Related Experiment Video
Updated: Sep 11, 2026
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
Published on: May 10, 2012
Motion artifacts reduction in brain MRI by means of a deep residual network with densely connected multi-resolution
Junchi Liu1, Mehmet Kocak2, Mark Supanich2
1Department of Electrical and Computer Engineering, Illinois Institute of Technology, 10 W 35th St, Chicago, IL 60616, USA.
Objective:
Magnetic resonance imaging (MRI) acquisition is inherently sensitive to motion, and motion artifact reduction is essential for improving image quality in MRI.
Methods:
We developed a deep residual network with densely connected multi-resolution blocks (DRN-DCMB) model to reduce the motion artifacts in T1 weighted (T1W) spin echo images acquired on different imaging planes before and after contrast injection. The DRN-DCMB network consisted of multiple multi-resolution blocks connected with dense connections in a feedforward manner. A single residual unit was used to connect the input and output of the entire network with one shortcut connection to predict a residual image (i.e. artifact image). The model was trained with five motion-free T1W image stacks (pre-contrast axial and sagittal, and post-contrast axial, coronal, and sagittal images) with simulated motion artifacts.
Results:
In other 86 testing image stacks with simulated artifacts, our DRN-DCMB model outperformed other state-of-the-art deep learning models with significantly higher structural similarity index (SSIM) and improvement in signal-to-noise ratio (ISNR). The DRN-DCMB model was also applied to 121 testing image stacks appeared with various degrees of real motion artifacts. The acquired images and processed images by the DRN-DCMB model were randomly mixed, and image quality was blindly evaluated by a neuroradiologist. The DRN-DCMB model significantly improved the overall image quality, reduced the severity of the motion artifacts, and improved the image sharpness, while kept the image contrast.
Conclusion:
Our DRN-DCMB model provided an effective method for reducing motion artifacts and improving the overall clinical image quality of brain MRI.
Insights
A new deep learning model effectively reduces motion artifacts in brain MRI scans. This method significantly improves image quality, sharpness, and signal-to-noise ratio for clearer diagnostic imaging.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neuroscience
Background:
- Magnetic Resonance Imaging (MRI) is highly susceptible to motion artifacts.
- Reducing these artifacts is crucial for enhancing MRI image quality and diagnostic accuracy.
Purpose of the Study:
- To develop and evaluate a novel deep learning model for reducing motion artifacts in T1-weighted (T1W) spin echo MRI images.
- To assess the model's effectiveness on various imaging planes and contrast conditions.
Main Methods:
- A deep residual network with densely connected multi-resolution blocks (DRN-DCMB) was developed.
- The model was trained using simulated motion artifacts on T1W image stacks.
- Performance was evaluated against state-of-the-art deep learning models using structural similarity index (SSIM) and improvement in signal-to-noise ratio (ISNR).
Main Results:
- The DRN-DCMB model significantly outperformed other deep learning models in reducing simulated motion artifacts.
- Applied to real-world MRI scans, the model demonstrated significant improvements in overall image quality, sharpness, and artifact reduction.
- Neuroradiologist evaluation confirmed the model's effectiveness in enhancing clinical image quality without compromising contrast.
Conclusions:
- The DRN-DCMB model offers an effective solution for motion artifact reduction in brain MRI.
- This deep learning approach enhances overall clinical image quality, aiding in more accurate diagnoses.
