Group Convolutional Neural Networks for DWI Segmentation
Research output: Contribution to journal › Conference article › Research
Standard
Group Convolutional Neural Networks for DWI Segmentation. / Liu, Renfei; Lauze, Francois Bernard; Bekkers, Erik J. ; Erleben, Kenny.
In: Proceedings of Machine Learning Research, Vol. 2022, No. 1, 2022, p. 1-11.Research output: Contribution to journal › Conference article › Research
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Group Convolutional Neural Networks for DWI Segmentation
AU - Liu, Renfei
AU - Lauze, Francois Bernard
AU - Bekkers, Erik J.
AU - Erleben, Kenny
PY - 2022
Y1 - 2022
N2 - We present a Group Convolutional Network for Segmentation of Diffusion Weighted Imaging data (DWI). The network incorporates group actions that are natural for this type of data, in the form of equivariant convolutions, i.e., roto-translation equivariant convolutions. The equivariance property provides an important inductive bias and may alleviate the need for data augmentation strategies. Instead of performing group equivariant convolutions via spectral (Fourier-based) approaches, as is common for equivariance, we implement direct and light-weight regular group convolutions. We study the effect of equivariance and weight sharing over on performances of the networks on DWI scans from the Human Connectome project. We show how that full equivariance improves segmentations, while limiting the number of learnable parameters.
AB - We present a Group Convolutional Network for Segmentation of Diffusion Weighted Imaging data (DWI). The network incorporates group actions that are natural for this type of data, in the form of equivariant convolutions, i.e., roto-translation equivariant convolutions. The equivariance property provides an important inductive bias and may alleviate the need for data augmentation strategies. Instead of performing group equivariant convolutions via spectral (Fourier-based) approaches, as is common for equivariance, we implement direct and light-weight regular group convolutions. We study the effect of equivariance and weight sharing over on performances of the networks on DWI scans from the Human Connectome project. We show how that full equivariance improves segmentations, while limiting the number of learnable parameters.
M3 - Conference article
VL - 2022
SP - 1
EP - 11
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
SN - 2640-3498
IS - 1
T2 - GeoMedIA Workshop 2022
Y2 - 18 November 2022
ER -
ID: 339166879