Abstract #3405

Prostate Cancer Localization Using Multi-Parametric MRI and a Maximum Likelihood Classification Algorithm

Sharon Clarke¹, Bruce Daniel², Jesse McKenney³, Manojkumar Saranathan², Brian Andrew Hargreaves², James Brooks⁴, Harachan Gill⁴, Mark Gonzalgo⁴, Benjamin Chung⁴, Emine U. Saritas⁵, Ajit Shankaranarayanan⁶, Graham Sommer²

¹Diagnostic Radiology, Dalhousie University, Halifax, Nova Scotia, Canada; ²Diagnostic Radiology, Stanford University, Stanford, CA, United States; ³Anatomic Pathology, Cleveland Clinic, Cleveland, OH, United States; ⁴Urology, Stanford University, Stanford, CA, United States; ⁵Bioengineering, University of California Berkeley, Berkeley, CA, United States; ⁶GE Healthcare, Menlo Park, CA, United States

Segmentation of multi-parametric MR images of the prostate gland using a maximum likelihood classification algorithm correlate well with histopathology. These results show promise for identification of clinically relevant prostate cancer for either MR-guided biopsy or focal therapy.