AUTHOR=Yu Ting-ting , Lam Sai-kit , To Lok-hang , Tse Ka-yan , Cheng Nong-yi , Fan Yeuk-nam , Lo Cheuk-lai , Or Ka-wa , Chan Man-lok , Hui Ka-ching , Chan Fong-chi , Hui Wai-ming , Ngai Lo-kin , Lee Francis Kar-ho , Au Kwok-hung , Yip Celia Wai-yi , Zhang Yong , Cai Jing 

TITLE=Pretreatment Prediction of Adaptive Radiation Therapy Eligibility Using MRI-Based Radiomics for Advanced Nasopharyngeal Carcinoma Patients

JOURNAL=Frontiers in Oncology

VOLUME=9

YEAR=2019

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2019.01050

DOI=10.3389/fonc.2019.01050

ISSN=2234-943X

ABSTRACT=<p><bold>Background and purpose:</bold> Adaptive radiotherapy (ART) can compensate for the dosimetric impacts induced by anatomic and geometric variations in patients with nasopharyngeal carcinoma (NPC); Yet, the need for ART can only be assessed during the radiation treatment and the implementation of ART is resource intensive. Therefore, we aimed to determine tumoral biomarkers using pre-treatment MR images for predicting ART eligibility in NPC patients prior to the start of treatment.</p><p><bold>Methods:</bold> Seventy patients with biopsy-proven NPC (Stage II-IVB) in 2015 were enrolled into this retrospective study. Pre-treatment contrast-enhanced T1-w (CET1-w), T2-w MR images were processed and filtered using Laplacian of Gaussian (LoG) filter before radiomic features extraction. A total of 479 radiomics features, including the first-order (<italic>n</italic> = 90), shape (<italic>n</italic> = 14), and texture features (<italic>n</italic> = 375), were initially extracted from Gross-Tumor-Volume of primary tumor (GTVnp) using CET1-w, T2-w MR images. Patients were randomly divided into a training set (<italic>n</italic> = 51) and testing set (<italic>n</italic> = 19). The least absolute shrinkage and selection operator (LASSO) logistic regression model was applied for radiomic model construction in training set to select the most predictive features to predict patients who were replanned and assessed in the testing set. A double cross-validation approach of 100 resampled iterations with 3-fold nested cross-validation was employed in LASSO during model construction. The predictive performance of each model was evaluated using the area under the receiver operator characteristic (ROC) curve (AUC).</p><p><bold>Results:</bold> In the present cohort, 13 of 70 patients (18.6%) underwent ART. Average AUCs in training and testing sets were 0.962 (95%CI: 0.961–0.963) and 0.852 (95%CI: 0.847–0.857) with 8 selected features for CET1-w model; 0.895 (95%CI: 0.893–0.896) and 0.750 (95%CI: 0.745–0.755) with 6 selected features for T2-w model; and 0.984 (95%CI: 0.983–0.984) and 0.930 (95%CI: 0.928–0.933) with 6 selected features for joint T1-T2 model, respectively. In general, the joint T1-T2 model outperformed either CET1-w or T2-w model alone.</p><p><bold>Conclusions:</bold> Our study successfully showed promising capability of MRI-based radiomics features for pre-treatment identification of ART eligibility in NPC patients.</p>