Advertisement

FEASIBILITY OF QUANTIFYING AMYLOID BURDEN USING VOLUMETRIC MRI DATA: PRELIMINARY FINDINGS BASED ON THE DEEP LEARNING 3D CONVOLUTIONAL NEURAL NETWORK APPROACH

      Amyloid positron emission tomography (PET) technique has been used to image beta-amyloid (Aβ) for studies of AD. The standard uptake value ratio (SUVr) between a pre-specified mean-cortical target region and the cerebellum (or other) reference region over the amyloid PET image is routinely used as a measure of Aβ burden in the brain. On the other hand, the volumetric magnetic resonance imaging (vMRI) with information on the structural damage presumably caused by the Aβ accumulation could be potentially used to assess Aβ burden. This study examined the feasibility of using 3D convolutional neural network (3D-CNN) to estimate SUVr and to determine Aβ positivity based on only vMRI data.
      To read this article in full you will need to make a payment
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'