Meeting Banner
Abstract #1997

Unsupervised anomaly detection using generative adversarial networks in 1H-MRS of the brain

Joon Jang1, Hyeong Hun Lee1, Ji-Ae Park2, and Hyeonjin Kim3,4
1Department of Biomedical Sciences, Seoul National University, Seoul, Korea, Republic of, 2Division of Applied RI, Korea Institute of Radiological & Medical Science, Seoul, Korea, Republic of, 3Department of Medical Sciences, Seoul National University, Seoul, Korea, Republic of, 4Department of Radiology, Seoul National University Hospital, Seoul, Korea, Republic of

The applicability of generative adversarial networks (GANs) capable of unsupervised anomaly detection (AnoGAN) was investigated in the management of quality of 1H-MRS human brain spectra. The AnoGAN showed potential in the detection of the spectra with poor SNR or abnormal NAA levels. Despite the fact that those spectra contaminated with ghost, residual water or lipid have never been involved in the training or optimization of the AnoGAN, they were successfully filtered out depending on the intensity of the artifacts. Our unsupervised learning-based approach could be an option in the spectral quality management in addition to the previous supervised learning-based approaches.

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

Join Here