Enhancing Diffusion Signal Augmentation Using Spherical Convolutions
Koppers S, Merhof D (2021)
Publication Type: Conference contribution
Publication year: 2021
Publisher: Springer Science and Business Media Deutschland GmbH
Pages Range: 189-200
Conference Proceedings Title: Mathematics and Visualization
Event location: Virtual, Online
ISBN: 9783030730178
DOI: 10.1007/978-3-030-73018-5_15
Abstract
The application of deep learning in the field of diffusion imaging is becoming increasingly popular. However, correlations of acquired adjacent gradient directions are often ignored. To make use of this information in a neural network, a spherical convolution is necessary. This work evaluates three different ways to include spherical information: 2D projection, local spherical convolution and Fourier space transform. For comparison, all models are designed to have a similar amount of trainable parameters as well as the same network architecture, and are evaluated by considering the example of signal augmentation. Overall, all models achieved comparable good results, improving the reconstruction performance, compared to a reconstruction without augmentation, by ≈ 30% for the fractional anisotropy, ≈ 50% for the mean diffusivity, ≈ 70% for the mean signal kurtosis and ≈ 5% for the diffusion signal itself. Particularly, in comparison to a regular neural network that does not implement a spherical convolution, the average performance for all models that implement a sperical convolution increases slightly for all evaluated measures, where the local spherical convolution shows the most favorable results.
Involved external institutions
Germany (DE)How to cite
APA:
Koppers, S., & Merhof, D. (2021). Enhancing Diffusion Signal Augmentation Using Spherical Convolutions. In Noemi Gyori, Jana Hutter, Vishwesh Nath, Marco Palombo, Marco Pizzolato, Fan Zhang (Eds.), Mathematics and Visualization (pp. 189-200). Virtual, Online: Springer Science and Business Media Deutschland GmbH.
MLA:
Koppers, Simon, and Dorit Merhof. "Enhancing Diffusion Signal Augmentation Using Spherical Convolutions." Proceedings of the International Workshop on Computational Diffusion MRI, CDMRI 2020 held in conjunction with International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2020, Virtual, Online Ed. Noemi Gyori, Jana Hutter, Vishwesh Nath, Marco Palombo, Marco Pizzolato, Fan Zhang, Springer Science and Business Media Deutschland GmbH, 2021. 189-200.
BibTeX: Download