An artificial intelligence (AI) system matched the performance of world-leading uropathologists at identifying and grading prostate cancer, according to a study from the Karolinska Institute and Tampere University.1 Researchers at those institutions developed an AI-based method for histopathological diagnosis and grading of prostate cancer. The AI system has the potential to solve one of the bottlenecks in today’s prostate cancer histopathology by providing more accurate diagnosis and better treatment decisions.

Martin Eklund, PhD, Karolinska Institute.

Martin Eklund, PhD, Karolinska Institute.

“Our results show that it is possible to train an AI system to detect and grade prostate cancer on the same level as leading experts,” says Martin Eklund, PhD, associate professor of medical epidemiology and biostatistics at the Karolinska Institute, and leader of the study. “This has the potential to significantly reduce the workload of uropathologists and allow them to focus on the most difficult cases.”

A problem in today’s prostate pathology is that there is a certain degree of subjectivity in the assessments of the biopsies. Different pathologists can reach different conclusions even though they are studying the same samples. This leads to a clinical problem where the doctors must select a course of treatment based on ambiguous information. In this context, the researchers see significant potential for using AI technology to increase the reproducibility of pathology assessments.


Henrik Grönberg, MD, PhD, Karolinska Institute and Saint Göran Hospital.

To train and test the AI system, the researchers used digital pathology scanners to digitize to high-resolution images more than 8,000 biopsies taken from some 1,200 Swedish men aged 50 to 69. About 6,600 of the samples were used to train the AI system to spot the difference between biopsies with or without cancer. The remaining samples, and additional sets of samples collected from other labs, were used to test the AI system. Results from the system were also compared against the assessments of 23 experienced uropathologists.

The findings showed that the AI system was near-perfect in determining whether a sample contained cancer or not, as well as in estimating the length of the cancer tumor in the biopsy. When it came to determining the severity of the prostate cancer, the so-called Gleason score, the AI system was on par with the international experts.

“When it comes to grading the severity of prostate cancer, the AI is in the same range as international experts, which is very impressive,” says Lars Egevad, MD, PhD, professor of pathology at the Karolinska Institute and coauthor of the study. “And when it comes to diagnostics, to determine whether or not it is cancer, the AI is simply outstanding.”

Photo EgevadLars-crop640x640

Lars Egevad, MD, PhD, Karolinska Institute.

According to the researchers, the initial findings are promising, but more validation is needed before the AI system may be rolled out broadly in clinical practice. A multicenter study spanning nine European countries is currently underway to train the AI-system to recognize cancer in biopsies taken from different laboratories, with different types of digital scanners, and with very rare growth patterns. That study is slated to be complete by the end of 2020. In addition, a randomized study starting in 2020 will examine how the AI model may be implemented in Sweden’s healthcare system.

Screen Shot 2020-02-26 at 5.22.39 PM“AI-based evaluation of prostate cancer biopsies could revolutionize future healthcare,” says Henrik Grönberg, MD, PhD, professor of cancer epidemiology at the Karolinska Institute and head of the prostate cancer center at Saint Göran Hospital. “It has the potential to improve diagnostic quality, and thereby secure a more equitable care at a lower cost.”

“The idea is not that AI should replace the human involvement, but rather act as a safety net to ensure that pathologists don’t miss some cancers, and assist in standardization of grading,” says Eklund. “It could also serve as an alternative in parts of the world where there is a complete lack of pathological expertise today.”


  1. Ström P, Kartasalo K, Olsson H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020;21(2):222–232; doi: 10.1016/s1470-2045(19)30738-7.

Featured image:

Prostate cancer of a human, highly detailed segment of panorama. Microphotograph as seen under the microscope, 10x zoom. Image © Viachaslau Bondarau, courtesy Dreamstime (ID 66313424).