mlsanityData to 14 Oct 2026

GPAFormer: Graph-guided Patch Aggregation Transformer for Efficient 3D Medical Image Segmentation

arXiv 2604.06658 ↗First posted 8 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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. GPAFormer incorporated two core modules: the multi-scale attention-guided stacked aggregation (MASA) and the mutual-aware patch graph aggregator (MPGA). MASA utilized three parallel paths with different receptive fields, combined through planar aggregation, to enhance the network's capability in handling structures of varying sizes. MPGA employed a graph-guided approach to dynamically aggregate regions with similar feature distributions based on inter-patch feature similarity and spatial adjacency, thereby improving the discrimination of both internal and boundary structures of organs. Experiments were performed on public whole-body CT and MRI datasets including BTCV, Synapse, ACDC, and BraTS. Compared to the existed 3D segmentation networkd, GPAFormer using only 1.81 M parameters achieved overall highest DSC on BTCV (75.70%), Synapse (81.20%), ACDC (89.32%), and BraTS (82.74%). Using consumer level GPU, the inference time for one validation case of BTCV spent less than one second. The results demonstrated that GPAFormer balanced accuracy and efficiency in multi-organ, multi-modality 3D segmentation tasks across various clinical scenarios especially for resource-constrained and time-sensitive clinical environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

20 of 43 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  9. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  10. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  11. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  12. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
8 more
  1. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  2. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  3. 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 422
  4. 2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
  5. 2021nnFormer: Interleaved Transformer for Volumetric Segmentationcited by 180
  6. 2022UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentationcited by 112
  7. 2018Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challengecited by 56
  8. 2024SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentationcited by 31

Built on by

Not cited yet.