Related Experiment Video
Updated: Sep 26, 2025
Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing
Published on: February 23, 2024
Addressing Motion Blurs in Brain MRI Scans Using Conditional Adversarial Networks and Simulated Curvilinear Motions
1Department of Computer and Information Sciences, Fordham University, New York, NY 10023, USA.
Abstract:
In-scanner head motion often leads to degradation in MRI scans and is a major source of error in diagnosing brain abnormalities. Researchers have explored various approaches, including blind and nonblind deconvolutions, to correct the motion artifacts in MRI scans. Inspired by the recent success of deep learning models in medical image analysis, we investigate the efficacy of employing generative adversarial networks (GANs) to address motion blurs in brain MRI scans. We cast the problem as a blind deconvolution task where a neural network is trained to guess a blurring kernel that produced the observed corruption. Specifically, our study explores a new approach under the sparse coding paradigm where every ground truth corrupting kernel is assumed to be a "combination" of a relatively small universe of "basis" kernels. This assumption is based on the intuition that, on small distance scales, patients' moves follow simple curves and that complex motions can be obtained by combining a number of simple ones. We show that, with a suitably dense basis, a neural network can effectively guess the degrading kernel and reverse some of the damage in the motion-affected real-world scans. To this end, we generated 10,000 continuous and curvilinear kernels in random positions and directions that are likely to uniformly populate the space of corrupting kernels in real-world scans. We further generated a large dataset of 225,000 pairs of sharp and blurred MR images to facilitate training effective deep learning models. Our experimental results demonstrate the viability of the proposed approach evaluated using synthetic and real-world MRI scans. Our study further suggests there is merit in exploring separate models for the sagittal, axial, and coronal planes.
Insights
Generative adversarial networks (GANs) can effectively correct motion blurs in brain MRI scans by learning to estimate and reverse motion artifacts. This deep learning approach shows promise for improving diagnostic accuracy in neuroimaging.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neuroscience
Background:
- In-scanner head motion significantly degrades Magnetic Resonance Imaging (MRI) quality, introducing motion artifacts that are a primary source of diagnostic error in brain abnormality detection.
- Traditional methods like blind and nonblind deconvolutions have been explored for motion artifact correction, but deep learning offers a promising new avenue.
Purpose of the Study:
- To investigate the efficacy of generative adversarial networks (GANs) for correcting motion blurs in brain MRI scans.
- To explore a novel sparse coding approach for estimating motion-corrupting kernels in MRI.
Main Methods:
- The problem is framed as a blind deconvolution task where a neural network estimates the blurring kernel responsible for MRI corruption.
- A sparse coding paradigm is employed, assuming complex motion kernels are combinations of simpler basis kernels.
- A large dataset of 225,000 sharp/blurred MR image pairs and 10,000 continuous, curvilinear kernels were generated for training deep learning models.
Main Results:
- The proposed GAN-based approach successfully estimated degrading kernels and reversed motion-induced damage in both synthetic and real-world MRI scans.
- Experimental results demonstrate the viability and effectiveness of the deep learning strategy for motion artifact correction.
- The study suggests that distinct models for sagittal, axial, and coronal planes may further enhance performance.
Conclusions:
- Generative adversarial networks offer a powerful tool for mitigating motion artifacts in brain MRI, improving image quality and diagnostic reliability.
- The sparse coding approach, combined with deep learning, provides an effective framework for blind deconvolution of motion-blurred MRI.
- Further research into plane-specific models is warranted to optimize motion correction in neuroimaging.
More Related Videos
09:46MPI CyberMotion Simulator: Implementation of a Novel Motion Simulator to Investigate Multisensory Path Integration in Three Dimensions
Published on: May 10, 2012
09:38Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
Published on: November 14, 2017
Related Concept Videos
01:23Curvilinear Motion: Rectangular Components
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
01:27Curvilinear Motion: Normal and Tangential Components
The positive direction of the t-axis aligns with the increasing position of the car along the curved path, denoted by the unit vector ut. Simultaneously, the n-axis, perpendicular to the t-axis, dissects the curved path into differential arc segments, each forming the arc of a circle with a radius of...
01:25Relative Motion Analysis using Rotating Axes
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it...
01:24Absolute Motion Analysis- General Plane Motion
As the drone's propellers rotate, an upward force is generated that counteracts the force of gravity, enabling the drone to lift off from the ground. This initial movement of the drone is along a straight path, representing a form of translational motion. In this phase, every point on the...
01:29Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...