TY - JOUR
T1 - Topology-Guided Cyclic Brain Connectivity Generation using Geometric Deep Learning
AU - Sserwadda, Abubakhari
AU - Rekik, Islem
N1 - Funding - 2232 International Fellowship for Outstanding Researchers Program of TUBITAK (Project No:118C288) supporting I. Rekik.
PY - 2021/4/1
Y1 - 2021/4/1
N2 - Background: There is a growing need for analyzing medical data such as brain connectomes. However, the unavailability of large-scale training samples increases risks of model over-fitting. Recently, deep learning (DL) architectures quickly gained momentum in synthesizing medical data. However, such frameworks are primarily designed for Euclidean data (eg., images), overlooking geometric data (eg., brain connectomes). A few existing geometric DL works that aimed to predict a target brain connectome from a source one primarily focused on domain alignment and were agnostic to preserving the connectome topology.New Method: To address the above limitations, firstly, we adapt the graph translation generative adversarial network (GT GAN) architecture to brain connectomic data. Secondly, we extend the baseline GT GAN to a cyclic graph translation (CGT) GAN, allowing bidirectional brain network translation between the source and target views. Finally, to preserve the topological strength of brain regions of interest (ROIs), we impose a topological strength constraint on the CGT GAN learning, thereby introducing CGTS GAN architecture.Comparison with existing methods: We compared CGTS with graph translation methods and its ablated versions.Results: Our deep graph network outperformed the baseline comparison method and its ablated versions in mean squared error (MSE) using multiview autism spectrum disorder connectomic dataset.Conclusion: We designed a topology-aware bidirectional brain connectome synthesis framework rooted in geometric deep learning, which can be used for data augmentation in clinical diagnosis.
AB - Background: There is a growing need for analyzing medical data such as brain connectomes. However, the unavailability of large-scale training samples increases risks of model over-fitting. Recently, deep learning (DL) architectures quickly gained momentum in synthesizing medical data. However, such frameworks are primarily designed for Euclidean data (eg., images), overlooking geometric data (eg., brain connectomes). A few existing geometric DL works that aimed to predict a target brain connectome from a source one primarily focused on domain alignment and were agnostic to preserving the connectome topology.New Method: To address the above limitations, firstly, we adapt the graph translation generative adversarial network (GT GAN) architecture to brain connectomic data. Secondly, we extend the baseline GT GAN to a cyclic graph translation (CGT) GAN, allowing bidirectional brain network translation between the source and target views. Finally, to preserve the topological strength of brain regions of interest (ROIs), we impose a topological strength constraint on the CGT GAN learning, thereby introducing CGTS GAN architecture.Comparison with existing methods: We compared CGTS with graph translation methods and its ablated versions.Results: Our deep graph network outperformed the baseline comparison method and its ablated versions in mean squared error (MSE) using multiview autism spectrum disorder connectomic dataset.Conclusion: We designed a topology-aware bidirectional brain connectome synthesis framework rooted in geometric deep learning, which can be used for data augmentation in clinical diagnosis.
KW - Brain connectome generation
KW - Cyclic adversarial graph translation
KW - Geometric deep learning
KW - Topological strength
UR - http://www.scopus.com/inward/record.url?scp=85100972286&partnerID=8YFLogxK
U2 - 10.1016/j.jneumeth.2020.108988
DO - 10.1016/j.jneumeth.2020.108988
M3 - Article
C2 - 33160020
VL - 353
JO - Journal of Neuroscience Methods
JF - Journal of Neuroscience Methods
SN - 0165-0270
M1 - 108988
ER -