Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation
This addresses the need for efficient and accurate segmentation of diverse 3D medical scans for clinical diagnostics and treatment planning, representing a strong specific gain rather than an incremental improvement.
The paper tackles the problem of achieving both high accuracy and computational efficiency in 3D medical image segmentation by proposing GCNV-Net, which integrates a Tri-directional Dynamic Nonvoid Voxel Transformer, a Geometrical Cross-Attention module, and Nonvoid Voxelization. The method achieves state-of-the-art performance across multiple benchmarks (e.g., 0.65% improvement in Dice) while reducing FLOPs by 56.13% and inference latency by 68.49% compared to conventional approaches.
Accurate segmentation of 3D medical scans is crucial for clinical diagnostics and treatment planning, yet existing methods often fail to achieve both high accuracy and computational efficiency across diverse anatomies and imaging modalities. To address these challenges, we propose GCNV-Net, a novel 3D medical segmentation framework that integrates a Tri-directional Dynamic Nonvoid Voxel Transformer (3DNVT), a Geometrical Cross-Attention module (GCA), and Nonvoid Voxelization. The 3DNVT dynamically partitions relevant voxels along the three orthogonal anatomical planes, namely the transverse, sagittal, and coronal planes, enabling effective modeling of complex 3D spatial dependencies. The GCA mechanism explicitly incorporates geometric positional information during multi-scale feature fusion, significantly enhancing fine-grained anatomical segmentation accuracy. Meanwhile, Nonvoid Voxelization processes only informative regions, greatly reducing redundant computation without compromising segmentation quality, and achieves a 56.13% reduction in FLOPs and a 68.49% reduction in inference latency compared to conventional voxelization. We evaluate GCNV-Net on multiple widely used benchmarks: BraTS2021, ACDC, MSD Prostate, MSD Pancreas, and AMOS2022. Our method achieves state-of-the-art segmentation performance across all datasets, outperforming the best existing methods by 0.65% on Dice, 0.63% on IoU, 1% on NSD, and relatively 14.5% on HD95. All results demonstrate that GCNV-Net effectively balances accuracy and efficiency, and its robustness across diverse organs, disease conditions, and imaging modalities highlights strong potential for clinical deployment.