EUVIMEDEUVIMED entdecken
Crossref

FCT-Net: Efficient Bridge Fusion Incorporating CNN-Transformer Network for Medical Image Segmentation

Bowen Zhou, Xingbo Dong, Xiaowei Zhao, Chenglong Li, Zhe Jin, Huabin Wang

IEEE Transactions on Radiation and Plasma Medical Sciences · 2025-07 · 9 (6) · 762-775

DOI: 10.1109/trpms.2024.3516014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Radiation and Plasma Medical Sciences, 2025-07. Verfasst von Bowen Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The hybrid architecture of convolutional neural networks (CNNs) and Transformers has gained popularity in medical image segmentation. However, in this hybrid architecture, the semantic gaps between multiscale CNN and Transformer branch features hinder the segmentation performance. To address this issue, we propose a new pipeline for medical image segmentation, named FCT-Net. First, we employ large kernel convolutions in CNN branch and the shift-window self-attention mechanism in Transformer branch to construct a parallel three-branch architecture for efficiently capturing global and local information. Second, to better fuse CNN and Transformer features, we introduce the bridge fusion module (BFM), to effectively extract local features and global representations at different semantic scales by integrating semantic information from different branches, thereby reducing the semantic gap between features. Finally, to capture multiscale information during the encoding process, we design the multiscale feature compilation module (MFCM) to adaptively fuse features from different stages of the encoder. Additionally, we introduce residual attention (RA) to enhance the features obtained after encoding, further boosting the network’s representational capacity. FCT-Net is evaluated on four different medical image segmentation benchmarks, achieving Dice scores of 83.56%, 90.87%, 92.21%, and 91.92% on COVID-19 Lung dataset, ISIC-2018, SegPC-2021, and ACDC, respectively, outperforming other state-of-the-art methods. Source code will be available athttps://github.com/ZBW830/FCTNet.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhou, B., Dong, X., Zhao, X., Li, C., Jin, Z., & Wang, H. (2025). FCT-Net: Efficient Bridge Fusion Incorporating CNN-Transformer Network for Medical Image Segmentation. IEEE Transactions on Radiation and Plasma Medical Sciences, 9(6), 762-775. https://doi.org/10.1109/trpms.2024.3516014

Vancouver

Zhou B, Dong X, Zhao X, Li C, Jin Z, Wang H. FCT-Net: Efficient Bridge Fusion Incorporating CNN-Transformer Network for Medical Image Segmentation. IEEE Transactions on Radiation and Plasma Medical Sciences. 2025;9(6):762-775. doi:10.1109/trpms.2024.3516014

BibTeX
@article{Zhou2025,
  author = {Zhou, Bowen and Dong, Xingbo and Zhao, Xiaowei and Li, Chenglong and Jin, Zhe and Wang, Huabin},
  title = {FCT-Net: Efficient Bridge Fusion Incorporating CNN-Transformer Network for Medical Image Segmentation},
  journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
  year = {2025},
  volume = {9},
  number = {6},
  pages = {762--775},
  doi = {10.1109/trpms.2024.3516014}
}
Kostenlos starten →