Deep learning-based PI-RADS score estimation to detect prostate cancer using multiparametric magnetic resonance imaging

Prostate cancer (PCa) is the most common type of cancer among men. Digital rectal examination and prostate-specific antigen (PSA) tests are used to diagnose the PCa accurately. Since PSA is organ-specific and not disease-specific, multiparametric magnetic resonance imaging (mpMRI) is used to reduce unnecessary biopsies. Prostate imaging reporting and data system (PI-RADS) is widely used for mpMRI scoring to detect PCa. There is low-level agreement among interpreters and also subjectivity associated with PI-RADS scoring. Hence, in this study, a hybrid model has been proposed to accurately interpret mpMRI examination and predict PI-RADS scores. In the proposed systems, feature maps of mpMR images were extracted using the MobilenetV2, Efficientnetb0, and Darknet53 architectures. Then, the feature maps obtained using these three architectures were combined. The merged feature maps are subjected to neighborhood components analysis (NCA) to eliminate redundant features. The proposed system provided 96.09% accuracy.

Automated summary

Prostate cancer is the most common cancer among men, and accurate diagnosis is commonly achieved through digital rectal examination and prostate-specific antigen tests. To reduce unnecessary biopsies, multiparametric magnetic resonance imaging (mpMRI) is used. However, there is low-level agreement and subjectivity in the interpretation of mpMRI scores. This study proposes a hybrid model to accurately interpret mpMRI examinations and predict scores, achieving a 96.09% accuracy rate.