Papers › 3D Medical Point Transformer: Introducing Convolution to Attention Networks for...

3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis

9 Dec 2021arXiv:2112.04863archive 2025-07-28

Jianhui Yu, Chaoyi Zhang, Heng Wang, Dingxin Zhang, Yang song, Tiange Xiang, Dongnan Liu, Weidong Cai

General point clouds have been increasingly investigated for different tasks, and recently Transformer-based networks are proposed for point cloud analysis. However, there are barely related works for medical point clouds, which are important for disease detection and treatment. In this work, we propose an attention-based model specifically for medical point clouds, namely 3D medical point Transformer (3DMedPT), to examine the complex biological structures. By augmenting contextual information and summarizing local responses at query, our attention module can capture both local context and global content feature interactions. However, the insufficient training samples of medical data may lead to poor feature learning, so we apply position embeddings to learn accurate local geometry and Multi-Graph Reasoning (MGR) to examine global knowledge propagation over channel graphs to enrich feature representations. Experiments conducted on IntrA dataset proves the superiority of 3DMedPT, where we achieve the best classification and segmentation results. Furthermore, the promising generalization ability of our method is validated on general 3D point cloud benchmarks: ModelNet40 and ShapeNetPart. Code is released.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

crane-papercode/3dmedpt officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Part Segmentation3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation IntrA 3DMedPT DSC (A) 89.71 #1 of 7 Archive leaderboard report
3D Part Segmentation IntrA 3DMedPT DSC (V) 97.29 #1 of 7 Archive leaderboard report
3D Part Segmentation IntrA 3DMedPT IoU (A) 82.39 #1 of 7 Archive leaderboard report
3D Part Segmentation IntrA 3DMedPT IoU (V) 94.82 #1 of 7 Archive leaderboard report
3D Point Cloud Classification IntrA 3DMedPT F1 score (5-fold) 0.936 #1 of 12 Archive leaderboard report
3D Point Cloud Classification ModelNet40 3DMedPT Number of params 1.54M #63 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 3DMedPT Overall Accuracy 93.4 #63 of 111 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections