Abstract #4397
MRI Based Automated Deep-Learning System in the Assessment of Prostate Cancer: Comparison of Advanced Zoomed DWI and Conventional Technique
Lei Hu1, Caixia Fu2, Robert Grimm3, Heinrich von Busch4, Thomas Benkert 3, and Jun-gong Zhao1
1Department of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People’s Hospital, Shanghai, China, 2MR Application Development, Siemens Shenzhen Magnetic Resonance Ltd, Shenzhen, China, 3MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany, 4Innovation Owner Artificial Intelligence for Oncology, Siemens Healthcare GmbH, Erlangen, Germany
Synopsis
Prostate cancer (PCa) detection by an automated deep-learning computer-aided diagnosis (DL-CAD) system using advanced zoomed diffusion-weighted imaging (z-DWI) and full-field-of-view DWI (f-DWI) were compared. The DL-CAD system using z-DWI performed significantly better for PCa detection accuracy per patient (AUC: 0.937 vs. 0.871; P=0.002) and had significantly higher PCa lesion detection accuracy per lesion compared to f-DWI (AUC: 0.912 vs. 0.833; P=0.003). Given this, use of z-DWI can improve the performance of the DL-CAD system for PCa detection.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
