# How can spherical CNNs benefit ML-based diffusion MRI parameter estimation?

arXiv: https://arxiv.org/abs/2207.00572 · HTML: https://mlsanity.com/paper/2207.00572/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 1 Jul 2022.

## Builds on (most cited first, 4 of 4)

- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Efficient Generalized Spherical CNNs](https://mlsanity.com/paper/2010.11661/) (2020)
- [DIFFnet: Diffusion parameter mapping network generalized for input diffusion gradient schemes and bvalues](https://mlsanity.com/paper/2102.02463/) (2021)
- [Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data](https://mlsanity.com/paper/2102.09462/) (2021)

## Built on by (most cited first, 7 of 7)

- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Differentiable and accelerated spherical harmonic and Wigner transforms](https://mlsanity.com/paper/2311.14670/) (2023)
- [Spherical convolutional neural networks can improve brain microstructure estimation from diffusion MRI data](https://mlsanity.com/paper/2211.09887/) (2022)
- [A Unified Learning Model for Estimating Fiber Orientation Distribution Functions on Heterogeneous Multi-shell Diffusion-weighted MRI](https://mlsanity.com/paper/2303.16376/) (2023)
- [E(3) × SO(3)-Equivariant Networks for Spherical Deconvolution in Diffusion MRI](https://mlsanity.com/paper/2304.06103/) (2023)
- [Equivariant spatio-hemispherical networks for diffusion MRI deconvolution](https://mlsanity.com/paper/2411.11819/) (2024)
- [Protocol generalisation for brain tissue microstructure estimation via hypernetwork-controlled geometric deep learning](https://mlsanity.com/paper/2608.02053/) (2026)

## Abstract (arXiv)

This paper demonstrates spherical convolutional neural networks (S-CNN) offer distinct advantages over conventional fully-connected networks (FCN) at estimating scalar parameters of tissue microstructure from diffusion MRI (dMRI). Such microstructure parameters are valuable for identifying pathology and quantifying its extent. However, current clinical practice commonly acquires dMRI data consisting of only 6 diffusion weighted images (DWIs), limiting the accuracy and precision of estimated microstructure indices. Machine learning (ML) has been proposed to address this challenge. However, existing ML-based methods are not robust to differing dMRI gradient sampling schemes, nor are they rotation equivariant. Lack of robustness to sampling schemes requires a new network to be trained for each scheme, complicating the analysis of data from multiple sources. A possible consequence of the lack of rotational equivariance is that the training dataset must contain a diverse range of microstucture orientations. Here, we show spherical CNNs represent a compelling alternative that is robust to new sampling schemes as well as offering rotational equivariance. We show the latter can be leveraged to decrease the number of training datapoints required.