mlsanityData to 14 Oct 2026

JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targets

arXiv 2105.00234 ↗First posted 1 May 2021eess.IV cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Automated and accurate segmentations of left atrium (LA) and atrial scars from late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) images are in high demand for quantifying atrial scars. The previous quantification of atrial scars relies on a two-phase segmentation for LA and atrial scars due to their large volume difference (unbalanced atrial targets). In this paper, we propose an inter-cascade generative adversarial network, namely JAS-GAN, to segment the unbalanced atrial targets from LGE CMR images automatically and accurately in an end-to-end way. Firstly, JAS-GAN investigates an adaptive attention cascade to automatically correlate the segmentation tasks of the unbalanced atrial targets. The adaptive attention cascade mainly models the inclusion relationship of the two unbalanced atrial targets, where the estimated LA acts as the attention map to adaptively focus on the small atrial scars roughly. Then, an adversarial regularization is applied to the segmentation tasks of the unbalanced atrial targets for making a consistent optimization. It mainly forces the estimated joint distribution of LA and atrial scars to match the real ones. We evaluated the performance of our JAS-GAN on a 3D LGE CMR dataset with 192 scans. Compared with the state-of-the-art methods, our proposed approach yielded better segmentation performance (Average Dice Similarity Coefficient (DSC) values of 0.946 and 0.821 for LA and atrial scars, respectively), which indicated the effectiveness of our proposed approach for segmenting unbalanced atrial targets.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 1 May 2021.

Builds on

25 of 51 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2016Improved Techniques for Training GANscited by 2,970
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  6. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  7. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  9. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  10. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  11. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  12. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 379
13 more
  1. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  2. 2018Boundary loss for highly unbalanced segmentationcited by 190
  3. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  4. 2015Instance-aware Semantic Segmentation via Multi-task Network Cascadescited by 121
  5. 2019Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challengecited by 100
  6. 2017Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascadecited by 53
  7. 2018Multi-Task Learning for Left Atrial Segmentation on GE-MRIcited by 16
  8. 2020Simultaneous Left Atrium Anatomy and Scar Segmentations via Deep Learning in Multiview Information with Attentioncited by 16
  9. 20173D Densely Convolutional Networks for Volumetric Segmentationcited by 9
  10. 2017Transfer learning for multi-center classification of chronic obstructive pulmonary diseasecited by 8
  11. 2017CardiacNET: Segmentation of Left Atrium and Proximal Pulmonary Veins from MRI Using Multi-View CNNcited by 7
  12. 2017Fully Automatic Segmentation and Objective Assessment of Atrial Scars for Longstanding Persistent Atrial Fibrillation Patients Using Late Gadolinium-Enhanced MRIcited by 5
  13. 2019Discriminative Consistent Domain Generation for Semi-supervised Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 0; 2023: 0; 2024: 2.

5 papers.

  1. 2021Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectivescited by 7
  2. 2024Semi-Supervised Disease Classification based on Limited Medical Image Datacited by 7
  3. 2021Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Datacited by 6
  4. 2021Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectivescited by 3
  5. 2024How good nnU-Net for Segmenting Cardiac MRI: A Comprehensive Evaluationcited by 2