EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MRI segmentation of head and neck tumors using hybrid attention mechanism and dense dilated spatial pyramid pooling

Qiang Han iD, Songlin He, Yuebin Zheng, Huacai Zhong, Dengyao Luo, Jun Wu, Zhiqiang Zhao, Bincheng Yan, Chengjian Cao, Xiu Liu

Journal of Applied Clinical Medical Physics · 2026

DOI: 10.1002/acm2.70426 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, 2026. Verfasst von Qiang Han und 9 weiteren Autor:innen. Beteiligte Einrichtung: Intelligent Perception and Control Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Yibin, China. Hauptthemen laut MEDLINE: Head and Neck Neoplasms, Magnetic Resonance Imaging, Radiotherapy Planning, Computer-Assisted, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Health Commission of Sichuan Province Medical Science and Technology Program, Key Research and Development Project for High-Quality Development of Zigong First People's Hospital and Zigong Academy of Medical Sciences in 2024, Sichuan University of Science and Engineering Talent Introduction Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Head and neck cancer (HNC) involves anatomically intricate regions where precise target delineation is essential for radiotherapy. The superior soft‐tissue contrast of MRI provides clearer boundary visualization compared with computed tomography (CT), enabling tighter margins and supporting daily plan adaptation in online adaptive radiotherapy. However, despite the advances of U‐Net‐based deep learning models, tumor segmentation in HNC remains challenging due to ill‐defined borders and heterogeneous intensity patterns, which limit feature extraction and compromise small‐lesion recognition.

Purpose

To overcome the limitations of traditional approaches, this study proposes an improved SCDU‐Net model that integrates collaborative spatial‐channel attention mechanisms with densely connected atrous spatial pyramid pooling techniques, aiming to significantly enhance the segmentation accuracy and robustness of head and neck tumor MRI images.

Methods

SCDU‐Net integrates two modified modules to improve segmentation capability. The model incorporates a spatial‐channel dual attention module (SC) in the decoding pathway, which strengthens critical tumor feature expression through adaptive channel weight adjustment mechanisms, while capturing long‐range spatial dependencies using coordinate axis attention to improve localization accuracy of small target lesions. Additionally, the network embeds a densely connected atrous spatial pyramid pooling module dense atrous spatial pyramid pooling (DenseASPP) in the bottleneck layer, which enhances edge contour detail perception through multi‐scale receptive field fusion strategies, improving the network's segmentation performance.

Results

Our proposed model is evaluated on the publicly available HNTS‐MRG2024 dataset, showing promising results compared to existing approaches.

Conclusions

The results indicate that by integrating two modules, our method performs spatial and channel feature recalibration and multi‐scale contextual modeling within the deep neural network, yielding more accurate and promising head and neck tumor segmentation with potential to assist physicians in diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Head and Neck NeoplasmsMagnetic Resonance ImagingRadiotherapy Planning, Computer-AssistedImage Processing, Computer-AssistedDeep LearningHumansAlgorithmsRadiotherapy, Intensity-ModulatedTomography, X-Ray ComputedRadiotherapy Dosage

Stichwörter der Autor:innen

MRIU‐Netdeep learningdensely connected atrous spatial pyramid poolinghead and neck tumor segmentationspatial–channel dual attention

Autor:innen und Institutionen

  • Intelligent Perception and Control Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Yibin, China.
  • School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin, China.
  • Department of Otorhinolaryngology Head and Neck Surgery, Zigong First People's Hospital, Zigong, China.

ORCID-Profile: Qiang Han

Förderung

  • Health Commission of Sichuan Province Medical Science and Technology Program
  • Key Research and Development Project for High-Quality Development of Zigong First People's Hospital and Zigong Academy of Medical Sciences in 2024
  • Sichuan University of Science and Engineering Talent Introduction Program

Zitieren

APA

Han, Q., He, S., Zheng, Y., Zhong, H., Luo, D., Wu, J., Zhao, Z., Yan, B., Cao, C., & Liu, X. (2026). MRI segmentation of head and neck tumors using hybrid attention mechanism and dense dilated spatial pyramid pooling. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70426

Vancouver

Han Q, He S, Zheng Y, Zhong H, Luo D, Wu J, et al. MRI segmentation of head and neck tumors using hybrid attention mechanism and dense dilated spatial pyramid pooling. Journal of Applied Clinical Medical Physics. 2026. doi:10.1002/acm2.70426

BibTeX
@article{Han2026,
  author = {Han, Qiang and He, Songlin and Zheng, Yuebin and Zhong, Huacai and Luo, Dengyao and Wu, Jun and Zhao, Zhiqiang and Yan, Bincheng and Cao, Chengjian and Liu, Xiu},
  title = {MRI segmentation of head and neck tumors using hybrid attention mechanism and dense dilated spatial pyramid pooling},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  doi = {10.1002/acm2.70426}
}
Kostenlos starten →