Evaluating the Feasibility of AI-Predicted mpMRI Image Features for Predicting Prostate Cancer Aggressiveness: a Multicenter Study

Abstract Objective To evaluate the feasibility of utilizing artificial intelligence (AI)-predicted multiparametric MRI (mpMRI) image features for predicting the aggressiveness of prostate cancer (PCa). Materials and methods A total of 878 PCa patients from 4 hospitals were retrospectively collected, all of whom had pathological results after radical prostatectomy(RP).A pre-trained AI algorithm was used to select suspected PCa lesions and extract lesion features for model development. The study evaluated five prediction methods, including 1) A clinical model of clinical features and image features of suspected PCa lesions selected by AI algorithm, 2)the PIRADS category, 3)a conventional radiomics model, 4) a radiomics model based on deep learning, 5)biopsy pathology. Results In the externally validated dataset, the deep learn-based radiomics model showed the highest area under the curve (AUC 0.700 to 0.791).It exceeded clinical model (AUC 0.597 to 0.718), traditional radiomic model (AUC 0.566 to 0.632), PIRADS score (AUC 0.554 to 0.613) and biopsy pathology (AUC 0.537 to 0.578). And the AUC predicted by the model did not show statistically significant difference among the three externally verified hospitals (P > 0.05). Conclusion Deep-radiomics models utilizing AI-extracted image features from mpMRI images can potentially be used to predict PCa aggressiveness, demonstrating a generalized ability for external validation.