Degenerative adversarial neuroimage nets for brain scan simulations: Application in ageing and dementia
Year: 2021
Type: article
Abstract: Accurate and realistic simulation of high-dimensional medical images has become an important research area relevant to many AI-enabled healthcare applications. However, current state-of-the-art approaches lack the ability to produce satisfactory high-resolution and accurate subject-specific images. In this work, we present a deep learning framework, namely 4D-Degenerative Adversarial NeuroImage Net (4D-DANI-Net), to generate high-resolution, longitudinal MRI scans that mimic subject-specific neurodegeneration in ageing and dementia. 4D-DANI-Net is a modular framework based on adversarial training and a set of novel spatiotemporal, biologically-informed constraints. To ensure efficient training and overcome memory limitations affecting such high-dimensional problems, we rely on three key technological advances: i) a new 3D training consistency mechanism called Profile Weight Functions (PWFs), ii) a 3D super-resolution module and iii) a transfer learning strategy to fine-tune the system for a given individual. To evaluate our approach, we trained the framework on 9852 T1-weighted MRI scans from 876 participants in the Alzheimer's Disease Neuroimaging Initiative dataset and held out a separate test set of 1283 MRI scans from 170 participants for quantitative and qualitative assessment of the personalised time series of synthetic images. We performed three evaluations: i) image quality assessment; ii) quantifying the accuracy of regional brain volumes over and above benchmark models; and iii) quantifying visual perception of the synthetic images by medical experts. Overall, both quantitative and qualitative results show that 4D-DANI-Net produces realistic, low-artefact, personalised time series of synthetic T1 MRI that outperforms benchmark models.
Source: Medical Image Analysis
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,970
Funders: U.S. Department of Defense, Alzheimer's Association, Bristol-Myers Squibb, Eli Lilly and Company, Pfizer, Biogen, University of Southern California, Meso Scale Diagnostics, Nvidia, BioClinica, Novartis Pharmaceuticals Corporation, Northern California Institute for Research and Education, UK Research and Innovation, National Institute for Health and Care Research, European Commission, Eisai, University College London Hospitals NHS Foundation Trust, Servier, H. Lundbeck A/S, IXICO, National Institutes of Health, Genentech, Canadian Institutes of Health Research, Engineering and Physical Sciences Research Council, National Institute on Aging
Awards: G104586243, G1298807586, G1554142629, G1593117279, G1650819308, G1693528767, G1880935189, Alzheimer's Disease Neuroimaging Initiative, G2100670906, G2152643862, G2189010064, G2340207221, G2471646051, G2522063444, G2810537366, G3018663809, G3131374986, Medical image computing for next-generation healthcare technology, G3158472349, G3553156159, G3710456697, G3752451908, G3870774570, G3908963977, G4119534169, G4266322423, Data-driven models for Progression Of Neurological Disease, G43180419, G434337789, G4475667458, G4501223628, G4669776581, G4800177743, G5207404921, G5209990037, G528601746, G5324093878, G5365730499, EFFECTS OF TRAUMATIC BRAIN INJURY (TBI) AND POST TRAUMATIC STRESS DISORDER (PTSD) ON ALZHEIMER'S DISEASE (AD) IN VETERANS USING IMAGING AND BIOMARKERS IN THE AD NEUROIMAGING INITIATIVE (ADNI)", G5581794527, G5619513383, G5654639750, G5740349702, G5850682332, G6039058924, G613619302, G6173816828, G6210868510, G6305660231, G6371410416, G6412110892, G6447063303, G6719828067, G6792506723, G6899163935, G72415811, G7298697282, G764699806, G7799614282, G781725486, G8228018387, G8281378126, G839208290, G844244329, G8852128998, G8895907669, G8897063270, G8957659042, G9000039018, G9000122335, G902693135
OpenAlex ID: W3119619513