Abstract #0381

Radio-pathomic maps of histo-morphometric features trained with whole mount prostate histology distinguish prostate cancer on MP-MRI

Savannah Rae Duenweg¹, Samuel A Bobholz¹, Allison K Lowman¹, Aleksandra Winiarz², Biprojit Nath², Benjamin Chao², Stephanie Vincent-Sheldon¹, Kathleen Bhatt¹, Leela Chaudhary¹, Katherine Troy¹, Kenneth A Iczkowski^3,4, Kenneth M Jacobsohn⁵, and Peter S LaViolette^1,2,6

¹Radiology, Medical College of Wisconsin, Wauwatosa, WI, United States, ²Biophysics, Medical College of Wisconsin, Wauwatosa, WI, United States, ³Pathology and Laboratory Medicine, University of California – Davis, Davis, CA, United States, ⁴Urologic Surgery, University of California – Davis, Davis, CA, United States, ⁵Urology, Medical College of Wisconsin, Wauwatosa, WI, United States, ⁶Biomedical Engineering, Medical College of Wisconsin, Wauwatosa, WI, United States

Synopsis

Keywords: Prostate, Prostate, Radio-pathomics; Histo-morphometric features; Cancer; Prostate Cancer

Motivation: Prostate cancer is the most common male cancer in the U.S. MP-MRI is effective at aiding diagnosis, however, it may yield false positive results or miss small lesions.

Goal(s): This study used MP-MRI intensities as input to machine learning models to create radio-pathomic maps of prostate cancer.

Approach: This study analyzed 236 prostate cancer patients' pre-surgical MRI and histology data to develop tumor detection models. Images were processed, segmenting tissue features. Custom software co-registered MRI and histology, and models were trained to predict cancer.

Results: Histological feature models performed within one standard deviation of ground truth, while classification models achieved ~80% prediction accuracy.

Impact: This innovative approach uses radio-pathomic mapping for non-invasive prostate cancer detection, offering a quantitative alternative to PI-RADS scoring, enhanced cancer localization, and potentially improving diagnosis, grading, and treatment planning for prostate cancer patients.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.