What does the future hold for artificial intelligence in urology?
On day 3 of EAU22, a Thematic Session on artificial intelligence (AI) gave an enthusiastic insight into the developing opportunities and challenges for urologists in the future with this new method. This evolving topic was chaired by Prof. James N’Dow (GB) and Prof. Kari Tikkinen (FI).
Dr. Michael Bussmann (DE) kicked off the session with his pre-recorded presentation “Basics of explainable artificial intelligence with applications in PCa”. He stated that AI currently mimics human intelligence but to advance, explainable AI needs lots of data to create value. Diverse, big and high-quality data is key to successful AI building, this data needs to be complex and unstructured.
According to Dr. Bussmann, great prospects of explainable AI in PCa include, but are not limited to classification of prostate tumours with MRI, PCa detection, Gleason Score grading, risk stratification, lesion detection, biochemical recurrence, and robotic surgery.
Dr. Bussmann also shed light on the big potential of synthetic data. He gave a synthetic CT generated from MRI data for dose calculation as an example. The idea of creating a synthetic imaging from data, even if it was never in a patient before, is advantageous for research, helping patients understand decisions, or explaining the decision of an AI algorithm.
In his presentation “What explainable artificial intelligence means for urologists now and in the future”?, Prof. Phillipe Lambin (NL) talked about how the future lies with human and machine (AI) collaboration, with an AI-based decision support system and an AI-based treatment delivery.
“AI can make the life of a urologist much easier. For example, what if every medical decision, whether made by an intensivist or a community health worker, was instantly reviewed by a team of relevant experts who provided guidance if the decision seemed amiss?”
According to Prof. Lambin, the role of explainable AI will be to optimise workflow and it will allow for work to be done faster too. Looking to the future, there is a new approach being developed called ‘foundation modelling’ and he expects that by 2030 this new phase of AI will have the characteristics of deep in-content learning at the same power as the human brain.
“My point of view is that AI can facilitate the life of urologists and save lives. The urologist who does not use AI will be replaced by the one who does”, concluded Prof. Lambin.