MRI-based radiomics signature is a quantitative prognostic biomarker for nasopharyngeal carcinoma

Abstract

This study aimed to develop prognosis signatures through a radiomics analysis for patients with nasopharyngeal carcinoma (NPC) by their pretreatment diagnosis magnetic resonance imaging (MRI). A total of 208 radiomics features were extracted for each patient from a database of 303 patients. The patients were split into the training and validation cohorts according to their pretreatment diagnosis date. The radiomics feature analysis consisted of cluster analysis and prognosis model analysis for disease free-survival (DFS), overall survival (OS), distant metastasis-free survival (DMFS) and locoregional recurrence-free survival (LRFS). Additionally, two prognosis models using clinical features only and combined radiomics and clinical features were generated to estimate the incremental prognostic value of radiomics features. Patients were clustered by non-negative matrix factorization (NMF) into two groups. It showed high correspondence with patients’ T stage (p < 0.00001) and overall stage information (p < 0.00001) by chi-squared tests. There were significant differences in DFS (p = 0.0052), OS (p = 0.033), and LRFS (p = 0.037) between the two clustered groups but not in DMFS (p = 0.11) by log-rank tests. Radiomics nomograms that incorporated radiomics and clinical features could estimate DFS with the C-index of 0.751 [0.639, 0.863] and OS with the C-index of 0.845 [0.752, 0.939] in the validation cohort. The nomograms improved the prediction accuracy with the C-index value of 0.029 for DFS and 0.107 for OS compared with clinical features only. The DFS and OS radiomics nomograms developed in our study demonstrated the excellent prognostic estimation for NPC patients with a noninvasive way of MRI. The combination of clinical and radiomics features can provide more information for precise treatment decision.

Baseline MRI-Radiomics Can Predict Overall Survival in Non-Endemic EBV-Related Nasopharyngeal Carcinoma Patients

“…The combined signature was the one with the best performance. This is in line with the majority of studies of literature on radiomics applications to head and neck cancer (see [ 10 , 18 ] or the training set in [ 13 ]).…”

“…In terms of DFS, the combined radiomic-clinical model (HR 1.98 (1.03–3.80), log-rank p = 0.037) was the only one determining a significant split in the Kaplan-Meier curves between low- and high-risk patients. However, The C-index of the combined model in the study was lower than that reported by the previous studies on NPC [ 10 , 12 , 16 ]. This may depend on the fact that those models were trained specifically for DFS prognosis.…”

“…The present results were indeed comparable to the ones observed for a prognostic model for OS trained on a larger dataset of computed tomography (CT) images [ 18 ]. The performance of the present model was worse than the analogous one developed for patients from endemic areas [ 10 , 13 ] but this may be due to the differences in the type of image used, since those models, unlike ours, also involve contrast-enhanced T1w. It is also interesting to see how a relatively simple model based on Cox regression like the one presented in this study managed to perform similarly, in terms of C-index on the primary endpoint, to a model based on a more complex deep learning model trained on a larger dataset of over 400 patients [ 20 ].…”

“…Head and neck magnetic resonance imaging (MRI) is the modality of choice for loco-regionally staging of NPC [ 9 ]. Recently MRI-based radiomics signatures turned out to significantly predict response to induction chemotherapy and survival in advanced NPC [ 10 , 11 , 12 , 13 , 14 ].…”

Exploring Applications of Radiomics in Magnetic Resonance Imaging of Head and Neck Cancer: A Systematic Review

“…At the time, CT radiomics research in HNC concentrated on the latter category ( 14 ). Discovered through our search strategy, abstracts from conference proceedings (Table S3 in Supplementary Material) all focused on prognostic endpoints in NPC patients ( 71 – 73 ). Thus, perhaps, MRI radiomic studies in HNC are trending toward these outcome measures.…”