EUVIMEDEUVIMED entdecken
Crossref

A Dual‐Branch Cross‐Attention Fusion Network for Multi‐Subtype Lung Cancer Classification

Libin Liu, Yanfang Huang, Xiqing Li, Nuo Zheng, Nila Wang, Tingxiong Xiao, Xiaolong Lin, Haidun Chen, Qin Shi, Yuyin Le iD

The International Journal of Medical Robotics and Computer Assisted Surgery · 2026-06 · 22 (3)

DOI: 10.1002/rcs.70183 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, online erschienen am 13.05.2026. Verfasst von Libin Liu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Fuzhou Pulmonary Hospital of Fujian Province, Teaching Hospital of Fujian Medical University, Fuzhou, Fujian, China. Hauptthemen laut MEDLINE: Lung Neoplasms, Tomography, X-Ray Computed. Die Arbeit nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate lung cancer subtyping from CT images is essential for treatment planning. However, manual interpretation suffers from inter‐observer variability across morphologically similar subtypes.

Methods

To overcome this limitation, we propose a dual‐branch cross‐attention fusion network integrating ConvNeXt‐Small and Swin Transformer‐Small. Specifically, this architecture captures both local textures and global structural representations. A learnable cross‐attention module then fuses these streams into a 512‐dimensional unified descriptor. We train our network on a four‐class dataset.

Results

It achieves 98.46% accuracy and 98.45% F1‐score on the test set. Ultimately, our method significantly outperforms state‐of‐the‐art baselines.

Conclusions

The proposed framework demonstrates massive clinical potential for non‐invasive subtyping, offering a robust tool for personalised treatment planning while reducing diagnostic subjectivity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsTomography, X-Ray ComputedHumansAlgorithmsNeural Networks, ComputerDeep Learning

Stichwörter der Autor:innen

cross‐attention fusiondeep learningdual‐branch networklung cancer subtyping

Autor:innen und Institutionen

  • Department of Radiation Oncology, Fuzhou Pulmonary Hospital of Fujian Province, Teaching Hospital of Fujian Medical University, Fuzhou, Fujian, China.
  • Department of Oncology, Fuzhou Pulmonary Hospital of Fujian Province, Teaching Hospital of Fujian Medical University, Fuzhou, Fujian, China.
  • Central Laboratory, Fujian Medical University Clinical Teaching Hospital, Fuzhou Pulmonary Hospital of Fujian Province, Fuzhou, Fujian, China.

ORCID-Profile: Yuyin Le

Zitieren

APA

Liu, L., Huang, Y., Li, X., Zheng, N., Wang, N., Xiao, T., Lin, X., Chen, H., Shi, Q., & Le, Y. (2026). A Dual‐Branch Cross‐Attention Fusion Network for Multi‐Subtype Lung Cancer Classification. The International Journal of Medical Robotics and Computer Assisted Surgery, 22(3). https://doi.org/10.1002/rcs.70183

Vancouver

Liu L, Huang Y, Li X, Zheng N, Wang N, Xiao T, et al. A Dual‐Branch Cross‐Attention Fusion Network for Multi‐Subtype Lung Cancer Classification. The International Journal of Medical Robotics and Computer Assisted Surgery. 2026;22(3). doi:10.1002/rcs.70183

BibTeX
@article{Liu2026,
  author = {Liu, Libin and Huang, Yanfang and Li, Xiqing and Zheng, Nuo and Wang, Nila and Xiao, Tingxiong and Lin, Xiaolong and Chen, Haidun and Shi, Qin and Le, Yuyin},
  title = {A Dual‐Branch Cross‐Attention Fusion Network for Multi‐Subtype Lung Cancer Classification},
  journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
  year = {2026},
  volume = {22},
  number = {3},
  doi = {10.1002/rcs.70183}
}
Kostenlos starten →