Abstract #1522

Evaluation of the Substantia Nigra and Locus Coeruleus by Neuromelanin-Sensitive MR Imaging with Deep Learning Based Noise Reduction

Sonoko Oshima¹, Yasutaka Fushimi¹, Satoshi Nakajima¹, Yusuke Yokota¹, Sayo Otani¹, Azusa Sakurama¹, Krishna Pandu Wicaksono¹, Yuichiro Sano², Ryo Matsuda², Masahito Nambu², Koji Fujimoto³, Hitomi Numamoto⁴, Kanae Kawai Miyake⁴, Tsuneo Saga⁴, and Kaori Togashi¹

¹Department of Diagnostic Radiology and Nuclear Medicine, Graduate School of Medicine, Kyoto University, Kyoto, Japan, ²MRI Systems Division, Canon Medical Systems Corporation, Otawara, Japan, ³Human Brain Research Center, Graduate School of Medicine, Kyoto University, Kyoto, Japan, ⁴Department of Advanced Medical Imaging Research, Graduate School of Medicine, Kyoto University, Kyoto, Japan

We assessed neuromelanin-sensitive MR images with number of excitations of 1 or 2 with and without deep learning reconstruction (DLR) denoising method about visualization of the substantia nigra (SN) and locus coeruleus (LC) in 19 patients. The results of visual assessment were better in images with DLR. Contrast ratios of SN did not change after application of DLR, whereas contrast ratios of LC were decreased and hyperintense SN areas became larger. Neuromelanin imaging with DLR has a potential to reduce scan time without spoiling image quality, but further studies are needed for interpreting the signal contrast of SN and LC.

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

Join Here