Meeting Banner
Abstract #1125

Deep Learning Based Mask Generation Tools for QSM

Gawon Lee1, Ji Wan Son1, Ken SaKaie2, Woojin Jung3, and Se-hong Oh1,2
1Division of Biomedical engineering, Hankuk University of Foreign Studies, Yongin-si, Gyeonggi-do, Korea, Republic of, 2Imaging institute, Cleveland Clinic Foundation, Cleveland, OH, United States, 3AIRS Medical, Seoul, Korea, Republic of


Even subtle differences in masks can generate systematic but avoidable errors in QSM calculations. We believe these errors propagate through the calculation of the background phase. In this work, we assessed the effect of the mask on the QSM, selected optimal mask generation method and Deep Learning-based efficient mask generation method for in-vivo has been presented. This study represents the first step towards a fully-automated and optimal workflow for QSM calculation.

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

Join Here