Machine learning-based radiomics nomograms to predict number of fields in postoperative IMRT for breast cancer

Abstract

Background: Breast cancer is now the most commonly diagnosed cancer in women worldwide. Radiotherapy is an important part of the treatment for breast cancer, while setting proper number of fields dramatically affects the benefits one can receive. Machine learning and radiomics have been widely investigated in the management of breast cancer. This study aims to provide models to predict the best number of fields based on machine learning and improve the prediction performance by adding clinical factors. Methods: Two-hundred forty-two breast cancer patients were retrospectively enrolled for this study, all of whom received postoperative intensity modulated radiation therapy. The patients were randomized into a training set and a validation set at a ratio of 7:3. Radiomics shape features were extracted for eight machine learning algorithms to predict the number of fields. Univariate and multivariable logistic regression were implemented to screen clinical factors. A combined model of rad-score and clinical factors were finally constructed. The area under receiver operating characteristic curve, precision, recall, F1 measure and accuracy were used to evaluate the model. Results: Random Forest outperformed from eight machine learning algorithms while predicting the number of fields. Prediction performance of the radiomics model was better than the clinical model, while the predictive nomogram combining the rad-score and clinical factors performed the best. Conclusions: The model combining rad-score and clinical factors performed the best. Nomograms constructed from the combined models can be of reliable references for medical dosimetrists.