MR fingerprinting and complex-valued neural network for quantification of brain amyloid burden
Shohei Fujita1,2, Yujiro Otsuka1,3,4, Katsutoshi Murata5, Gregor Koerzdoerfer6, Mathias Nittka6, Yumiko Motoi7,8, Madoka Nakajima8,9, Koji Murakami10, Issei Fukunaga1, Koji Kamagata1, Osamu Abe2, and Shigeki Aoki1
1Department of Radiology, Juntendo University, Tokyo, Japan, 2Department of Radiology, The University of Tokyo, Tokyo, Japan, 3Milliman Inc, Tokyo, Japan, 4Plusman LLC, Tokyo, Japan, 5Siemens Healthcare Japan KK, Tokyo, Japan, 6Siemens Healthcare GmbH, Erlangen, Germany, 7Department of Neurology, Juntendo University, Tokyo, Japan, 8Medical Center for Dementia, Juntendo University, Tokyo, Japan, 9Department of Neurosurgery, Juntendo University, Tokyo, Japan, 10Division of Nuclear Medicine, Department of Radiology, Juntendo University, Tokyo, Japan
We developed a framework utilizing MR fingerprinting and a complex-valued neural network to detect brain amyloid burden. The tailored neural network was trained on real amyloid-PET imaging data and MR fingerprinting acquisitions to estimate PET-derived amyloid deposition from the MR fingerprinting signal evolutions. This complex-valued neural network architecture, designed to increase sensitivity to amyloid-related signals, showed a subject-level amyloid positivity classification with AUC = 0.87 in patients with cognitive decline. The proposed method enables non-invasive amyloid burden mapping, T1 and T2 mapping in a single scan, and is suitable not only for diagnosis but also for monitoring amyloid-reducing treatments.
This abstract and the presentation materials are available to members only;
a login is required.