Automated Prediction of Radiotherapy Sensitivity Using Hybrid Model-Based MRI Radiomics in Locally Advanced Cervical Cancer

Abstract

Abstract Background To develop a model that could automatically predict radiotherapy sensitivity for patients with locally advanced cervical cancer (LACC) based on T2-weighted MR images and clinical parameters. Methods: A total of 138 patients were enrolled, T2-weighted MR images and clinical information of the patients before treatment were collected. Clinical information includes age, stage, pathological type, squamous cell carcinoma (SCC) level, and lymph node status. A hybrid model extracted the domain specific features from computational radiomics system, the abstract features from deep learning network and the clinical parameters, and employed an ensemble learning classifier weighted by logistic regression (LR) classifier, support vector machine (SVM) classifier, K-Nearest Neighbor (KNN) classifier and Bayesian classifier to predict pathologic complete response (pCR).The area under the receiver operating characteristics curve (AUC), accuracy (ACC), true positive rate (TPR), true negative rate (TNR) and precision were used as evaluation metrics. Results: Among 138 LACC patients, 74 were in the pCR group and 64 were in the non-pCR group. There was no significant difference between the two cohorts in terms of tumor diameter, lymph node and stage before radiotherapy, p = 0.787, 0.068, 0.846, respectively. The 109-dimension domain features and 1472-dimension abstract features from MRI image were selected to use for forming hybrid model. The average AUC, ACC, TPR, TNR and precision of the proposed hybrid model was about 0.80, 0.71, 0.75, 0.66 and 0.71, while The AUC values of using clinical parameters, domain specific features, abstract features alone were 0.61, 0.67 and 0.76, respectively. The AUC value of model without ensemble learning classifier was 0.76. Conclusions: The proposed hybrid model could predict well radiotherapy sensitivity of patients with LACC, which might help radiation oncologist to make personalized treatment plans for patients.