Learning implicit brain MRI manifolds with deep learning
Year: 2018
Type: conference-paper
Abstract: An important task in image processing and neuroimaging is to extract quantitative information from the acquired images in order to make observations about the presence of disease or markers of development in populations. Having a low-dimensional manifold of an image allows for easier statistical comparisons between groups and the synthesis of group representatives. Previous studies have sought to identify the best mapping of brain MRI to a low-dimensional manifold, but have been limited by assumptions of explicit similarity measures. In this work, we use deep learning techniques to investigate implicit manifolds of normal brains and generate new, high-quality images. We explore implicit manifolds by addressing the problems of image synthesis and image denoising as important tools in manifold learning. First, we propose the unsupervised synthesis of T1-weighted brain MRI using a Generative Adversarial Network (GAN) by learning from 528 examples of 2D axial slices of brain MRI. Synthesized images were first shown to be unique by performing a cross-correlation with the training set. Real and synthesized images were then assessed in a blinded manner by two imaging experts providing an image quality score of 1-5. The quality score of the synthetic image showed substantial overlap with that of the real images. Moreover, we use an autoencoder with skip connections for image denoising, showing that the proposed method results in higher PSNR than FSL SUSAN after denoising. This work shows the power of artificial networks to synthesize realistic imaging data, which can be used to improve image processing techniques and provide a quantitative framework to structural changes in the brain.
DOI: 10.1117/12.2293515
Institutions: Vanderbilt University, Vanderbilt University Medical Center
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: green
Funders: National Institutes of Health, National Institute on Aging, National Institute of General Medical Sciences, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, National Center for Research Resources, National Center for Advancing Translational Sciences, Eunice Kennedy Shriver National Institute of Child Health and Human Development
Awards: Resource Development for the Java Image Science Toolkit, Eunice Kennedy Shriver Intellectual and Developmental Disability Research Center, Computer-Assited Functional Neurosurgery, Medical Scientist Training Program, Predicting Late-Emerging RD: Neurobiological and Cognitive Factors, Eunice Kennedy Shriver Intellectual and Developmental Disabilities Research Center at Vanderbilt University, The Vanderbilt Institute for Clinical and Translational Research (VICTR) UL1, Johns Hopkins Alzheimer's Disease Research Center, Cognitive and Neural Processes in Reading Comprehension, The Vanderbilt Institute for Clinical and Translational Research (VICTR)
OpenAlex ID: W2781600508