Prostate cancer is one of the most common tumors in the world. Multi-parameter magnetic resonance imaging (mpMRI) as a non-invasive tool, can improve the detection, classification and volume quantification of prostate lesions. Machine learning is a branch of artificial intelligence (AI). It can quickly and accurately analyze mpMRI images, has good consistency in identifying prostate lesions, and can strengthen the standardized management of prostate cancer. It has become a tool for improving the diagnostic efficiency and accuracy of radiologists. This review summarizes the application of AI in mpMRI of the prostate (mainly including prostate segmentation, lesion detection and segmentation, and lesion feature description) and its development in the future.