Cochlea CT radiomics predicts chemoradiotherapy induced sensorineural hearing loss in head and neck cancer patients: A machine learning and multi-variable modelling study. (January 2018)

• Record Type: Journal Article
• Authors: Abdollahi, Hamid; Mostafaei, Shayan; Cheraghi, Susan; Shiri, Isaac; Rabi Mahdavi, Seied; Kazemnejad, Anoshirvan
• Is Part Of: Physica medica. Volume 45(2018)
• Page Start: 192
• Page End: 197
• Publication Date: 2018-01
• Subjects: Cochlea -- CT -- Chemoradiotherapy -- Hearing loss -- Radiomics -- Prediction -- Machine learning -- LASSO; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2017.10.008
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: Chemoradiotherapy induces hearing loss in head and neck cancer patients. Radiomics is a new approach to assess and predict radiotherapy induced injuries. CT radiomic could help in the prediction of hearing loss induced by chemoradiation. Combination of radiomic features with clinical and dosimetric variables can model hearing loss. Abstract: Objectives: Immediately or after head-and-neck (H&N) cancer chemoradiotherapy (CRT), patients may undergone significant sensorineural hearing loss (SNHL) which could affect their quality of life. Radiomic feature analysis is proposed to predict SNHL induced by CRT. Material and methods: 490 image features of 94 cochlea from 47 patients treated with three dimensional conformal RT (3DCRT) for different H&N cancers were extracted from CT images. Different machine learning (ML) algorithms and also least absolute shrinkage and selection operator (LASSO) penalized logistic regression were implemented on radiomic features for feature selection, classification and prediction. Also, LASSO penalized logistic model was used for outcome modelling. Results: The predictive power of ten ML methods was more than 70% (in accuracy, precision and area under the curve of receiver operating characteristic curve (AUC)). According to the LASSO penalized logistic modelling, 10 of the 490 radiomic features selected as the associated features with SNHL status. All of the 10 features were statistically associated with SNHL (all of adjusted P-values < .001). Conclusion: CT radiomic analysis proposed in this study, could help in the prediction of hearing loss induced by chemoradiation. Our study also, demonstrates that combination of radiomic features with clinical and dosimetric variables can model radiotherapy outcome such as SNHL.