MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Disease

08/04/2021
by   Apoorva Sikka, et al.
12

Medical imaging datasets are inherently high dimensional with large variability and low sample sizes that limit the effectiveness of deep learning algorithms. Recently, generative adversarial networks (GANs) with the ability to synthesize realist images have shown great potential as an alternative to standard data augmentation techniques. Our work focuses on cross-modality synthesis of fluorodeoxyglucose (FDG) Positron Emission Tomography (PET) scans from structural Magnetic Resonance (MR) images using generative models to facilitate multi-modal diagnosis of Alzheimer's disease (AD). Specifically, we propose a novel end-to-end, globally and locally aware image-to-image translation GAN (GLA-GAN) with a multi-path architecture that enforces both global structural integrity and fidelity to local details. We further supplement the standard adversarial loss with voxel-level intensity, multi-scale structural similarity (MS-SSIM) and region-of-interest (ROI) based loss components that reduce reconstruction error, enforce structural consistency at different scales and perceive variation in regional sensitivity to AD respectively. Experimental results demonstrate that our GLA-GAN not only generates synthesized FDG-PET scans with enhanced image quality but also superior clinical utility in improving AD diagnosis compared to state-of-the-art models. Finally, we attempt to interpret some of the internal units of the GAN that are closely related to this specific cross-modality generation task.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

page 9

page 10

research
08/10/2020

GANDALF: Generative Adversarial Networks with Discriminator-Adaptive Loss Fine-tuning for Alzheimer's Disease Diagnosis from MRI

Positron Emission Tomography (PET) is now regarded as the gold standard ...
research
06/20/2018

Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT

In medical imaging, a general problem is that it is costly and time cons...
research
09/12/2021

Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network

Frontotemporal dementia and Alzheimer's disease are two common forms of ...
research
11/29/2021

Data Augmentation For Medical MR Image Using Generative Adversarial Networks

Computer-assisted diagnosis (CAD) based on deep learning has become a cr...
research
09/15/2023

Cross-Modal Synthesis of Structural MRI and Functional Connectivity Networks via Conditional ViT-GANs

The cross-modal synthesis between structural magnetic resonance imaging ...
research
02/21/2022

Outlier-based Autism Detection using Longitudinal Structural MRI

Diagnosis of Autism Spectrum Disorder (ASD) using clinical evaluation (c...
research
11/25/2021

Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN

The diagnosis of early stages of Alzheimer's disease (AD) is essential f...

Please sign up or login with your details

Forgot password? Click here to reset