Meeting Banner
Abstract #0775

Predictive Cytological Topography (PiCT): a Radio-Pathomics Approach to Mapping Prostate Cancer

Sean D McGarry1, Sarah L Hurrell2, Kenneth A Iczkowski3, Amy Kaczmarowski2, Anjishnu Banerjee4, Tucker Keuter4, Kenneth Jacobsohn5, William Hall6, Marja Nevalainen3, Mark Hohenwalter2, William See5, Andrew Nencka2, and Peter LaViolette2

1Biophysics, Medical College of Wisconsin, Wawautosa, WI, United States, 2Radiology, Medical College of Wisconsin, Wawautosa, WI, United States, 3Pathology, Medical College of Wisconsin, Wawautosa, WI, United States, 4Biostatistics, Medical College of Wisconsin, Wawautosa, WI, United States, 5Urologic Surgery, Medical College of Wisconsin, Wawautosa, WI, United States, 6Radiation Oncology, Medical College of Wisconsin, Wawautosa, WI, United States

We present a machine learning technique for mapping prostate cancer cellular features into MRI space. 39 patients were prospectively recruited for imaging prior to prostaectomy. Tissue was aligned with the MRI using a non-linear control point warping technique. Pathologist annotations were likewise transformed into MRI space. A partial least squares regression (PLS) algorithm was trained on two sets of 10 patients and applied to 19 test patients, using MRI values as the input to predict epithelial and lumen density. The output maps are new interpretable image contrasts predictive of prostate cancer presence.

This abstract and the presentation materials are available to members only; a login is required.

Join Here