Abstract:
Recent studies suggest that combined analysis of Magnetic
resonance imaging (MRI) that measures brain atrophy and positron
emission tomography (PET) that quanti es hypo-metabolism provides
improved accuracy in diagnosing Alzheimer's disease. However, such techniques
are limited by the availability of corresponding scans of each
modality. Current work focuses on a cross-modal approach to estimate
FDG-PET scans for the given MR scans using a 3D U-Net architecture.
The use of the complete MR image instead of a local patch based approach
helps in capturing non-local and non-linear correlations between
MRI and PET modalities. The quality of the estimated PET scans is
measured using quantitative metrics such as MAE, PSNR and SSIM. The
efficacy of the proposed method is evaluated in the context of Alzheimer's
disease classi cation. The accuracy using only MRI is 70.18% while joint
classi cation using synthesized PET and MRI is 74.43% with a p-value of
0:06. The signi cant improvement in diagnosis demonstrates the utility
of the synthesized PET scans for multi-modal analysis.
