wall transfer framework that leverages a high-accuracy LA cavity model as an anatomical prior to improve thin-wall delineation. Using a 3D U-Net with a ResNeXt encoder and instance normalization, Stage 1 pre-trains the network to segment the LA cavity, learning robust atrial representations. Stage 2 transfers these weights and adapts the network to LA wall segmentation using a progressive layer-unfreezing schedule to preserve endocardial features while enabling wall-specific refinement. Experiments on the 2018 LA Segmentation Challenge dataset demonstrate substantial gains over an architecture-matched baseline trained from scratch: wall Dice improves from 0.623 to 0.814, and Surface Dice at 1 mm improves from 0.553 to 0.731. Boundary errors were substantially reduced, with the 95th-percentile Hausdorff distance (HD95) decreasing from 2.95 mm to 2.55 mm and the average symmetric surface distance (ASSD) from 0.71 mm to 0.63 mm. Furthermore, even with reduced supervision (70 training volumes sampled from the same training pool), C2W-Tune achieved a Dice score of 0.78 and an HD95 of 3.15 mm, maintaining competitive performance and exceeding multi-class benchmarks that typically report Dice values around 0.6-0.7. These results show that anatomically grounded task transfer with controlled fine-tuning improves boundary accuracy for thin LA wall segmentation in 3D LGE-MRI.

