Publications by authors named "David J Ma"
Improving across-dataset brain tissue segmentation for MRI imaging using transformer.
Front Neuroimaging
November 2022
Article Synopsis
- This study addresses the challenges of manual brain tissue segmentation in MRI data analysis and highlights the limitations of existing automated methods, especially CNNs, in achieving reliable results.
- The authors introduce a new hybrid CNN-Transformer architecture that enhances performance for 3D medical image segmentation, demonstrating its effectiveness on diverse T1-weighted MRI datasets.
- The model's robustness is validated across multiple sites and conditions, showing superior generality and reliability, making it a promising tool for brain research and available for public access via GitHub.
Background: Deep learning-based methods have been successfully applied to MRI image registration. However, there is a lack of deep learning-based registration methods for magnetic resonance spectroscopy (MRS) spectral registration (SR).
Purpose: To investigate a convolutional neural network-based SR (CNN-SR) approach for simultaneous frequency-and-phase correction (FPC) of single-voxel Meshcher-Garwood point-resolved spectroscopy (MEGA-PRESS) MRS data.
Purpose: To introduce a novel convolutional neural network (CNN)-based approach for frequency-and-phase correction (FPC) of MR spectroscopy (MRS) spectra to achieve fast and accurate FPC of single-voxel MEGA-PRESS MRS data.
Methods: Two neural networks (one for frequency and one for phase) were trained and validated using published simulated and in vivo MEGA-PRESS MRS dataset with wide-range artificial frequency and phase offsets applied. The CNN-based approach was subsequently tested and compared to the current deep learning solution: multilayer perceptrons (MLP).