Abstract
Summary This review summarizes and provides an outlook for developments around the use of artificial intelligence (AI) in the diagnosis and treatment of prostate cancer. We searched existing literature on the design and development of new AI-based systems using a non-systematic approach. Areas targeted by AI include the diagnosis, Gleason scoring, biomarker identification, and prognosis of prostate cancer (PCa) from digitised histopathology, segmentation, detection, and classification of PCa from magnetic resonance imaging, AI applications for prostate ultrasound, AI in radiotherapy for PCa including synthetic computed tomography generation and treatment planning and AI in measuring and improving surgical outcomes and education. Recent work has focused on deep learning techniques. Algorithms have achieved results that outperform or are similar to those of experts. However, few proposed algorithms are clinically oriented and can be practically deployed. Future progress needs to be made in data availability, prospective evaluation, regulation, responsible AI, explainability, and practical aspects of clinical deployment.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
