Artificial intelligence tools for radiology, clinical laboratory, and pathology diagnostics continue to advance and improve
Researchers in Germany have developed a fully automated, artificial intelligence (AI) tool that improves the diagnosis of prostate cancer. Developed by mediaire, a company that creates AI-based tools for radiologists, the software reduces clinical workloads and could be beneficial in counteracting issues associated with variability in magnetic resonance imaging (MRI) reporting. This is another example of AI’s growth in the clinical diagnostic industry, including clinical laboratory and pathology medicine.
The software, called mdprostate, has received the mandatory certification mark (CE or European Conformity) for products sold within the European Economic Area (EEA). It is now commercially available in those countries and was recently incorporated into the picture archiving and communications system (PACS) of some healthcare organizations and applied to a group of patients who had undergone a multiparametric prostate MRI (mpMRI).
The goal was to compare the overall performance of mdprostate against radiologists who executed the initial interpretations of the mpMRIs, according to Health Imaging.
“Mdprostate is intended to support radiologists by automating time-consuming processes and improving the objectivity of diagnosis through data quantification,” said Tonia Michaely, chief of staff at mediaire, in a news release.
The researchers published their findings in the European Journal of Radiology titled, “Assessment of a Fully Automated Diagnostic AI Software in Prostate MRI: Clinical Evaluation and Histopathological Correlation.”
“By providing objective assessments and standardizing lesion detection and classification, AI has the potential to augment radiologists’ performance throughout the PCa [prostate cancer] diagnostic pathway,” Nadine Bayerl, Dr. med., a radiologist with the Institute of Radiology at University Hospital Erlangen and corresponding author of the mediaire study, told Health Imaging. (Photo copyright: University Hospital Erlangen.)
Scoring Cancer Risk
To perform the comparison, a team of researchers applied the AI tool to 123 prostate MRI exams followed by systematic and targeted biopsies. The software was instructed to automatically segment the prostrate, calculate prostate volume, and classify lesions per the Prostate Imaging Reporting and Data System (PI-RADS).
PI-RADS, according to the America College of Radiology, is a reporting method that indicates how likely a lesion is to be clinically significant cancer on a score of one to five:
- PI-RADS 1: very low (clinically significant cancer is highly unlikely to be present).
- PI-RADS 2: low (clinically significant cancer is unlikely to be present).
- PI-RADS 3: intermediate (the presence of clinically significant cancer is equivocal).
- PI-RADS 4: high (clinically significant cancer is likely to be present).
- PI-RADS 5: very high (clinically significant cancer is highly likely to be present).
For PI-RADS scores greater than two, mdprostate generated 100% sensitivity and dismissed all cancers for lesions that were below that threshold. For PI-RADS scores of four or higher, the AI tool yielded 85.5% sensitivity and specificity of 63.2% for clinically significant cancers.
Deep Learning in Diagnostic Pathway
“In practical terms, these results indicate that when a case falls below the PI-RADS ≥ 2 cutoff, clinicians can rule out malignancy with a high degree of confidence,” the authors explained in the European Journal of Radiology. “This capability is particularly valuable in clinical decision-making, as it allows for the safe avoidance of unnecessary biopsies or further invasive procedures in these patients.”
“Recent advances in deep learning algorithms, facilitated by larger labeled datasets, improved computing hardware, and refined training techniques, have led to several studies highlighting the diagnostic value of deep learning algorithms in prostate imaging,” radiologist Nadine Bayerl, Dr. med., Institute of Radiology at University Hospital Erlangen and corresponding author of the study, told Health Imaging.
The software “demonstrated high diagnostic performance in identifying and grading prostate lesions, with results comparable to those reported in meta-analyses of expert readers using PI-RADS,” the researchers noted in their published study.
“Its ability to standardize evaluations and potentially reduce variability underscores its potential as a valuable adjunct in the prostate cancer diagnostic pathway. The high accuracy of mdprostate, particularly in ruling out prostate cancers, highlights its clinical utility by reducing workload and enhancing patient outcomes,” they concluded.
AI in Clinical Laboratories and Pathology
Dark Daily has frequently covered AI’s expanding role in clinical laboratory testing and pathology diagnostics. At the recent Executive War College, a dozen sessions explored its growth in the industry. During one session, Sam Terese, CEO and president at Alverno Laboratories said, “AI is allowing us to drive our business. It is really resonating that we need to use AI in the future.”
Members who could not attend the 2025 Executive War College can order audio recordings of these valuable sessions by clicking here.
—JP Schlingman