Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures

• Published in: European radiology Vol. 30; no. 11; pp. 6311 - 6321
• Main Authors: Mes, Steven W., van Velden, Floris H. P., Peltenburg, Boris, Peeters, Carel F. W., te Beest, Dennis E., van de Wiel, Mark A., Mekke, Joost, Mulder, Doriene C., Martens, Roland M., Castelijns, Jonas A., Pameijer, Frank A., de Bree, Remco, Boellaard, Ronald, Leemans, C. René, Brakenhoff, Ruud H., de Graaf, Pim
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2020
• Subjects: Aged; Area Under Curve; Biomarkers; Comorbidity; Diagnostic Radiology; Disease-Free Survival; Factor Analysis, Statistical; Female; Head and Neck; Head and Neck Neoplasms - diagnostic imaging; Humans; Imaging; Internal Medicine; Interventional Radiology; Kaplan-Meier Estimate; Magnetic Resonance Imaging; Male; Medicine; Medicine & Public Health; Middle Aged; Neoplasm Recurrence, Local - diagnostic imaging; Neuroradiology; Observer Variation; Prognosis; Radiology; Radiometry; Reproducibility of Results; Retrospective Studies; Squamous Cell Carcinoma of Head and Neck - diagnostic imaging; Treatment Outcome; Ultrasound; Prognosis; Factor analysis; Magnetic resonance imaging; Head and neck neoplasms
• ISSN: 0938-7994; 1432-1084
• DOI: 10.1007/s00330-020-06962-y

Objectives Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. Materials and Methods Native T1-weighted images of four independent, retrospective (2005–2013), patient cohorts ( n = 102, n = 76, n = 89, and n = 56) were used to delineate primary tumors, and to extract 545 quantitative features from. Subsequently, redundancy filtering and factor analysis were performed to handle collinearity in the data. Next, radiomic prognostic models were trained and validated to predict overall survival (OS) and relapse-free survival (RFS). Radiomic features were compared to and combined with prognostic models based on standard clinical parameters. Performance was assessed by integrated area under the curve (iAUC). Results In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only ( p < 0.001). Conclusions MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. Key Points • MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. • MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. • Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.