mlsanityData to 14 Oct 2026

DeepMesh: Mesh-based Cardiac Motion Tracking using Deep Learning

arXiv 2309.14306 ↗First posted 25 Sep 2023eess.IV cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

3D motion estimation from cine cardiac magnetic resonance (CMR) images is important for the assessment of cardiac function and the diagnosis of cardiovascular diseases. Current state-of-the art methods focus on estimating dense pixel-/voxel-wise motion fields in image space, which ignores the fact that motion estimation is only relevant and useful within the anatomical objects of interest, e.g., the heart. In this work, we model the heart as a 3D mesh consisting of epi- and endocardial surfaces. We propose a novel learning framework, DeepMesh, which propagates a template heart mesh to a subject space and estimates the 3D motion of the heart mesh from CMR images for individual subjects. In DeepMesh, the heart mesh of the end-diastolic frame of an individual subject is first reconstructed from the template mesh. Mesh-based 3D motion fields with respect to the end-diastolic frame are then estimated from 2D short- and long-axis CMR images. By developing a differentiable mesh-to-image rasterizer, DeepMesh is able to leverage 2D shape information from multiple anatomical views for 3D mesh reconstruction and mesh motion estimation. The proposed method estimates vertex-wise displacement and thus maintains vertex correspondences between time frames, which is important for the quantitative assessment of cardiac function across different subjects and populations. We evaluate DeepMesh on CMR images acquired from the UK Biobank. We focus on 3D motion estimation of the left ventricle in this work. Experimental results show that the proposed method quantitatively and qualitatively outperforms other image-based and mesh-based cardiac motion tracking methods.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 23 of its 56 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

23 of 56 references.

References · 23

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  3. 2015Spatial Transformer Networkscited by 1,429
  4. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  6. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  7. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  8. 2020Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flowscited by 61
  9. 2018Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequencescited by 47
  10. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  11. 2018Deep learning cardiac motion analysis for human survival predictioncited by 31
  12. 2019DARNet: Deep Active Ray Network for Building Segmentationcited by 30
11 more
  1. 2021DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Imagescited by 26
  2. 2018Locating Objects Without Bounding Boxescited by 25
  3. 2020Adversarial Uni- and Multi-modal Stream Networks for Multimodal Image Registrationcited by 25
  4. 2020Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRIcited by 24
  5. 2020FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimationcited by 21
  6. 2018Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flowcited by 16
  7. 2022MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRIcited by 16
  8. 2019End to End Trainable Active Contours via Differentiable Renderingcited by 15
  9. 2020Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimationcited by 15
  10. 2022Mesh-based 3D Motion Tracking in Cardiac MRI using Deep Learningcited by 9
  11. 2020Enhanced 3D Myocardial Strain Estimation from Multi-View 2D CMR Imagingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 8; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRIcited by 12
  2. 2025CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matchingcited by 9
  3. 2024Explicit Differentiable Slicing and Global Deformation for Cardiac Mesh Reconstructioncited by 8
  4. 2025End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRIcited by 6
  5. 2025From Pixels to Polygons: A Survey of Deep Learning Approaches for Medical Image-to-Mesh Reconstructioncited by 4
  6. 2026CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRIcited by 3
  7. 2024MorphiNet: A Graph Subdivision Network for Adaptive Bi-ventricle Surface Reconstructioncited by 1
  8. 2025Parametric shape models for vessels learned from segmentations via differentiable voxelizationcited by 1
  9. 2025Dyna3DGR: 4D Cardiac Motion Tracking with Dynamic 3D Gaussian Representationcited by 1
  10. 2025CardioMorphNet: Cardiac Motion Prediction Using a Shape-Guided Bayesian Recurrent Deep Networkcited by 1
  11. 2026VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSetscited by 1
  12. 2026NISF++: Geometrically-grounded implicit representations of 3D+time cardiac function from 2D short- and long-axis MR viewscited by 1
2 more
  1. 2025MCM: Mamba-based Cardiac Motion Tracking using Sequential Images in MRIcited by 0
  2. 2025Non-Intrusive Parametrized-Background Data-Weak Reconstruction of Cardiac Displacement Fields from Sparse MRI-like Observationscited by 0