Predictive Model for Post Surgery Prostate Cancer Recurrence

Application

An artificial intelligence based prognostic model for early Biochemical recurrence (BCR) risk assessment of men post-radical prostatectomy.

Key Benefits

• Identifies significant features, including tumor-infiltrating lymphocytes (TIL), in prostate cancer recurrence.

Market Summary

Prostate cancer is one of the most diagnosed cancers in the US, of which 1 in 8 US men will be diagnosed with prostate cancer at some point in their lives. Although prostatectomy is effective to remove cancerous tissue, biochemical recurrence (BCR) of prostate antigens post-surgery elevates risk for metastasis and subsequent mortality. The ability to identify early risk of BCR has potential to identify patients for preventative therapy, thereby reducing the risk for prostate cancer-related deaths.

Technical Summary

This invention is an artificial intelligence-based computational pathology model that extracts features relating to both glandular morphology and spatial architecture of tumor-infiltrating lymphocytes (TIL) from images of post-prostatectomy patients. This platform generates 16 features and successfully identifies those associated with prostate glandular lumina and TILs.

Development Stage

• This invention employed two cohorts of radial-prostatectomy (RP) specimens, dubbed S1 & S2.
• S1 training set comprised 170 patients, and S2 comprised of 171 patients.

Publication Leo, P., Janowczyk, A., Elliott, R., Janaki, N., Bera, K., Shiradkar, R., . . . Madabhushi, A. (2021). Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study. npj Precision Oncology, 5(1), 35. doi:10.1038/s41698-021-00174-3