Learning Implicit Brain MRI Manifolds with Deep Learning

By Camilo Bermudez, Andrew J. Plassard, L. Davis, Allen T. Newton, Susan M. Resnick, Bennett A. Landman. 2018

139 citations recorded by the source corpus.

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.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “GANs [79] A generative adversarial network consists of two neural networks pitted against each other.”
Generative Adversarial Network in Medical Imaging: A Review (2018, methodology): “(2012) HCP Human Connectome Project Brain MR D21 Codella et al. (2018) ISIC2017 Skin lesion analysis Skin Dermoscopy”
On Leveraging Pretrained GANs for Limited-Data Generation (2020, background): “For the problem of limited-data generation, to naively train a GAN on the limited data is prone to overfitting for powerful GAN models with a lot of parameters, which are essential for realistic generation (Bermudez et al., 2018; Bowles et al., 2018; Frid-Adar et al., 2018; Finlayson et al., 2018).”
GANs for Medical Image Analysis (2018, background): “[26] has shown that the DCGAN can learn to mimic the distribution of entire MR data at considerably high resolution, even from a surprisingly small amount of samples.”
On Leveraging Pretrained GANs for Generation with Limited Data (2020, background): “When a limited quantity of data are available, to naively train a GAN is prone to overfitting, as powerful GAN models have numerous parameters that are essential for realistic generation (Bermudez et al., 2018; Bowles et al., 2018; Frid-Adar et al., 2018; Finlayson et al., 2018).”