Skip to main content

ORIGINAL RESEARCH article

Front. Neurol.
Sec. Applied Neuroimaging
Volume 15 - 2024 | doi: 10.3389/fneur.2024.1344324
This article is part of the Research Topic Recent insights in Neuroimaging: advancements in therapeutic studies and early diagnosis View all 3 articles

MRI-based radiomics models predict cystic brain radionecrosis of nasopharyngeal carcinoma after intensity modulated radiotherapy

Provisionally accepted
Jing Hou Jing Hou 1Yun He Yun He 2Handong Li Handong Li 1Qiang Lu Qiang Lu 1Huashan Lin Huashan Lin 3Biao Zeng Biao Zeng 1*Chuanmiao Xie Chuanmiao Xie 2*Xiaoping Yu Xiaoping Yu 1*
  • 1 Hunan Cancer Hospital, Xiangya School of Medicine, Central South University, Changsha, China
  • 2 Sun Yat-sen University Cancer Center (SYSUCC), Guangzhou, Guangdong Province, China
  • 3 Department of Pharmaceuticals Diagnosis, GE Healthcare (China), Hangzhou, Jiangsu Province, China

The final, formatted version of the article will be published soon.

    Objective: To construct radiomics models based on MRI at different time points for the early prediction of cystic brain radionecrosis (CBRN) for nasopharyngeal carcinoma (NPC). Methods: A total of 202 injured temporal lobes from 155 NPC patients with radiotherapy-induced temporal lobe injury (RTLI) after intensity modulated radiotherapy (IMRT) were included in the study. All the injured lobes were randomly divided into the training (n = 143) and validation (n = 59) sets. Radiomics models were constructed by using features extracted from T2WI at two different time points: at the end of IMRT (post-IMRT) and the first-detected RTLI (first-RTLI). A delta-radiomics feature was defined as the percentage change in a radiomics feature from post-IMRT to first-RTLI. The radiomics nomogram was constructed by combining clinical risk factors and radiomics signatures using multivariate logistic regression analysis. Predictive performance was evaluated using receiver operating characteristic analysis, and the area under the curve (AUC) values of the different models were compared by DeLong test. Results: The post-IMRT, first-RTLI, and delta-radiomics models yielded AUC values of 0.84 (95% CI: 0.76-0.92), 0.86 (95% CI: 0.78-0.94), and 0.77 (95% CI: 0.67-0.87), respectively. The nomogram, which combined the history of drinking and radiomics signatures exhibited the highest AUC of 0.91 (95% CI: 0.85-0.97) compared to any single radiomics model. However, there were no statistically significant differences between the nomogram and post-IMRT radiomics model, nor between the nomogram and first-RTLI radiomics model. Conclusion: Both radiomic models based on MRI at the end of IMRT and the first-detected RTLI, as well as radiomics nomogram model showed similarly excellent prediction potential. CBRN can be predicted at an earlier time after the completion of IMRT rather than at the first-detected RTLI.

    Keywords: nasopharyngeal carcinoma, Cystic brain radionecrosis, Magnetic Resonance Imaging, Radiomics, Intensity Modulated Radiotherapy

    Received: 25 Nov 2023; Accepted: 30 Apr 2024.

    Copyright: © 2024 Hou, He, Li, Lu, Lin, Zeng, Xie and Yu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Biao Zeng, Hunan Cancer Hospital, Xiangya School of Medicine, Central South University, Changsha, China
    Chuanmiao Xie, Sun Yat-sen University Cancer Center (SYSUCC), Guangzhou, 510060, Guangdong Province, China
    Xiaoping Yu, Hunan Cancer Hospital, Xiangya School of Medicine, Central South University, Changsha, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.