Bi-PT: Bidirectional Cross-Attention Point Transformers for Four-Chamber Heart Reconstruction from Sparse Cardiac MRI Data

• URL: http://arxiv.org/abs/2607.06923v1
• Date: Wed, 08 Jul 2026 02:37:55 GMT
• Title: Bi-PT: Bidirectional Cross-Attention Point Transformers for Four-Chamber Heart Reconstruction from Sparse Cardiac MRI Data
• Abstract summary: Bi-PT enables accurate inference of the four-chamber heart mesh from the sparse point cloud.<n>We formulate the deformation field as a Neural Ordinary Differential Equation (NODE) parameterized by a per-point affine transformation.<n>Bi-PT achieves accurate and robust performance compared to baselines.
• Score: 4.642439193156724
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose Bi-PT, a pipeline for reconstructing 3D four-chamber human heart meshes from clinical sparsely sampled cardiac magnetic resonance imaging (CMR) data. This work addresses the error-prone generation of 3D cardiac shape from a sparse point cloud (SPC) extracted from 2D long-axis and short-axis views used in routine clinical CMR protocols. Bi-PT enables accurate inference of the four-chamber heart mesh from the SPC by learning robust point features via bidirectional point cross-attention between an atlas and the SPC, together with per-point semantic labels that improve correspondence estimation. We formulate the deformation field as a Neural Ordinary Differential Equation (NODE) parameterized by a per-point affine transformation and translation to deform the atlas toward the target heart shape. By learning such a NODE, we can guarantee the deformation field to be a locally affine diffeomorphic deformation. We also integrate a semantic label loss into the Chamfer distance to encourage label-consistent correspondences and add a smoothness regularization to stabilize and improve the learning of the deformation field. Extensive experiments demonstrate that Bi-PT achieves accurate and robust performance compared to baselines.

Related papers

• Automatic LV Localization and Short-Axis Plane Estimation from Arbitrary CMR Slice [12.859805507388728]
  Accurate estimation of left ventricular (LV) orientation is essential for cardiac magnetic resonance (CMR) imaging and downstream analysis.<n>Existing methods typically formulate orientation recognition as discrete view classification or rely on multi-slice geometric intersection.<n>This work introduces a novel paradigm: Joint LV localization and 3D orientation estimation from a single CMR slice.
  arXiv  Detail & Related papers  (2026-07-31T16:11:01Z)
• HeartVolMesh: Cardiac Volumetric Mesh Reconstruction via Covariance-Guided Graph Deformation [40.08276134769528]
  HeartVolMesh lifts each template to an anisotropic Gaussian kernel and uses a 3D CNN-GNN to predict per-vertex displacements.<n>For volumetric meshing, we warp a fixed tetrahedral template to the reconstructed surface via staged alignment, non-rigid registration, and deformation propagation.<n>Experiments show consistent gains over deformation-based baselines in surface mesh accuracy and volumetric mesh fidelity.
  arXiv  Detail & Related papers  (2026-07-05T11:42:37Z)
• Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints [51.7011449975586]
  Land-Reg is a deformable registration framework that learns latent-grounded 2D-3D landmark correspondences.<n>For rigid registration, Land-Reg embraces a Cross-modal Latent Alignment module.<n>An Uncertainty-enhanced Overlap Landmark Detector with similarity matching is proposed to robustly estimate explicit 2D-3D landmark correspondences.
  arXiv  Detail & Related papers  (2026-03-02T10:44:03Z)
• Fighting MRI Anisotropy: Learning Multiple Cardiac Shapes From a Single Implicit Neural Representation [0.6558127228160233]
  We propose to leverage near-isotropic, higher resolution computed tomography angiography (CTA) data of the heart.<n>We use this data to train a single neural implicit function to jointly represent cardiac shapes from CMRI at any resolution.<n>We evaluate the method for the reconstruction of right ventricle (RV) and myocardium (MYO), where MYO simultaneously models endocardial and epicardial left-ventricle surfaces.
  arXiv  Detail & Related papers  (2026-02-11T23:20:14Z)
• Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform [62.27337227010514]
  We introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with Local Shape Transform, dubbed RIST. RIST learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. RIST demonstrates state-of-the-art performances on 3D part label transfer and semantic keypoint transfer given arbitrarily rotated point cloud pairs.
  arXiv  Detail & Related papers  (2024-04-17T08:09:25Z)
• Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging [8.12099697240624]
  We propose a novel neural deformable model (NDM) targeting at the reconstruction and modeling of 3D bi-ventricular shape of the heart. We model the bi-ventricular shape using blended deformable superquadrics, which are parameterized by a set of geometric parameter functions. Our NDM can learn to densify a sparse cardiac point cloud with arbitrary scales and generate high-quality triangular meshes automatically.
  arXiv  Detail & Related papers  (2023-07-15T03:11:16Z)
• Error correcting 2D-3D cascaded network for myocardial infarct scar segmentation on late gadolinium enhancement cardiac magnetic resonance images [1.099532646524593]
  We propose a cascaded framework of convolutional neural networks (CNNs) which enables to calculate the extent of myocardial infarction in a fully automated way.<n>We show that our framework outperforms state-of-the-art reference methods in segmentation of myocardial infarction.
  arXiv  Detail & Related papers  (2023-06-26T14:21:18Z)
• CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame [60.24797081117877]
  We propose the CRIN, namely Centrifugal Rotation-Invariant Network. CRIN directly takes the coordinates of points as input and transforms local points into rotation-invariant representations. A continuous distribution for 3D rotations based on points is introduced.
  arXiv  Detail & Related papers  (2023-03-06T13:14:10Z)
• Three-dimensional micro-structurally informed in silico myocardium -- towards virtual imaging trials in cardiac diffusion weighted MRI [58.484353709077034]
  We propose a novel method to generate a realistic numerical phantom of myocardial microstructure. In-silico tissue models enable evaluating quantitative models of magnetic resonance imaging.
  arXiv  Detail & Related papers  (2022-08-22T22:01:44Z)
• Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling [67.75095378830694]
  We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations. In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases. Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
  arXiv  Detail & Related papers  (2022-02-27T12:52:27Z)
• SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching [47.79483848496141]
  We propose a 3D sphere representation-based center-points matching detection network (SCPM-Net) It is anchor-free and automatically predicts the position, radius, and offset of nodules without the manual design of nodule/anchor parameters. We show that our proposed SCPM-Net framework achieves superior performance compared with existing used anchor-based and anchor-free methods for lung nodule detection.
  arXiv  Detail & Related papers  (2021-04-12T05:51:29Z)
• Enhanced 3D Myocardial Strain Estimation from Multi-View 2D CMR Imaging [0.0]
  We propose an enhanced 3D myocardial strain estimation procedure, which combines complementary displacement information from multiple orientations of a single imaging modality (untagged CMR SSFP images) We register the sets of short-axis, four-chamber and two-chamber views via a 2D non-rigid registration algorithm implemented in a commercial software (Segment, Medviso) We then create a series of interpolating functions for the three directions of motion and use them to deform a tetrahedral mesh representation of a patient-specific left ventricle.
  arXiv  Detail & Related papers  (2020-09-25T22:47:50Z)

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.