Abstract #0051

Exploring generalization capacity of artificial neural network for myelin water imaging

Jieun Lee¹, Joon Yul Choi², Dongmyung Shin¹, Se-Hong Oh³, and Jongho Lee¹

¹Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea, Republic of, ²Cleveland Clinic, Epilepsy Center, Neurological Institute, Cleveland, OH, United States, ³Division of Biomedical Engineering, Hankuk University of Foreign Studies, Gyeonggi-do, Republic of Korea

In this study, the generalization capacity of the artificial neural network for myelin water imaging (ANN-MWI) is explored by testing datasets with different (1) scan protocols (resolution, RF shape, and TE), (2) noise levels, and (3) types of disorders (NMO and edema). The ANN-MWI results show high reliability in generating myelin water fraction maps from the datasets with different resolution and noise levels. However, the increased errors are reported for the datasets with the different RF shape, TEs, and disorder type.

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

Join Here