317 Background: Multiparametric magnetic resonance imaging (mpMRI)-derived radiomic features have been shown to capture sub-visual patterns for quantitative characterization of tumor phenotypes in prostate cancer (PC) patients. The present study seeks to develop, test, and validate a mpMRI-derived radiomic model for predicting PC recurrence following initial treatment. Methods: mpMRI was obtained from 76 patients who had undergone radical prostatectomy for treatment of localized PC. All patients had >2 years follow-up with monitoring via prostate specific antigen (PSA). Patients with neo-adjuvant/adjuvant treatment were excluded. Regions of interest were manually delineated on each mpMRI and radiomics features were extracted. Stability on histogram matching was assessed via interclass correlation coefficients (ICC) and a pre-established feature selection pipeline excluded redundant features. The most important and non-redundant features were then aggregated into a radiomic model against a primary outcome of PC recurrence. Patients were randomly split 3 to 1 to training and validation datasets and the training dataset was used to iteratively train and test the best parameters for a Random Forest predictive model. The model with the best parameters as determined by receiver-operator curve (ROC) analysis was then applied to the validation set. ROC analysis was conducted and sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were reported. Results: Clinicodemographic of the 76 patients included in analysis are displayed in Table. 924 radiomic features were initially extracted and 75 (8.1%) features were determined to be stable and robust following histogram matching. Based on the figure selection pipeline, six features were determined to be important and non-redundant. These features were iteratively tested in the training dataset (n=56) and the model with the best parameters yielded a mean ROC with area under the curve (AUC) of 0.95 ± 0.06. After application to validation dataset (n=20), the model yielded an AUC of 0.67. Sensitivity, specificity, PPV, and NPV were 33%, 100%, 40% and 100%, respectively. Conclusions: Radiomic analysis of 76 PC patients yielded six mpMRI-derived radiomic features significantly correlated with PC recurrence following primary treatment. When aggregated and applied to a validation dataset, the final radiomic model yielded 100% specificity in predicting PC recurrence. These findings represent excellent potential for the development of a radiomic-based diagnostic tool with high positive predictive value in identifying patients at high-risk for PC recurrence at time of initial PC diagnosis. Future projects will seek to incorporate patient demographics and disease characteristics to further improve model sensitivity and validation of this model will be pursued with an external cohort of patients.[Table: see text]
The development of precise medical imaging has facilitated the establishment of radiomics, a computer-based method of quantitatively analyzing subvisual imaging characteristics. The present review summarizes the current literature on the use of diagnostic magnetic resonance imaging (MRI)-derived radiomics in prostate cancer (PCa) risk stratification. A stepwise literature search of publications from 2017 to 2022 was performed. Of 218 articles on MRI-derived prostate radiomics, 33 (15.1%) generated models for PCa risk stratification. Prediction of Gleason score (GS), adverse pathology, postsurgical recurrence, and postradiation failure were the primary endpoints in 15 (45.5%), 11 (33.3%), 4 (12.1%), and 3 (9.1%) studies. In predicting GS and adverse pathology, radiomic models differentiated well, with receiver operator characteristic area under the curve (ROC-AUC) values of 0.50–0.92 and 0.60–0.92, respectively. For studies predicting post-treatment recurrence or failure, ROC-AUC for radiomic models ranged from 0.73 to 0.99 in postsurgical and radiation cohorts. Finally, of the 33 studies, 7 (21.2%) included external validation. Overall, most investigations showed good to excellent prediction of GS and adverse pathology with MRI-derived radiomic features. Direct prediction of treatment outcomes, however, is an ongoing investigation. As these studies mature and reach potential for clinical integration, concerted effort to validate these radiomic models must be undertaken.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.