ABSTRACT
Background: To identify multiparametric magnetic resonance imaging (mp-MRI)-based radiomics features as prognostic factors in patients with localized prostate cancer after radiotherapy. Methods:From 2011 to 2016, a total of 91 consecutive patients with T1-4N0M0 prostate cancer were identified and divided into two cohorts for an adaptive boosting (Adaboost) model (training cohort: n = 73; test cohort: n = 18). All patients were treated with neoadjuvant endocrine therapy followed by radiotherapy. The optimal feature set, identified through an Inception-Resnet v2 network, consisted of a combination of T1, T2, and diffusion-weighted imaging (DWI) MR series. Through a Wilcoxon sign rank test, a total of 45 distinct signatures were extracted from 1,536 radiomics features and used in our Adaboost model. Results:Among 91 patients, 29 (32%) were classified as biochemical recurrence (BCR) and 62 (68%) as non-BCR. Once trained, the model demonstrated a predictive classification accuracy of 50.0 and 86.1% respectively for BCR and non-BCR groups on our test samples. The overall classification accuracy of the test cohort was 74.1%. The highest classification accuracy was 77.8% between three-fold cross-validation. The areas under the curve (AUC) of receiver operating characteristic curve (ROC) indices for the training and test cohorts were 0.99 and 0.73, respectively. Conclusion:The potential of multiparametric MRI-based radiomics to predict the BCR of localized prostate cancer patients was demonstrated in this manuscript. This analysis provided additional prognostic factors based on routine MR images and holds the potential to contribute to precision medicine and inform treatment management.
ABSTRACT
BACKGROUND: Recurrence is the major cause of mortality in patients with resected HCC. However, without a standard approach to evaluate prognosis, it is difficult to select candidates for additional therapy. METHODS: A total of 201 patients with HCC who were followed up for at least 5 years after curative hepatectomy were enrolled in this retrospective, multicentre study. A total of 3144 radiomics features were extracted from preoperative MRI. The random forest method was used for radiomics signature building, and five-fold cross-validation was applied. A radiomics model incorporating the radiomics signature and clinical risk factors was developed. RESULTS: Patients were divided into survivor (n = 97) and non-survivor (n = 104) groups based on the 5-year survival after surgery. The 30 most survival-related radiomics features were selected for the radiomics signature. Preoperative AFP and AST were integrated into the model as independent clinical risk factors. The model demonstrated good calibration and satisfactory discrimination, with a mean AUC of 0.9804 and 0.7578 in the training and validation sets, respectively. CONCLUSIONS: This radiomics model is a valid method to predict 5-year survival in patients with HCC and may be used to identify patients for clinical trials of perioperative therapies and for additional surveillance.
