C.-L.J. Hu

Chenchuhui Hu, Shaoming Pan, Leon Axel et al.

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.

Shaoming Pan, Chenchuhui Hu, Leon Axel et al.

Clinical cardiac MRI is commonly acquired with high in-plane resolution but coarse through-plane resolution to reduce scan time and accommodate breath-hold and cardiac-motion constraints, which limits 3D analysis and diagnostic accuracy. We propose STRMSR, a reference- and memory-guided through-plane super-resolution (SR) framework that reconstructs high-resolution (HR) cardiac volumes by leveraging HR reference views acquired from the same subject and intermediate SR results as the memory. Our method uses coarse-to-fine contextual matching to establish robust correspondence between low-resolution target and reference/memory images under spatial misalignment. A learnable patch-wise dynamic feature aggregation module predicts content-adaptive mixture weights for each local patch, effectively fusing dynamic information while suppressing unreliable feature transfers. The intermediate SR results stored in the memory bank ensure slice-to-slice consistency for the super-resolved 3D volume. Experiments on the WHS cardiac MRI dataset under two reference protocols, orthogonal-plane views and long-axis chamber views, demonstrate consistent improvements over baselines at 4x and 8x upsampling factors.

Chenchuhui Hu

Combinatorial optimization (CO) problems are challenging as the computation time grows exponentially with the input. Graph Neural Networks (GNNs) show promise for researchers in solving CO problems. This study investigates the effectiveness of GNNs in solving the maximum independent set (MIS) problem, inspired by the intriguing findings of Schuetz et al., and aimed to enhance this solver. Despite the promise shown by GNNs, some researchers observed discrepancies when reproducing the findings, particularly compared to the greedy algorithm, for instance. We reproduced Schuetz' Quadratic Unconstrained Binary Optimization (QUBO) unsupervised approach and explored the possibility of combining it with a supervised learning approach for solving MIS problems. While the QUBO unsupervised approach did not guarantee maximal or optimal solutions, it provided a solid first guess for post-processing techniques like greedy decoding or tree-based methods. Moreover, our findings indicated that the supervised approach could further refine the QUBO unsupervised solver, as the learned model assigned meaningful probabilities for each node as initial node features, which could then be improved with the QUBO unsupervised approach. Thus, GNNs offer a valuable method for solving CO problems by integrating learned graph structures rather than relying solely on traditional heuristic functions. This research highlights the potential of GNNs to boost solver performance by leveraging ground truth during training and using optimization functions to learn structural graph information, marking a pioneering step towards improving prediction accuracy in a non-autoregressive manner.