Anatomy-Aware Fine-Grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report
IEEE Transactions on Medical Imaging · 2026-11 · 45 (11) · 5276-5288
DOI: 10.1109/tmi.2026.3719112 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026-11. Verfasst von Xingyue Zhao und 14 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Multimodal Imaging, Pharyngeal Neoplasms, Laryngeal Neoplasms. Gefördert von: Shanghai Natural Science Foundation of China, AI for Science Foundation of Fudan University, Fujian Provincial Department of Science and Technology Guidance Project.
Abstract (Originalsprache)
Accurate T-staging is crucial for guiding personalized treatment strategies for laryngopharyngeal cancer. However, current clinical practice relies on invasive biopsy procedures, whereas computed tomography (CT)-based staging remains challenging due to the complex patterns of tumor invasion. Recent computer-aided approaches face two key challenges: 1) Structural relationship modeling: existing methods underrepresent anatomically structured patterns of tumor invasion, as they either process whole CT volumes without tumor-specific anatomical constraints or rely on labor-intensive tumor segmentation. 2) Fine-grained cross-modal alignment: while radiology reports contain organ-specific invasion details, current methods that apply global feature fusion struggle to accurately align individual anatomical structures with their corresponding textual descriptions. To address these issues, we propose an anatomy-aware multimodal framework that integrates organ-level CT context and radiology reports into a unified representation for laryngopharyngeal T-staging. The framework first constructs an Anatomy-Structured Organ Graph (AOG) that captures invasion patterns between primary sites and surrounding organs, then performs Organ-Anchored Cross-Modal Alignment (OCA) so that each organ node aggregates textual evidence from the radiology report, and finally refines this graph representation by injecting organ-specific invasion cues extracted from the report via Report-Enhanced Graph-Refinement (REG), yielding a multimodal organ graph that combines spatial and textual evidence. Extensive experiments demonstrate that the proposed framework achieves superior performance in T-staging of laryngopharyngeal cancer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Shanghai Natural Science Foundation of China
- AI for Science Foundation of Fudan University
- Fujian Provincial Department of Science and Technology Guidance Project
- Xuhui District Academy-Local Cooperation Project of Shanghai
Zitieren
APA
Zhao, X., Su, Y., Zhang, F., Ji, Z., Wang, Y., Guo, D., Ju, S., Cheng, Y., Chen, Y., Feng, M., Lu, L., Ho, T. Y., Wang, J., Jin, D., & Shen, N. (2026). Anatomy-Aware Fine-Grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report. IEEE Transactions on Medical Imaging, 45(11), 5276-5288. https://doi.org/10.1109/tmi.2026.3719112
Vancouver
Zhao X, Su Y, Zhang F, Ji Z, Wang Y, Guo D, et al. Anatomy-Aware Fine-Grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report. IEEE Transactions on Medical Imaging. 2026;45(11):5276-5288. doi:10.1109/tmi.2026.3719112
BibTeX
@article{Zhao2026,
author = {Zhao, Xingyue and Su, Yanzhou and Zhang, Fang and Ji, Zhanghexuan and Wang, Yirui and Guo, Dazhou and Ju, Sibo and Cheng, Yuehua and Chen, Yuzhen and Feng, Ming and Lu, Le and Ho, Tsung-Ying and Wang, Jian and Jin, Dakai and Shen, Na},
title = {Anatomy-Aware Fine-Grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report},
journal = {IEEE Transactions on Medical Imaging},
year = {2026},
volume = {45},
number = {11},
pages = {5276--5288},
doi = {10.1109/tmi.2026.3719112}
}
EUVIMED