Deep learning for risk prediction in patients with nasopharyngeal carcinoma using multi-parametric MRIs

• Published in: Computer methods and programs in biomedicine Vol. 197; p. 105684
• Main Authors: Jing, Bingzhong, Deng, Yishu, Zhang, Tao, Hou, Dan, Li, Bin, Qiang, Mengyun, Liu, Kuiyuan, Ke, Liangru, Li, Taihe, Sun, Ying, Lv, Xing, Li, Chaofeng
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01-12-2020
• Subjects: Deep Learning; Humans; Magnetic resonance images; Magnetic Resonance Imaging; Nasopharyngeal carcinoma; Nasopharyngeal Carcinoma - diagnostic imaging; Nasopharyngeal Neoplasms - diagnostic imaging; Retrospective Studies; Risk prediction; Survival analysis; Deep learning; Nasopharyngeal carcinoma; Survival analysis; Risk prediction; Magnetic resonance images
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2020.105684

lWe proposed deep learning to integrate multi-parametric MRIs as a novel prognostic factor to predict the overall risk score in patients with NPC.lWe used a large retrospective cohort study to test the performance and validate the feasibility of utilizing the method in the real world.lWe developed a novel model to predict the overall risk score for NPC patients by integrating quantitation of multi-parametric MRIs with clinical stages, which was more accurate than using clinical stages alone.
Magnetic resonance images (MRI) is the main diagnostic tool for risk stratification and treatment decision in nasopharyngeal carcinoma (NPC). However, the holistic feature information of multi-parametric MRIs has not been fully exploited by clinicians to accurately evaluate patients.
To help clinicians fully utilize the missed information to regroup patients, we built an end-to-end deep learning model to extract feature information from multi-parametric MRIs for predicting and stratifying the risk scores of NPC patients.
In this paper, we proposed an end-to-end multi-modality deep survival network (MDSN) to precisely predict the risk of disease progression of NPC patients. Extending from 3D dense net, this proposed MDSN extracted deep representation from multi-parametric MRIs (T1w, T2w, and T1c). Moreover, deep features and clinical stages were integrated through MDSN to more accurately predict the overall risk score (ORS) of individual NPC patient.
A total of 1,417 individuals treated between January 2012 and December 2014 were included for training and validating the end-to-end MDSN. Results were then tested in a retrospective cohort of 429 patients included in the same institution. The C-index of the proposed method with or without clinical stages was 0.672 and 0.651 on the test set, respectively, which was higher than the that of the stage grouping (0.610).
The C-index of the model which integrated clinical stages with deep features is 0.062 higher than that of stage grouping alone (0.672 vs 0.610). We conclude that features extracted from multi-parametric MRIs based on MDSN can well assist the clinical stages in regrouping patients.