A deep learning method for differentiating nasopharyngeal carcinoma and lymphoma based on MRI.
10.13201/j.issn.2096-7993.2025.07.001
- Author:
Yuchen TANG
1
;
Hongli HUA
1
;
Yan WANG
1
;
Zezhang TAO
1
Author Information
1. Department of Otolaryngology Head and Neck Surgery，Wuhan University People's Hospital，Wuhan，430000，China.
- Publication Type:Journal Article
- Keywords:
MRI;
deep learning;
nasopharyngeal carcinoma;
nasopharyngeal lymphoma
- MeSH:
Humans;
Nasopharyngeal Carcinoma/diagnostic imaging*;
Deep Learning;
Magnetic Resonance Imaging;
Retrospective Studies;
Nasopharyngeal Neoplasms/diagnostic imaging*;
Lymphoma/diagnostic imaging*;
Diagnosis, Differential;
ROC Curve;
Male;
Female;
Middle Aged;
Adult
- From:
Journal of Clinical Otorhinolaryngology Head and Neck Surgery
2025;39(7):597-609
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To development a deep learning（DL） model based on conventional MRI for automatic segmentation and differential diagnosis of nasopharyngeal carcinoma（NPC） and nasopharyngeal lymphoma（NPL）. Methods:The retrospective study included 142 patients with NPL and 292 patients with NPC who underwent conventional MRI at Renmin Hospital of Wuhan University from June 2012 to February 2023. MRI from 80 patients were manually segmented to train the segmentation model. The automatically segmented regions of interest（ROIs） formed four datasets: T1 weighted images（T1WI）, T2 weighted images（T2WI）, T1 weighted contrast-enhanced images（T1CE）, and a combination of T1WI and T2WI. The ImageNet-pretrained ResNet101 model was fine-tuned for the classification task. Statistical analysis was conducted using SPSS 22.0. The Dice coefficient loss was used to evaluate performance of segmentation task. Diagnostic performance was assessed using receiver operating characteristic（ROC） curves. Gradient-weighted class activation mapping（Grad-CAM） was imported to visualize the model's function. Results:The DICE score of the segmentation model reached 0.876 in the testing set. The AUC values of classification models in testing set were as follows: T1WI: 0.78（95%CI 0.67-0.81）, T2WI: 0.75（95%CI 0.72-0.86）, T1CE: 0.84（95%CI 0.76-0.87）, and T1WI+T2WI: 0.93（95%CI 0.85-0.94）. The AUC values for the two clinicians were 0.77（95%CI 0.72-0.82） for the junior, and 0.84（95%CI 0.80-0.89） for the senior. Grad-CAM analysis revealed that the central region of the tumor was highly correlated with the model's classification decisions, while the correlation was lower in the peripheral regions. Conclusion:The deep learning model performed well in differentiating NPC from NPL based on conventional MRI. The T1WI+T2WI combination model exhibited the best performance. The model can assist in the early diagnosis of NPC and NPL, facilitating timely and standardized treatment, which may improve patient prognosis.
