Meeting Banner
Abstract #0704

A Comparison between Radiologists versus Deep Learning for Prostate Cancer Detection in Multi-parameter MRI

Ruiming Cao1, Xinran Zhong2, Sohrab Afshari Mirak3, Ely Felker3, Voraparee Suvannarerg3,4, Teeravut Tubtawee3,5, Fabien Scalzo6, Steve Raman3, and Kyunghyun Sung3
1Bioengineering, UC Berkeley, Berkeley, CA, United States, 2UT Southwestern, Dallas, TX, United States, 3Radiology, UCLA, Los Angeles, CA, United States, 4Radiology, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand, 5Radiology, Faculty of Medicine, Prince of Songkla University, Songkhla, Thailand, 6Computer Science, UCLA, Los Angeles, CA, United States

We evaluated our recently developed deep learning system, FocalNet, for prostate cancer detection in multi-parametric MRI (mpMRI). This study performed a head-to-head comparison between FocalNet and four genitourinary radiologists in an independent evaluation cohort consisting of 126 mpMRI scans untouched during the development. FocalNet demonstrated similar detection performance to radiologists under the high specificity condition or the high sensitivity condition, while radiologists outperformed FocalNet in moderate specificity and sensitivity.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here