DELIMIT PyTorch - An extension for Deep Learning in Diffusion Imaging

TL;DR

DELIMIT extends PyTorch with novel spherical harmonic and local spherical convolution layers, enabling deep learning applications directly on spherical diffusion imaging data for improved analysis and preprocessing.

Contribution

The paper introduces new spherical harmonic interpolation and local spherical convolution layers as extensions to PyTorch for diffusion imaging.

Findings

Enables direct deep learning on spherical diffusion data.

Facilitates preprocessing of diffusion signals.

Provides convenient tools for spherical signal analysis.

Abstract

DELIMIT is a framework extension for deep learning in diffusion imaging, which extends the basic framework PyTorch towards spherical signals. Based on several novel layers, deep learning can be applied to spherical diffusion imaging data in a very convenient way. First, two spherical harmonic interpolation layers are added to the extension, which allow to transform the signal from spherical surface space into the spherical harmonic space, and vice versa. In addition, a local spherical convolution layer is introduced that adds the possibility to include gradient neighborhood information within the network. Furthermore, these extensions can also be utilized for the preprocessing of diffusion signals.