English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Medical imaging datasets are inherently high dimensional with largevariability and low sample sizes that limit the effectiveness of deep learningalgorithms. Recently, generative adversarial networks (GANs) with the abilityto synthesize realist images have shown great potential as an alternative tostandard data augmentation techniques. Our work focuses on cross-modalitysynthesis of fluorodeoxyglucose~(FDG) Positron Emission Tomography~(PET) scansfrom structural Magnetic Resonance~(MR) images using generative models tofacilitate multi-modal diagnosis of Alzheimer's disease (AD). Specifically, wepropose a novel end-to-end, globally and locally aware image-to-imagetranslation GAN (GLA-GAN) with a multi-path architecture that enforces bothglobal structural integrity and fidelity to local details. We furthersupplement the standard adversarial loss with voxel-level intensity,multi-scale structural similarity (MS-SSIM) and region-of-interest (ROI) basedloss components that reduce reconstruction error, enforce structuralconsistency at different scales and perceive variation in regional sensitivityto AD respectively. Experimental results demonstrate that our GLA-GAN not onlygenerates synthesized FDG-PET scans with enhanced image quality but alsosuperior clinical utility in improving AD diagnosis compared tostate-of-the-art models. Finally, we attempt to interpret some of the internalunits of the GAN that are closely related to this specific cross-modalitygeneration task.

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