mlsanityData to 7 Oct 2026

How good nnU-Net for Segmenting Cardiac MRI: A Comprehensive Evaluation

arXiv 2408.06358 ↗First posted 26 Jul 2024eess.IV cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Cardiac segmentation is a critical task in medical imaging, essential for detailed analysis of heart structures, which is crucial for diagnosing and treating various cardiovascular diseases. With the advent of deep learning, automated segmentation techniques have demonstrated remarkable progress, achieving high accuracy and efficiency compared to traditional manual methods. Among these techniques, the nnU-Net framework stands out as a robust and versatile tool for medical image segmentation. In this study, we evaluate the performance of nnU-Net in segmenting cardiac magnetic resonance images (MRIs). Utilizing five cardiac segmentation datasets, we employ various nnU-Net configurations, including 2D, 3D full resolution, 3D low resolution, 3D cascade, and ensemble models. Our study benchmarks the capabilities of these configurations and examines the necessity of developing new models for specific cardiac segmentation tasks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 100 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

27 of 100 references.

References · 27

  1. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  2. 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentationcited by 235
  3. 2020Cardiac Segmentation with Strong Anatomical Guaranteescited by 43
  4. 2017An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentationcited by 36
  5. 2020Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRIcited by 28
  6. 2018Multi-Task Learning for Left Atrial Segmentation on GE-MRIcited by 16
  7. 2020Disentangled Representations for Domain-generalized Cardiac Segmentationcited by 14
  8. 2017Automatic Segmentation and Disease Classification Using Cardiac Cine MR Imagescited by 13
  9. 2020Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Informationcited by 12
  10. 2020Histogram Matching Augmentation for Domain Adaptation with Application to Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Image Segmentationcited by 12
  11. 2020Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfercited by 10
  12. 2021Right Ventricular Segmentation from Short- and Long-Axis MRIs via Information Transitioncited by 9
15 more
  1. 2018Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentationcited by 7
  2. 2018Dilated Convolutions in Neural Networks for Left Atrial Segmentation in 3D Gadolinium Enhanced-MRIcited by 6
  3. 2020Domain-Adversarial Learning for Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac MR Image Segmentationcited by 6
  4. 2021Learning With Context Feedback Loop for Robust Medical Image Segmentationcited by 6
  5. 2017GridNet with automatic shape prior registration for automatic MRI cardiac segmentationcited by 5
  6. 2021JAS-GAN: Generative Adversarial Network Based Joint Atrium and Scar Segmentations on Unbalanced Atrial Targetscited by 5
  7. 2022Tempera: Spatial Transformer Feature Pyramid Network for Cardiac MRI Segmentationcited by 5
  8. 2020Style-invariant Cardiac Image Segmentation with Test-time Augmentationcited by 4
  9. 2021Multi-view SA-LA Net: A framework for simultaneous segmentation of RV on multi-view cardiac MR Imagescited by 4
  10. 2018Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentationcited by 3
  11. 2020Generalisable Cardiac Structure Segmentation via Attentional and Stacked Image Adaptationcited by 3
  12. 2020Left atrial ejection fraction estimation using SEGANet for fully automated segmentation of CINE MRIcited by 3
  13. 2022UGformer for Robust Left Atrium and Scar Segmentation Across Scannerscited by 3
  14. 2023Automatically Segment the Left Atrium and Scars from LGE-MRIs Using a Boundary-focused nnU-Netcited by 2
  15. 2024Dynamic Position Transformation and Boundary Refinement Network for Left Atrial Segmentationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Segmenting Bi-Atrial Structures Using ResNext Based Frameworkcited by 0
  2. 2026Multicentre Bi-atrial Segmentation from LGE-MRI for Atrial Fibrillation with a 2D and 3D Frameworkcited by 0