Genitourinary

Automated Prostate Lesion Detection

Prostate cancer is the most commonly diagnosed male cancer in the United States.. Multiparametric MRI (mpMRI) is increasingly used for prostate cancer evaluation and biopsy guidance. Prostate organ and lesion segmentation is an important step in pre-biopsy surgical planning. We are developing an AI technology to automate the localization and segmentation of prostates, as well as the detection of prostate lesions. This will allow for clinicians to evaluate and stratify prostate lesions on an MRI in a more accurate manner. Overall, this technology will allow for the best treatment approach for patients with prostate cancer.

Automated Renal Cell Carcinoma (RCC) Detection and Characterization

Cancer of the kidney is the eighth most common cancer, but typically does not present with any symptoms. For this reason, it is often incidentally discovered when radiology imaging is obtained for other purposes. Early work has demonstrated that computational techniques such as AI, may be used to automatically evaluate kidney tumors. We are currently developing an AI clinical pipeline to analyze radiological images and accurately identify and characterize renal cell carcinoma (RCC), as well as predict probability of recurrence. This technology will allow for clinicians to plan the best treatment approach for patients with kidney cancer.