Publications by authors named "Rizhong Lin"
Diffusion Magnetic Resonance Imaging (dMRI) is a noninvasive method for depicting brain microstructure . Fiber orientation distributions (FODs) are mathematical representations extensively used to map white matter fiber configurations. Recently, FOD estimation with deep neural networks has seen growing success, in particular, those of neonates estimated with fewer diffusion measurements.
View Article and Find Full Text PDFArticle Synopsis
- Diffusion-weighted magnetic resonance imaging (dMRI) is commonly used to study brain white matter, but standard methods for computing fiber orientation distribution functions (FODs) need many measurements, which are hard to obtain for newborns and fetuses.
- The authors propose a new deep learning approach that can estimate FODs using as few as six diffusion-weighted measurements, producing results that are as good or better than traditional methods with significantly fewer data.
- Their method shows strong performance across different settings and is validated by comparing estimated FODs with histological data, highlighting both the advantages of deep learning and the limitations of dMRI in studying brain development.
Deep learning models have shown great promise in estimating tissue microstructure from limited diffusion magnetic resonance imaging data. However, these models face domain shift challenges when test and train data are from different scanners and protocols, or when the models are applied to data with inherent variations such as the developing brains of infants and children scanned at various ages. Several techniques have been proposed to address some of these challenges, such as data harmonization or domain adaptation in the adult brain.
View Article and Find Full Text PDF