Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time
Early and accurate assessment of brain microstructure using diffusion Magnetic Resonance Imaging (dMRI) is crucial for identifying neurodevelopmental disorders in neonates, but remains challenging due to low signal-to-noise ratio (SNR), motion artifacts, and ongoing myelination. In this study, we pr...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2025.1604545/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849412045174210560 |
|---|---|
| author | Haykel Snoussi Davood Karimi |
| author_facet | Haykel Snoussi Davood Karimi |
| author_sort | Haykel Snoussi |
| collection | DOAJ |
| description | Early and accurate assessment of brain microstructure using diffusion Magnetic Resonance Imaging (dMRI) is crucial for identifying neurodevelopmental disorders in neonates, but remains challenging due to low signal-to-noise ratio (SNR), motion artifacts, and ongoing myelination. In this study, we propose a rotationally equivariant Spherical Convolutional Neural Network (sCNN) framework tailored for neonatal dMRI. We predict the Fiber Orientation Distribution (FOD) from multi-shell dMRI signals acquired with a reduced set of gradient directions (30% of the full protocol), enabling faster and more cost-effective acquisitions. We train and evaluate the performance of our sCNN using real data from 43 neonatal dMRI datasets provided by the Developing Human Connectome Project (dHCP). Our results demonstrate that the sCNN significantly outperforms a Multi-Layer Perceptron (MLP) baseline across multiple quantitative metrics, including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Angular Correlation Coefficient (ACC), angular error, and peak match rate, indicating superior FOD estimation accuracy. More importantly, it yields FODs and tractography that are quantitatively comparable and qualitatively highly similar to those from a reliable Hybrid-CSD ground truth, despite using only 30% of the full acquisition data. These findings highlight sCNNs' potential for accurate and clinically efficient dMRI analysis, paving the way for improved diagnostic capabilities and characterization of early brain development with shorter scan times. |
| format | Article |
| id | doaj-art-e74a393e34e4462f93f5273d77e52abe |
| institution | Kabale University |
| issn | 1662-453X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj-art-e74a393e34e4462f93f5273d77e52abe2025-08-20T03:34:33ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-07-011910.3389/fnins.2025.16045451604545Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition timeHaykel SnoussiDavood KarimiEarly and accurate assessment of brain microstructure using diffusion Magnetic Resonance Imaging (dMRI) is crucial for identifying neurodevelopmental disorders in neonates, but remains challenging due to low signal-to-noise ratio (SNR), motion artifacts, and ongoing myelination. In this study, we propose a rotationally equivariant Spherical Convolutional Neural Network (sCNN) framework tailored for neonatal dMRI. We predict the Fiber Orientation Distribution (FOD) from multi-shell dMRI signals acquired with a reduced set of gradient directions (30% of the full protocol), enabling faster and more cost-effective acquisitions. We train and evaluate the performance of our sCNN using real data from 43 neonatal dMRI datasets provided by the Developing Human Connectome Project (dHCP). Our results demonstrate that the sCNN significantly outperforms a Multi-Layer Perceptron (MLP) baseline across multiple quantitative metrics, including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), Angular Correlation Coefficient (ACC), angular error, and peak match rate, indicating superior FOD estimation accuracy. More importantly, it yields FODs and tractography that are quantitatively comparable and qualitatively highly similar to those from a reliable Hybrid-CSD ground truth, despite using only 30% of the full acquisition data. These findings highlight sCNNs' potential for accurate and clinically efficient dMRI analysis, paving the way for improved diagnostic capabilities and characterization of early brain development with shorter scan times.https://www.frontiersin.org/articles/10.3389/fnins.2025.1604545/fulldiffusion MRIspherical CNNsneonatal brainfiber orientationgeometric deep learningtractography |
| spellingShingle | Haykel Snoussi Davood Karimi Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time Frontiers in Neuroscience diffusion MRI spherical CNNs neonatal brain fiber orientation geometric deep learning tractography |
| title | Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time |
| title_full | Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time |
| title_fullStr | Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time |
| title_full_unstemmed | Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time |
| title_short | Equivariant spherical CNNs for accurate fiber orientation distribution estimation in neonatal diffusion MRI with reduced acquisition time |
| title_sort | equivariant spherical cnns for accurate fiber orientation distribution estimation in neonatal diffusion mri with reduced acquisition time |
| topic | diffusion MRI spherical CNNs neonatal brain fiber orientation geometric deep learning tractography |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2025.1604545/full |
| work_keys_str_mv | AT haykelsnoussi equivariantsphericalcnnsforaccuratefiberorientationdistributionestimationinneonataldiffusionmriwithreducedacquisitiontime AT davoodkarimi equivariantsphericalcnnsforaccuratefiberorientationdistributionestimationinneonataldiffusionmriwithreducedacquisitiontime |