Unified Review and Benchmark of Deep Segmentation Architectures for Cardiac Ultrasound on CAMUS

• URL: http://arxiv.org/abs/2601.00839v1
• Date: Sat, 27 Dec 2025 06:07:57 GMT
• Title: Unified Review and Benchmark of Deep Segmentation Architectures for Cardiac Ultrasound on CAMUS
• Abstract summary: We combine a focused review of cardiac ultrasound segmentation literature with a comparison of three influential architectures.<n>Our benchmark spans multiple preprocessing routes, including native NIfTI volumes, 16-bit PNG exports, GPT-assisted polygon-based pseudo-labels, and self-supervised pretraining.
• Score: 39.950953035207384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Several review papers summarize cardiac imaging and DL advances, few works connect this overview to a unified and reproducible experimental benchmark. In this study, we combine a focused review of cardiac ultrasound segmentation literature with a controlled comparison of three influential architectures, U-Net, Attention U-Net, and TransUNet, on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) echocardiography dataset. Our benchmark spans multiple preprocessing routes, including native NIfTI volumes, 16-bit PNG exports, GPT-assisted polygon-based pseudo-labels, and self-supervised pretraining (SSL) on thousands of unlabeled cine frames. Using identical training splits, losses, and evaluation criteria, a plain U-Net achieved a 94% mean Dice when trained directly on NIfTI data (preserving native dynamic range), while the PNG-16-bit workflow reached 91% under similar conditions. Attention U-Net provided modest improvements on small or low-contrast regions, reducing boundary leakage, whereas TransUNet demonstrated the strongest generalization on challenging frames due to its ability to model global spatial context, particularly when initialized with SSL. Pseudo-labeling expanded the training set and improved robustness after confidence filtering. Overall, our contributions are threefold: a harmonized, apples-to-apples benchmark of U-Net, Attention U-Net, and TransUNet under standardized CAMUS preprocessing and evaluation; practical guidance on maintaining intensity fidelity, resolution consistency, and alignment when preparing ultrasound data; and an outlook on scalable self-supervision and emerging multimodal GPT-based annotation pipelines for rapid labeling, quality assurance, and targeted dataset curation.

