MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer's Classification

TL;DR

This paper presents a 3D U-Net based method to synthesize FDG-PET scans from MRI images, enabling improved Alzheimer's disease diagnosis when PET scans are unavailable.

Contribution

It introduces a cross-modal synthesis approach using full MRI images with a 3D U-Net, capturing complex correlations for better PET estimation and disease classification.

Findings

Synthesized PET scans achieved high quality metrics (MAE, PSNR, SSIM).

Joint MRI and synthesized PET classification improved accuracy from 70.18% to 74.43%.

The method demonstrates potential for multi-modal Alzheimer's diagnosis.

Abstract

Recent studies suggest that combined analysis of Magnetic resonance imaging~(MRI) that measures brain atrophy and positron emission tomography~(PET) that quantifies 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 classification. The accuracy using only MRI is 70.18% while joint classification using synthesized PET and MRI is 74.43% with a p-value of $0.06$. The significant improvement in diagnosis demonstrates the utility of the synthesized PET scans for multi-modal analysis.