Search papers, labs, and topics across Lattice.
This paper introduces Bi-PT, a novel pipeline that reconstructs 3D four-chamber heart meshes from sparse cardiac MRI data by leveraging bidirectional point cross-attention between an atlas and the sparse point cloud (SPC). The method addresses the challenges of generating accurate cardiac shapes from limited data by incorporating per-point semantic labels and a Neural Ordinary Differential Equation (NODE) for deformation, ensuring locally affine diffeomorphic transformations. Extensive experiments show that Bi-PT significantly outperforms existing baselines in terms of accuracy and robustness in heart mesh reconstruction.
Achieving precise 3D heart reconstructions from sparse MRI data, Bi-PT redefines the potential for cardiac imaging in clinical settings.
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.
