AI RESEARCH
GPAFormer: Graph-guided Patch Aggregation Transformer for Efficient 3D Medical Image Segmentation
arXiv CS.CV
•
ArXi:2604.06658v1 Announce Type: new Deep learning has been widely applied to 3D medical image segmentation tasks. However, due to the diversity of imaging modalities, the high-dimensional nature of the data, and the heterogeneity of anatomical structures, achieving both segmentation accuracy and computational efficiency in multi-organ segmentation remains a challenge. This study proposed GPAFormer, a lightweight network architecture specifically designed for 3D medical image segmentation, emphasizing efficiency while keeping high accuracy.