Rotation-Equivariant Deep Learning for Diffusion MRI
arXiv:2102.06942
Abstract
Convolutional networks are successful, but they have recently been outperformed by new neural networks that are equivariant under rotations and translations. These new networks work better because they do not struggle with learning each possible orientation of each image feature separately. So far, they have been proposed for 2D and 3D data. Here we generalize them to 6D diffusion MRI data, ensuring joint equivariance under 3D roto-translations in image space and the matching 3D rotations in -space, as dictated by the image formation. Such equivariant deep learning is appropriate for diffusion MRI, because microstructural and macrostructural features such as neural fibers can appear at many different orientations, and because even non-rotation-equivariant deep learning has so far been the best method for many diffusion MRI tasks. We validate our equivariant method on multiple-sclerosis lesion segmentation. Our proposed neural networks yield better results and require fewer scans for training compared to non-rotation-equivariant deep learning. They also inherit all the advantages of deep learning over classical diffusion MRI methods. Our implementation is available at https://github.com/philip-mueller/equivariant-deep-dmri and can be used off the shelf without understanding the mathematical background.
24 pages, 8 figures
References in corpus (12)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Searching for Activation Functions
- Group Equivariant Convolutional Networks
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Gauge Equivariant Convolutional Networks and the Icosahedral CNN
- Equivariance Through Parameter-Sharing
- 3D G-CNNs for Pulmonary Nodule Detection
- N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
- Convolutional Networks for Spherical Signals
- Site symmetry and crystal symmetry: a spherical tensor analysis
- B-Spline CNNs on Lie Groups
- Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods