Innovative AI Tool Uses Digitized Whole-Slide Images for Intermediate-Risk Prostate Cancer Management

By LabMedica International staff writers
Posted on 24 Sep 2024

Prostate cancer estimates for the United States in 2024 include approximately 299,010 new cases and about 35,250 deaths. Among patients in the intermediate-risk group, around 60% lack a clear treatment plan, and 30 to 50% experience cancer progression after the initial therapy. Early identification of patients at higher risk of rapid disease progression is critical for improving outcomes. Recent advances in artificial intelligence (AI), particularly in deep learning, have accelerated the development of new technologies that use medical images to predict diseases more accurately. Researchers have now developed an AI-powered tool to enhance the management and prognosis of prostate cancer.

The tool, called PATHOMIQ_PRAD, was created by researchers at the Icahn School of Medicine at Mount Sinai (New York, NY, USA) in partnership with PathomIQ, Inc. (Cupertino, CA, USA). It focuses on intermediate-risk prostate cancer patients and utilizes deep learning to extract morphological features from datasets based on biopsy or surgical hematoxylin- and eosin-stained whole-slide images. The tool helps identify patients at higher risk of rapid disease progression and aims to provide more accurate predictions for earlier intervention, leading to more targeted and personalized treatment plans. PATHOMIQ_PRAD scores range from 0 to 1, with higher scores signifying high-risk features. The study used large datasets to classify patients into high- and low-risk groups based on pre-set clinical cutoffs of 0.45 for biochemical recurrence (BCR) and 0.55 for metastasis, which were determined by factors such as the likelihood of cancer recurrence or spread.

Image: A cluster map of different prostate cancer patterns detected by the AI tool PATHOMIQ_PRAD from stained tissue images (Photo courtesy of Nair, et al. (2024), European Urology)

The findings reported in the online issue of European Urology show that PATHOMIQ_PRAD outperformed existing benchmark cancer outcome tools in predicting five-year outcomes. The researchers plan to conduct large-scale clinical validation studies with a more diverse patient population. They are also pursuing regulatory approval to develop PATHOMIQ_PRAD as a Lab Developed Test, making it available in CLIA-certified labs. Furthermore, the team is working to integrate the tool with advanced genomic profiling methods, including spatial transcriptomics and mass cytometry, to deepen the understanding of the biological factors behind the regions identified by PATHOMIQ_PRAD.

“By analyzing various tissue types—epithelial, stromal, and immune cells—it generates a detailed score for each patient, predicting outcomes and offering a powerful new way to guide treatment decisions,” said Dimple Chakravarty, PhD, Assistant Professor of Urology at Icahn Mount Sinai. “Ours is the first AI tool designed specifically for intermediate-risk prostate cancer patients that is both scalable and generalizable. It can be used for risk stratification from biopsy and surgery specimens. It’s affordable, quick, and adaptable for use in various healthcare settings.