EUVIMEDEUVIMED entdecken
Crossref

ASCNet: An Adaptive Spatial Contextual Network for Accurate Acupoint Detection in Chinese Acupuncture

Yingying Cao, Zhaoshui He, Hao Liang, Zihang He, Zhijie Lin, Min Shi, Shengli Xie

IEEE Sensors Journal · 15.06.2026 · 26 (12) · 19370-19381

DOI: 10.1109/jsen.2026.3690187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.06.2026. Verfasst von Yingying Cao und 6 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Postdoctoral Fellowship Program and China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Acupuncture is one of the most important therapies in Traditional Chinese Medicine (TCM), and its efficacy depends on the accurate detection of acupoints. Unlike general object detection, acupoint detection remains challenging because its visual features are not obvious and can be difficult to distinguish. Furthermore, most existing deep learning methods do not sufficiently consider modeling the strong dependencies between acupoints, which can greatly affect the detection performance. To address these challenges, this article proposes an adaptive spatial contextual network (ASCNet) consisting of two main modules: the adaptive spatial-aware (ASA) module and the deformable contextual feature (DCF) module. First, the ASA module enhances discriminative feature extraction by promoting information interaction across features, thereby improving the model’s learning capacity. Then, the DCF module leverages the long-range dependency modeling capability of the context network and integrates deformable receptive fields to more effectively capture the correlations between acupoints, thereby reducing missed detections and false detections. Extensive experiments conducted on two acupoint datasets show that the proposed ASCNet achieves superior performance compared with state-of-the-art methods.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Postdoctoral Fellowship Program and China Postdoctoral Science Foundation
  • Basic and Applied Basic Research Foundation of Guangdong Province

Zitieren

APA

Cao, Y., He, Z., Liang, H., He, Z., Lin, Z., Shi, M., & Xie, S. (2026). ASCNet: An Adaptive Spatial Contextual Network for Accurate Acupoint Detection in Chinese Acupuncture. IEEE Sensors Journal, 26(12), 19370-19381. https://doi.org/10.1109/jsen.2026.3690187

Vancouver

Cao Y, He Z, Liang H, He Z, Lin Z, Shi M, et al. ASCNet: An Adaptive Spatial Contextual Network for Accurate Acupoint Detection in Chinese Acupuncture. IEEE Sensors Journal. 2026;26(12):19370-19381. doi:10.1109/jsen.2026.3690187

BibTeX
@article{Cao2026,
  author = {Cao, Yingying and He, Zhaoshui and Liang, Hao and He, Zihang and Lin, Zhijie and Shi, Min and Xie, Shengli},
  title = {ASCNet: An Adaptive Spatial Contextual Network for Accurate Acupoint Detection in Chinese Acupuncture},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {19370--19381},
  doi = {10.1109/jsen.2026.3690187}
}
Kostenlos starten →