Abstract #4373

Diagnosis of Prostate Cancer using MRI derived quantitative Risk Maps

Aritrick Chatterjee¹, Dianning He^1,2, Xiaobing Fan¹, Tatjana Antic³, Ajit Devaraj⁴, Yulei Jiang ¹, Gregory S Karczmar¹, and Aytekin Oto¹

¹Department of Radiology, University of Chicago, Chicago, IL, United States, ²Sino-Dutch Biomedical and Information Engineering School, Northeastern University, Shenyang, China, ³Department of Pathology, University of Chicago, Chicago, IL, United States, ⁴Philips Research North America, Cambridge, MA, United States

This study develops a new tool that estimates the risk map for prostate cancer using quantitative mpMRI metrics and investigates the feasibility of this tool in screening for PCa. Quantitative mpMRI parameters: ADC, T2 and DCE signal enchantment values were calculated and subsequently cancer presence was predicted based on estimated risk scores. The sensitivity, specificity, positive predictive value and negative predictive value for PCa detection using a sector based analysis were 75.0%, 88.6%, 84.7% and 80.8% respectively. The area under the curve in ROC analysis was 0.818. Importantly, all the index lesions were identified by the risk map tool.

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

Join Here