posted on 2024-02-05, 08:30authored byLingkai Tang, Lilian Kebaya, Homa Vahidi, Paige Meyerink, Sandrine de Ribaupierre, Soume Bhattacharya, Keith St. Lawrence, Emma Duerden
Functional near-infrared spectroscopy (fNIRS) measures cortical changes in hemoglobin concentrations, yet cannot collected this information from the subcortices. To address this drawback, we propose a machine-learning-based approach to predict cortical-thalamic functional connectivity using cortical fNIRS data. We applied graph convolutional networks (GCN) on two datasets obtained from adults and neonates, respectively. Each dataset contained fNIRS data as input to the predictive models and connectivities of functional magnetic resonance imaging (fMRI) as training targets. GCN models performed better compared to conventional methods, on both identifying the connections, and regressing the quantified strengths of connections. We also propose the addition of inter-subject connections into the GCN kernels could improve performance. Our results show it is feasible to indicate subcortical activity from cortical fNIRS recordings.
History
Funder Name
Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Children's Health Foundation; Whaley and Harding Postdoctoral fellowship
Preprint ID
111721
Highlighter Commentary
This preprint indicates that machine learning models, particularly Graph Convolutional Networks, outperform conventional methods such as Artificial Neural Networks and Support Vector Machines in predicting cortical-thalamic connectivity from functional near-infrared spectroscopy data, especially when incorporating a multi-kernel strategy and inter-subject connections. Performance is suboptimal for neonatal data, however, potentially due to limitations in data acquisition and duration of scans.
-- Mousa Moradi, Ph.D. Candidate, Biomedical Engineering, UMASS Amherst