AI-enhanced radiology
detection, reporting
and clinical decision-making
in prostate cancer diagnosis

The National Information Processing Institute (OPI) has received funding to develop an innovative platform that facilitates prostate cancer diagnosis. The cutting-edge tool will rely on artificial intelligence (AI) to assist medical experts in implementing the most optimal therapies.

Prostate cancer is a growing medical and social issue. The most popular diagnostic methods include medical imaging and, in particular, multi-parametric magnetic resonance imaging (mpMRI). The evaluation of mpMRI scans is a complex and multifaceted task in which the quality of reporting of lesions and communication between radiologists and clinicians play key roles in implementing suitable diagnosis and treatment plans. With staff shortages among radiologists and the long training necessary to become an experienced specialist capable of properly evaluating mpMRI results, the use of modern technologies to improve radiologists’ cognitive abilities and to facilitate specialists’ tasks is of utmost importance.

The primary goal of the project is to create a system that reports prostate cancer mpMRI scans; one that is developed on the basis of integration of standardised structural reports and trained machine learning methods that analyse mpMRI scans—a highly innovative concept. The results of the image analyses will be used to support radiologists in various aspects of their work. These will include automatic measurement of the size and calculation of the volume of prostate glands, creation of visual cues regarding the locations of suspicious lesions, evaluation of the clinical relevance of identified lesions on the PI-RADS scale, automatic pre-filling of fields in template reports, and searching for similar cases.

The project’s results will be made available via an e-learning platform that will train its users how to structurally report prostate mpMRI scans according to PI-RADS using a dedicated reporting system. Educational resources will be provided by an integrated reference base of imaging data that contains an extensive set of thoroughly-described cases and full medical documentation. Both the database and the tasks related to medical aspects will be developed alongside the Lower Silesian Oncology Center in Wroclaw, Poland.