Related Experiment Video
Updated: Jun 27, 2025
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
Published on: November 8, 2012
Deep learning microstructure estimation of developing brains from diffusion MRI: A newborn and fetal study
Hamza Kebiri1, Ali Gholipour2, Rizhong Lin3
1CIBM Center for Biomedical Imaging, Switzerland; Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland; Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA.
Abstract:
Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results than standard methods such as Constrained Spherical Deconvolution and two state-of-the-art deep learning methods. For voxels with one and two fibers, respectively, our method shows an agreement rate in terms of the number of fibers of 77.5% and 22.2%, which is 3% and 5.4% higher than other deep learning methods, and an angular error of 10° and 20°, which is 6° and 5° lower than other deep learning methods. To determine baselines for assessing the performance of our method, we compute agreement metrics using densely sampled newborn data. Moreover, we demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical external datasets of newborns and fetuses. We validate fetal FODs, successfully estimated for the first time with deep learning, using post-mortem histological data. Our results show the advantage of deep learning in computing the fiber orientation density for the developing brain from in-vivo dMRI measurements that are often very limited due to constrained acquisition times. Our findings also highlight the intrinsic limitations of dMRI for probing the developing brain microstructure.
Insights
A new deep learning method enables accurate brain white matter fiber analysis using minimal diffusion-weighted imaging (dWI) measurements. This approach significantly improves fiber orientation distribution function (FOD) estimation in newborns and fetuses, overcoming previous data acquisition limitations.
Area of Science:
- Neuroimaging
- Medical Physics
- Computational Neuroscience
Background:
- Diffusion-weighted magnetic resonance imaging (dMRI) is crucial for evaluating brain white matter structure.
- Estimating fiber orientation distribution functions (FODs) accurately typically requires extensive dMRI measurements, posing challenges for vulnerable populations like newborns and fetuses due to limited acquisition times.
- Existing standard and deep learning methods struggle with limited dMRI data, particularly in developing brains.
Purpose of the Study:
- To develop and validate a novel deep learning approach for computing FODs from a reduced number of dMRI measurements.
- To overcome the limitations of standard FOD computation methods in scenarios with scarce dMRI data, such as in neonatal and fetal imaging.
- To demonstrate the generalizability and accuracy of the proposed deep learning method across different scanners, protocols, and anatomical structures.
Main Methods:
- A deep learning model was trained to map a minimal set of six dMRI measurements to target FODs, using high angular resolution data as the ground truth.
- The method's performance was quantitatively evaluated against standard techniques like Constrained Spherical Deconvolution and other deep learning approaches.
- Generalizability was assessed using two independent clinical datasets of newborns and fetuses, with fetal FODs validated against post-mortem histological data.
Main Results:
- The deep learning method achieved comparable or superior results to existing methods, despite using significantly fewer dMRI measurements.
- For single and double fiber voxels, the method demonstrated higher agreement rates (77.5% and 22.2%) and lower angular errors (10° and 20°) compared to other deep learning techniques.
- The model showed robust performance across different scanners, acquisition protocols, and anatomical variations, successfully estimating fetal FODs for the first time using dMRI.
Conclusions:
- Deep learning offers a powerful solution for accurate fiber orientation density computation in developing brains using limited in-vivo dMRI data.
- The proposed method significantly enhances the feasibility of advanced white matter tractography in neonates and fetuses.
- Despite advancements, inherent limitations of dMRI in probing developing brain microstructure persist, warranting further research.
More Related Videos
08:49Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy
Published on: August 1, 2022
13:26Measuring Connectivity in the Primary Visual Pathway in Human Albinism Using Diffusion Tensor Imaging and Tractography
Published on: August 11, 2016