EUVIMEDOpdag EUVIMED
Video/Audio

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Lei Ma, Dian Zhang, Zhaoxin Wang, Jincong Han, Xing Wang, Xin Zhou, Wenwen Yang, Peihua Lu

Journal of Visualized Experiments · 2024

DOI: 10.3791/66459 ↗

At a glance

Video/Audio in Journal of Visualized Experiments, 2024. Written by Lei Ma and 7 co-authors. Institution: School of Information Science and Technology, Nantong University. Major MEDLINE topics: Tomography, X-Ray Computed. 29 references.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Abdominal multi-organ segmentation is one of the most important topics in the field of medical image analysis, and it plays an important role in supporting clinical workflows such as disease diagnosis and treatment planning. In this study, an efficient multi-organ segmentation method called Swin-PSAxialNet based on the nnU-Net architecture is proposed. It was designed specifically for the precise segmentation of 11 abdominal organs in CT images. The proposed network has made the following improvements compared to nnU-Net. Firstly, Space-to-depth (SPD) modules and parameter-shared axial attention (PSAA) feature extraction blocks were introduced, enhancing the capability of 3D image feature extraction. Secondly, a multi-scale image fusion approach was employed to capture detailed information and spatial features, improving the capability of extracting subtle features and edge features. Lastly, a parameter-sharing method was introduced to reduce the model's computational cost and training speed. The proposed network achieves an average Dice coefficient of 0.93342 for the segmentation task involving 11 organs. Experimental results indicate the notable superiority of Swin-PSAxialNet over previous mainstream segmentation methods. The method shows excellent accuracy and low computational costs in segmenting major abdominal organs.

Subjects

MeSH terms (MEDLINE)

Tomography, X-Ray ComputedHumansImaging, Three-DimensionalImage Processing, Computer-AssistedNeural Networks, ComputerAbdomenRadiography, Abdominal

Authors and institutions

  • School of Information Science and Technology, Nantong University.
  • The Oncology and Hematology Department of Wuxi People's Hospital of Nanjing Medical University, Wuxi Medical Center, Nanjing Medical University.
  • The Oncology and Hematology Department of Wuxi People's Hospital of Nanjing Medical University, Wuxi Medical Center, Nanjing Medical University; lphty1_1@163.com.

Cite

APA

Ma, L., Zhang, D., Wang, Z., Han, J., Wang, X., Zhou, X., Yang, W., & Lu, P. (2024). Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique. Journal of Visualized Experiments. https://doi.org/10.3791/66459

Vancouver

Ma L, Zhang D, Wang Z, Han J, Wang X, Zhou X, et al. Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique. Journal of Visualized Experiments. 2024. doi:10.3791/66459

BibTeX
@article{Ma2024,
  author = {Ma, Lei and Zhang, Dian and Wang, Zhaoxin and Han, Jincong and Wang, Xing and Zhou, Xin and Yang, Wenwen and Lu, Peihua},
  title = {Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique},
  journal = {Journal of Visualized Experiments},
  year = {2024},
  doi = {10.3791/66459}
}
Start for free →