Abstract #4857

Deep-learned 3D black-blood imaging using automatic labeling technique and 3D convolutional neural networks for detection of metastatic brain tumors

Yohan Jun^1,2, Taejoon Eo¹, Taeseong Kim¹, Hyungseob Shin¹, Dosik Hwang¹, Sohi Bae³, Yaewon Park⁴, Hojoon Lee³, Byoungwook Choi³, and Sungsoo Ahn³

¹Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea, ²Philips Korea, Seoul, Republic of Korea, ³Radiology and Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, Republic of Korea, ⁴Department of Radiology, Ewha Womans University College of Medicine, Seoul, Republic of Korea

Black-blood (BB) imaging has complementary roles in addition to contrast-enhanced 3D gradient-echo (CE 3D-GRE) imaging for detection of brain metastases. We proposed deep-learned 3D BB imaging with an auto-labeling technique and 3D convolutional neural networks (CNNs) for detecting metastatic brain tumors. On deep-learned BB imaging, vessel signals of the brain were effectively suppressed in all patients. According to per lesion analysis, overall sensitivities were 90.3% for deep-learned BB and 100% for original BB. There were eight false positive nodules on original BB and only one on deep-learned BB. Deep-learned 3D BB imaging can be effectively used for detecting metastatic tumors in the brain.

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

Join Here