Related papers

• SonoCLIP: Mask-Guided Region-Aware Vision-Language Pretraining for Fetal Ultrasound Analysis [51.81845420301345]
  SonoCLIP is a vision-language foundation model for fetal ultrasound analysis.<n>It integrates segmentation masks as mask-channel visual prompts within the vision encoder.<n>It achieves superior zero-shot transfer performance under both global and mask-guided inference.
  arXiv  Detail & Related papers  (2026-06-28T20:04:49Z)
• Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision [3.3240679960197514]
  It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clinical sites.<n>We propose a target-informed self-supervised pretraining and model-ensemble strategy.<n>Our method used labeled source data for supervised training and leveraged target-domain pretraining to improve generalization.
  arXiv  Detail & Related papers  (2026-05-27T21:29:31Z)
• Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images [4.42778347374376]
  Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variability.<n>We propose a label-efficient segmentation framework that leverages the robust semantic priors of a pretrained DINOv3 foundational vision transformer backbone.<n>Our method achieves state-of-the-art performance compared to established fully supervised baselines, including U-Net, U-Net++, DeepLabV3, and MAnet.
  arXiv  Detail & Related papers  (2026-04-09T09:48:50Z)
• Left Atrial Segmentation with nnU-Net Using MRI [0.0]
  Deep learning methods have recently demonstrated superior performance in medical image segmentation tasks.<n>In this study, we applied the nnU-Net framework, an automated, self-configuring deep learning segmentation architecture, to the Left Atrial Challenge 2013 dataset.<n>The network exhibited robust generalization across variations in left atrial shape, pulmonary contrast, and image quality, accurately delineating both the atrial body and proximal veins.
  arXiv  Detail & Related papers  (2025-11-06T05:23:45Z)
• TopSeg: A Multi-Scale Topological Framework for Data-Efficient Heart Sound Segmentation [12.42019711058722]
  TopSeg is a representation-centric framework that encodes PCG dynamics with multi-scale topological features.<n>We train exclusively on PhysioNet 2016 dataset with subject-level subsampling and perform external validation on CirCor dataset.<n>Results indicate that TopSeg provides a strong inductive bias for data-efficient, cross-dataset PCG segmentation.
  arXiv  Detail & Related papers  (2025-10-20T09:43:39Z)
• UESA-Net: U-Shaped Embedded Multidirectional Shrinkage Attention Network for Ultrasound Nodule Segmentation [12.967178888045728]
  Existing networks struggle to reconcile high-level semantics with low-level spatial details.<n>We propose UESA-Net, a U-shaped network with multidirectional shrinkage attention.<n>On two public datasets, UESA-Net achieved state-of-the-art performance with intersection-over-union (IoU) scores of 0.8487 and 0.6495, respectively.
  arXiv  Detail & Related papers  (2025-09-26T14:54:38Z)
• Leveraging CORAL-Correlation Consistency Network for Semi-Supervised Left Atrium MRI Segmentation [14.296441810235223]
  Semi-supervised learning (SSL) has been widely used to learn from both a few labeled images and many unlabeled images. Most current SSL-based segmentation methods use pixel values directly to identify similar features in labeled and unlabeled data. We introduce CORAL(Correlation-Aligned)-Correlation Consistency Network (CORN) to capture the global structure shape and local details of Left Atrium.
  arXiv  Detail & Related papers  (2024-10-21T11:46:28Z)
• CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation [73.89509052503222]
  This paper presents a simple but performant semi-supervised semantic segmentation approach, called CorrMatch. We observe that the correlation maps not only enable clustering pixels of the same category easily but also contain good shape information. We propose to conduct pixel propagation by modeling the pairwise similarities of pixels to spread the high-confidence pixels and dig out more. Then, we perform region propagation to enhance the pseudo labels with accurate class-agnostic masks extracted from the correlation maps.
  arXiv  Detail & Related papers  (2023-06-07T10:02:29Z)
• Extraction of volumetric indices from echocardiography: which deep learning solution for clinical use? [6.144041824426555]
  We show that the proposed 3D nnU-Net outperforms alternative 2D and recurrent segmentation methods. Overall, the experimental results suggest that with sufficient training data, 3D nnU-Net could become the first automated tool to meet the standards of an everyday clinical device.
  arXiv  Detail & Related papers  (2023-05-03T09:38:52Z)
• Generalizing electrocardiogram delineation: training convolutional neural networks with synthetic data augmentation [63.51064808536065]
  Existing databases for ECG delineation are small, being insufficient in size and in the array of pathological conditions they represent. This article delves has two main contributions. First, a pseudo-synthetic data generation algorithm was developed, based in probabilistically composing ECG traces given "pools" of fundamental segments, as cropped from the original databases, and a set of rules for their arrangement into coherent synthetic traces. Second, two novel segmentation-based loss functions have been developed, which attempt at enforcing the prediction of an exact number of independent structures and at producing closer segmentation boundaries by focusing on a reduced number of samples.
  arXiv  Detail & Related papers  (2021-11-25T10:11:41Z)
• Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation [85.0078917060652]
  We propose a semi-weakly supervised segmentation algorithm to overcome this barrier. Our approach is based on a new formulation of deep supervision and student-teacher model. With our novel training regime for segmentation that flexibly makes use of images that are either fully labeled, marked with bounding boxes, just global labels, or not at all, we are able to cut the requirement for expensive labels by 94.22%.
  arXiv  Detail & Related papers  (2021-04-27T14:51:19Z)
• 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [76.42897462051067]
  3DIoUMatch is a novel semi-supervised method for 3D object detection applicable to both indoor and outdoor scenes. We leverage a teacher-student mutual learning framework to propagate information from the labeled to the unlabeled train set in the form of pseudo-labels. Our method consistently improves state-of-the-art methods on both ScanNet and SUN-RGBD benchmarks by significant margins under all label ratios.
  arXiv  Detail & Related papers  (2020-12-08T11:06:26Z)
• Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound [74.22397862400177]
  We propose a novel Frustum ultrasound based catheter segmentation method. The proposed method achieved the state-of-the-art performance with an efficiency of 0.25 second per volume.
  arXiv  Detail & Related papers  (2020-10-19T13:56:22Z)
• ECG-DelNet: Delineation of Ambulatory Electrocardiograms with Mixed Quality Labeling Using Neural Networks [69.25956542388653]
  Deep learning (DL) algorithms are gaining weight in academic and industrial settings. We demonstrate DL can be successfully applied to low interpretative tasks by embedding ECG detection and delineation onto a segmentation framework. The model was trained using PhysioNet's QT database, comprised of 105 ambulatory ECG recordings.
  arXiv  Detail & Related papers  (2020-05-11T16:29:12Z)

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.