Meeting Banner
Abstract #0317

On the linearity of deep neural network trained QSM

Woojin Jung1, Jaeyeon Yoon1, Joon Yul Choi1, Eung-Yeop Kim2, and Jongho Lee1

1Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea, Republic of, 2Department of Radiology, Gachon University, Incheon, Korea, Republic of

In this work, the linearity property of a recently proposed neural network-based QSM is explored. The QSMnet, which was trained using healthy volunteers, was quantitatively evaluated for patients with hemorrhage whose susceptibility values were outside of the trained range. The results showed that the QSMnet underestimated the susceptibility in hemorrhage, breaking linearity between true susceptibility and QSMnet-generated susceptibility. To overcome this limitation, we developed a linear scaling method that generalized the network for a wider range of susceptibility. The new network successfully reconstructed the patient data with good linearity results.

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

Join Here