Using an AI System to Diagnose Prostate Cancer
Tue, April 20, 2021

Using an AI System to Diagnose Prostate Cancer

New AI system offers to help for better diagnosis and treatment of prostate cancer / Credits: belchonock via 123RF

 

Prostate cancer has been reported as the second cause of cancer-related deaths in men. Reports show that 1 in 7 men in Europe and the US are diagnosed with prostate cancer in their lifetime. Currently, men have to undergo imaging to diagnose the illness, which needs to be confirmed by biopsy. But, artificial intelligence offers to help for better diagnosis and treatment of prostate cancer. 

Recently, a team led by Karolinska Institutet in Sweden developed a deep learning system that is better at determining the aggressiveness of prostate cancer. The researchers are part of the same team who developed Stockholm3 and OncoWatch, two projects supported by EIT Health. These projects doubled the identified number of aggressive cancers, while also reduced the number of unnecessary biopsies by 50%.

According to Imaging Technology News (ITN), an online site that reaches more than 34,000 radiology, radiation oncology, women's health, and nuclear medicine professionals, the new AI system taught itself to identify prostate cancer based on data from over 1,200 patients. It can examine a patient the same way a pathologist does but with better accuracy. The system works by examining thousands of images of biopsies to learn what a healthy prostate is as well as what more or less aggressive prostate cancer tissue looks like. 

Researcher Wouter Bulten stated that the AI system had been trained with 5,759 biopsies from more than 1,200 patients. “When we compared the performance of the algorithm with that of 15 pathologists from various countries and with differing levels of experience, our system performed better than ten of them and was comparable to highly experienced pathologists,” he said. 

According to EIT Health, a network of best-in-class health innovators backed by the EU that delivers solutions to enable European citizens to live longer, healthier lives, Martin Eklund, Associate Professor at the Department of Medical Epidemiology and Biostatistics at Karolinska Institutet, stated that the AI tool has the potential to reduce the workload of uropathologists. This would allow them to focus on the most difficult cases, while also improving quality.