EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High-Resolution Swin Transformer for Automatic Medical Image Segmentation

Chen Wei iD, Shenghan Ren iD, Kaitai Guo, Haihong Hu, Jimin Liang iD

Sensors · 24.03.2023 · 23 (7) · 3420

DOI: 10.3390/s23073420 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.03.2023. Verfasst von Chen Wei und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Economics and Management, Xi'an University of Posts & Telecommunications, Xi'an 710061, China. Hauptthemen laut MEDLINE: Brain Neoplasms. Die Arbeit wurde bisher 93-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, The Key Research and Development Program in the Shaanxi Province of China, Key Research and Development Program in the Shaanxi Province of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The resolution of feature maps is a critical factor for accurate medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation adopt a U-Net-like architecture, which contains an encoder that converts the high-resolution input image into low-resolution feature maps using a sequence of Transformer blocks and a decoder that gradually generates high-resolution representations from low-resolution feature maps. However, the procedure of recovering high-resolution representations from low-resolution representations may harm the spatial precision of the generated segmentation masks. Unlike previous studies, in this study, we utilized the high-resolution network (HRNet) design style by replacing the convolutional layers with Transformer blocks, continuously exchanging feature map information with different resolutions generated by the Transformer blocks. The proposed Transformer-based network is named the high-resolution Swin Transformer network (HRSTNet). Extensive experiments demonstrated that the HRSTNet can achieve performance comparable with that of the state-of-the-art Transformer-based U-Net-like architecture on the 2021 Brain Tumor Segmentation dataset, the Medical Segmentation Decathlon’s liver dataset, and the BTCV multi-organ segmentation dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Brain NeoplasmsHumansElectric Power SuppliesLiverMasksImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Swin TransformerTransformermedical image segmentationself-attention

Autor:innen und Institutionen

  • College of Economics and Management, Xi'an University of Posts & Telecommunications, Xi'an 710061, China.
  • School of Life Science and Technology, Xidian University, Xi'an 710071, China.
  • School of Electronic Engineering, Xidian University, Xi'an 710071, China.

ORCID-Profile: Chen Wei, Shenghan Ren, Jimin Liang

Förderung

  • National Natural Science Foundation of China
  • The Key Research and Development Program in the Shaanxi Province of China
  • Key Research and Development Program in the Shaanxi Province of China
  • Scientific Research Program of the Education Department of Shaanxi Provincial Government

Zitieren

APA

Wei, C., Ren, S., Guo, K., Hu, H., & Liang, J. (2023). High-Resolution Swin Transformer for Automatic Medical Image Segmentation. Sensors, 23(7), 3420. https://doi.org/10.3390/s23073420

Vancouver

Wei C, Ren S, Guo K, Hu H, Liang J. High-Resolution Swin Transformer for Automatic Medical Image Segmentation. Sensors. 2023;23(7):3420. doi:10.3390/s23073420

BibTeX
@article{Wei2023,
  author = {Wei, Chen and Ren, Shenghan and Guo, Kaitai and Hu, Haihong and Liang, Jimin},
  title = {High-Resolution Swin Transformer for Automatic Medical Image Segmentation},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {7},
  pages = {3420},
  doi = {10.3390/s23073420}
}
Kostenlos starten →