Related papers

• LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation [45.86925813888675]
  Fine-tuning SAM 3 on lung tumours raises the Dice obtained from a single point prompt from 0.298 to 0.757, and seven rounds of corrections raise it further to 0.765.<n>We propose LeCor, which performs test-time training on a small set of case adapters that are reset for every case.<n>LeCor raises the Dice reached after seven correction rounds from 0.787 with the fine-tuned model to 0.827, reduces the number of cases that never reach a Dice of 0.80 from 47 to 27, and reaches in three correction rounds the accuracy that the fine-tuned model attains in seven.
  arXiv  Detail & Related papers  (2026-09-08T21:49:56Z)
• Native-Space 3D CarveMix for Multi-Site T1w Stroke Segmentation [0.11739570123067224]
  We combine a MedNeXt-L backbone with on-the-fly 3D CarveMix augmentation that pastes real lesion patches into healthy brain regions during training.<n>Our method achieves a mean 5-fold cross-validation Dice of 0.648 at 500 epochs, a +0.018 improvement over the MedNeXt-L backbone at a matched training budget.
  arXiv  Detail & Related papers  (2026-08-24T22:45:11Z)
• A Neighborhood Attention Transformer Network for Enhanced 3D Segmentation of the Left Anterior Descending Artery [5.486895610501164]
  Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose sparing in thoracic radiotherapy.<n>We propose NA-UNETR, a 3D transformer-based segmentation model whose Neighborhood Attention (NA) and Dilated NA (DiNA) blocks jointly capture fine structural detail and long-range context.<n>A composite Dice-Focal and Hausdorff loss, dynamically balanced via homoscedastic uncertainty, improves overlap and boundary accuracy.
  arXiv  Detail & Related papers  (2026-08-12T17:13:59Z)
• DINO-3DRA: Leveraging 2D Foundation Model Semantics for 3D Cerebral Aneurysm Segmentation [42.65813094687315]
  We propose DINO-3DRA, a dual-path framework achieving effective cross-dimensional semantic transfer.<n>On multi-centre 3DRA data, DINO-3DRA achieves state-of-the-art aneurysm segmentation with only 5.72M trainable parameters.
  arXiv  Detail & Related papers  (2026-08-07T21:17:11Z)
• Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention [46.03321798937855]
  We show that the standard Generalized Dice Loss (GDL) is unstable under domain shift.<n>We propose a Subspace-Aware Class Attention (SACA) module that re-calibrates the bottleneck features and raises Enhancing Tumor (ET) sensitivity by 8%.
  arXiv  Detail & Related papers  (2026-07-23T09:59:30Z)
• Parameter-Efficient Adaptation of SAM 3 for Automated ITV Generation from 4DCT Images [0.0]
  Four-dimensional computed tomography (4DCT) captures the full respiratory cycle of thoracic anatomy.<n>Current Internal Target Volume contouring process each phase in isolation, discarding temporal coherence and leaving vulnerable to phase-specific artifacts.<n>We present a framework that applies parameter-efficient fine-tuning to the Segment Anything Model 3 (SAM 3) via low-rank adaptation (LoRA)<n>With only seven annotated volumes, the framework retains over 95% of full-data accuracy, and the entire pipeline is trainable on a single consumer-grade GPU.
  arXiv  Detail & Related papers  (2026-06-14T05:12:57Z)
• Attenuation-Resilient Alternating Optimization for Laparoscopic Liver Landmark Detection [45.05240977535136]
  Liver surface landmark detection is a fundamental prerequisite for anatomical guidance in laparoscopic liver surgery.<n>It remains unreliable in practice due to two pervasive challenges: illumination attenuation in underexposed regions and the structural mismatch between pixel-wise localization and continuous curvilinear geometry.<n>We propose A2ONet, an attenuation-resilient alternating optimization network for robust liver landmark detection.
  arXiv  Detail & Related papers  (2026-05-26T07:06:10Z)
• Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning [1.0680378628718095]
  We propose a Model-Agnostic Meta-Learning (MAML) framework for left atrial wall segmentation.<n>MAML is meta-trained on the wall task together with auxiliary left atrial and right atrial cavity tasks.<n>We evaluated MAML segmentation performance on a hold-out test set and assessed robustness under an unseen synthetic shift.
  arXiv  Detail & Related papers  (2026-03-26T03:25:40Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler [49.03919553747297]
  We propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries.<n>No prior studies have explored AI-driven cerebrovascular segmentation using Transcranial Color-coded Doppler (TCCD)<n>The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels.
  arXiv  Detail & Related papers  (2025-08-19T14:41:22Z)
• Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin Surface [13.161605581865357]
  Surf2CT is a framework that synthesizes full 3D computed tomography (CT) volumes of the human torso from external surface scans and demographic data.<n>We trained our model on a combined dataset of 3,198 torso CT scans sourced from Massachusetts General Hospital (MGH) and the AutoPET challenge.
  arXiv  Detail & Related papers  (2025-05-28T16:01:36Z)
• 3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation [0.0]
  A three-dimensional convolutional neural network was developed to classify T1-weighted brain scans as healthy or Alzheimer.<n>The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output.
  arXiv  Detail & Related papers  (2025-05-07T03:32:25Z)
• Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI [43.47826598981827]
  We introduce HybridVNet, a novel architecture for direct image-to-mesh extraction.<n>We show it can efficiently handle surface and volumetric meshes by encoding them as graph structures.<n>Our model combines traditional convolutional networks with variational graph generative models, deep supervision and mesh-specific regularisation.
  arXiv  Detail & Related papers  (2023-11-22T21:51:29Z)
• The Three-Dimensional Structural Configuration of the Central Retinal Vessel Trunk and Branches as a Glaucoma Biomarker [41.97805846007449]
  We trained a deep learning network to automatically segment the CRVT&B from the B-scans of the optical coherence tomography volume of the optic nerve head (ONH) The 3D and 2D diagnostic networks were able to differentiate glaucoma from non-glaucoma subjects with accuracies of 82.7% and 83.3%, respectively.
  arXiv  Detail & Related papers  (2021-11-07T04:41:49Z)
• Segmentation of the Myocardium on Late-Gadolinium Enhanced MRI based on 2.5 D Residual Squeeze and Excitation Deep Learning Model [55.09533240649176]
  The aim of this work is to develop an accurate automatic segmentation method based on deep learning models for the myocardial borders on LGE-MRI. A total number of 320 exams (with a mean number of 6 slices per exam) were used for training and 28 exams used for testing. The performance analysis of the proposed ensemble model in the basal and middle slices was similar as compared to intra-observer study and slightly lower at apical slices.
  arXiv  Detail & Related papers  (2020-05-27T20:44:38Z)

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.