A Radiomics-Based Classifier for the Progression of Oropharyngeal Cancer Treated with Definitive Radiotherapy

• Published in: Cancers 2023-07, Vol.15 (14), p.3715
• Main Authors: Garcia, Darwin A, Jeans, Elizabeth B, Morris, Lindsay K, Shiraishi, Satomi, Laughlin, Brady S, Rong, Yi, Rwigema, Jean-Claude M, Foote, Robert L, Herman, Michael G, Qian, Jing
• Format: Article
• Language: English
• Subjects: Biomarkers; Cancer therapies; Care and treatment; Chemotherapy; Clinical trials; Datasets; Development and progression; Head and neck carcinoma; Human papillomavirus; Learning algorithms; Machine learning; Medical imaging equipment; Medical prognosis; Medical research; Medicine, Experimental; Metabolism; Oropharyngeal cancer; Papillomavirus infections; Patients; PET imaging; Positron emission tomography; Radiation therapy; Radiomics; Radiotherapy; Risk assessment; Software; Squamous cell carcinoma; Surveillance; Throat cancer; Tomography
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers15143715

In this study, we investigated whether radiomics features from pre-treatment positron emission tomography (PET) images could be used to predict disease progression in patients with HPV-positive oropharyngeal cancer treated with definitive proton or x-ray radiotherapy. Machine learning models were built using a dataset from Mayo Clinic, Rochester, Minnesota (n = 72) and tested on a dataset from Mayo Clinic, Phoenix, Arizona (n = 22). A total of 71 clinical and radiomics features were considered. The Mann-Whitney U test was used to identify the top 2 clinical and top 20 radiomics features that were significantly different between progression and progression-free patients. Two dimensionality reduction methods were used to define two feature sets (manually filtered or machine-driven). A forward feature selection scheme was conducted on each feature set to build models of increased complexity (number of input features from 1 to 6) and evaluate model robustness and overfitting. The machine-driven features had superior performance and were less prone to overfitting compared to the manually filtered features. The four-variable Gaussian Naïve Bayes model using the 'Radiation Type' clinical feature and three machine-driven features achieved a training accuracy of 79% and testing accuracy of 77%. These results demonstrate that radiomics features can provide risk stratification beyond HPV-status to formulate individualized treatment and follow-up strategies.