Multi‐Sequence Fusion MRI Deep Learning Models for Discrimination of Recurrent Nasopharyngeal Carcinoma and Osteoradionecrosis
- 1ENT Institute and Department of Otolaryngology, Eye & ENT Hospital Fudan University Shanghai China
Abstract
Objectives To develop a multi‐sequence fusion model based on MRI images to differentiate between recurrent nasopharyngeal carcinoma (rNPC) and osteoradionecrosis (ORN) in patients with nasopharyngeal carcinoma (NPC) after radiotherapy, and to evaluate its diagnostic performance. Methods We retrospectively reviewed 370 patients with pathologically confirmed recurrent nasopharyngeal carcinoma (rNPC) or osteoradionecrosis (ORN). After screening, 346 patients (207 rNPC and 139 ORN) with both axial T1‐weighted contrast‐enhanced imaging (T1C) and T2‐weighted imaging (T2WI) were included and randomly split into a training set (n = 212), validation set (n = 61), and test set (n = 73). A dual‐branch 3D‐ResNet‐50‐based fusion model was developed to integrate multi‐sequence MRI features. Model performance was evaluated using AUC, accuracy, sensitivity, specificity, precision, and F1 score. Results On the test set, the proposed 3D‐ResNet‐Fusion model achieved an AUC of 0.86 and an accuracy of 84%, with a sensitivity of 91%, specificity of 72%, precision of 83%, and an F1 score of 0.87. Based on AUC comparisons, the fusion model outperformed comparator models based on EfficientNet (0.77, p = 0.20) and DenseNet (0.70, p = 0.02), as well as single‐sequence 3D‐ResNet models trained on T1C alone (0.71, p = 0.02) or T2WI alone (0.73, p = 0.046). In the human–AI comparison experiment, the proposed AI model achieved a 3% higher ACC than the senior otolaryngologist (p = 0.83), and outperformed the two junior otolaryngologists by 15% (p = 0.05) and 22% (p < 0.01), respectively. Conclusion The proposed AI model effectively integrates information from multiple MRI sequences, significantly improving classification performance in distinguishing rNPC from ORN.
Related
- The Oxygenation-Nutritional-Inflammatory (ONI) index and the risk of osteoradionecrosis of the jaw in locally advanced nasopharyngeal carcinoma: a continuous multidimensional modeling analysis.
- Recursive partitioning analysis model based on ¹⁸F-FDG PET/CT metabolic parameters for recurrent or metastatic nasopharyngeal carcinoma treated with PD-1 inhibitors and chemotherapy.
- Primary Epstein–Barr virus-negative lymphoepithelioma-like carcinoma of the supraglottic larynx mimicking nasopharyngeal carcinoma: a case report
- The association between serum uric acid and prognosis of nasopharyngeal carcinoma: a comprehensive meta-analysis of observational studies
- Rethinking nasopharyngeal carcinoma management: toward a low-toxicity, highly effective regimen with favorable tolerability and quality of life
BibTeX
@article{gong2026multisequence,
title = {{Multi‐Sequence Fusion MRI Deep Learning Models for Discrimination of Recurrent Nasopharyngeal Carcinoma and Osteoradionecrosis}},
author = {Wen‐Tao Gong and Xue‐Li Liu and Xiao Chen and Zhen Li and Ming‐Yan Qiu and Shang Shi and Xuan‐Yu Zhao and Li Wang and Quan Liu and Xi‐Cai Sun and Yu‐Xuan Shi and Hong‐Meng Yu},
journal = {World Journal of Otorhinolaryngology-Head and Neck Surgery},
year = {2026},
month = oct,
doi = {10.1002/wjo2.70165},
url = {https://doi.org/10.1002/wjo2.70165},
note = {CC BY},
}
RIS
TY - JOUR
TI - Multi‐Sequence Fusion MRI Deep Learning Models for Discrimination of Recurrent Nasopharyngeal Carcinoma and Osteoradionecrosis
AU - Wen‐Tao Gong
AU - Xue‐Li Liu
AU - Xiao Chen
AU - Zhen Li
AU - Ming‐Yan Qiu
AU - Shang Shi
AU - Xuan‐Yu Zhao
AU - Li Wang
AU - Quan Liu
AU - Xi‐Cai Sun
AU - Yu‐Xuan Shi
AU - Hong‐Meng Yu
PY - 2026
DA - 2026/10/23
JO - World Journal of Otorhinolaryngology-Head and Neck Surgery
DO - 10.1002/wjo2.70165
UR - https://doi.org/10.1002/wjo2.70165
AB - Objectives To develop a multi‐sequence fusion model based on MRI images to differentiate between recurrent nasopharyngeal carcinoma (rNPC) and osteoradionecrosis (ORN) in patients with nasopharyngeal carcinoma (NPC) after radiotherapy, and to evaluate its diagnostic performance. Methods We retrospectively reviewed 370 patients with pathologically confirmed recurrent nasopharyngeal carcinoma (rNPC) or osteoradionecrosis (ORN). After screening, 346 patients (207 rNPC and 139 ORN) with both axial T1‐weighted contrast‐enhanced imaging (T1C) and T2‐weighted imaging (T2WI) were included and randomly split into a training set (n = 212), validation set (n = 61), and test set (n = 73). A dual‐branch 3D‐ResNet‐50‐based fusion model was developed to integrate multi‐sequence MRI features. Model performance was evaluated using AUC, accuracy, sensitivity, specificity, precision, and F1 score. Results On the test set, the proposed 3D‐ResNet‐Fusion model achieved an AUC of 0.86 and an accuracy of 84%, with a sensitivity of 91%, specificity of 72%, precision of 83%, and an F1 score of 0.87. Based on AUC comparisons, the fusion model outperformed comparator models based on EfficientNet (0.77, p = 0.20) and DenseNet (0.70, p = 0.02), as well as single‐sequence 3D‐ResNet models trained on T1C alone (0.71, p = 0.02) or T2WI alone (0.73, p = 0.046). In the human–AI comparison experiment, the proposed AI model achieved a 3% higher ACC than the senior otolaryngologist (p = 0.83), and outperformed the two junior otolaryngologists by 15% (p = 0.05) and 22% (p < 0.01), respectively. Conclusion The proposed AI model effectively integrates information from multiple MRI sequences, significantly improving classification performance in distinguishing rNPC from ORN.
SN - 2589-1081
SN - 2095-8811
ER -