Reconstructing the Hemodynamic Response Function via a Bimodal Transformer
This addresses the challenge of understanding hemodynamic responses in fMRI for neuroscience, though it is incremental as it builds on existing knowledge with a new model.
The study tackled the problem of predicting blood flow from neuronal activity at the neuronal population level using a bimodal transformer, finding that incorporating neuronal activity significantly improved prediction accuracy.
The relationship between blood flow and neuronal activity is widely recognized, with blood flow frequently serving as a surrogate for neuronal activity in fMRI studies. At the microscopic level, neuronal activity has been shown to influence blood flow in nearby blood vessels. This study introduces the first predictive model that addresses this issue directly at the explicit neuronal population level. Using in vivo recordings in awake mice, we employ a novel spatiotemporal bimodal transformer architecture to infer current blood flow based on both historical blood flow and ongoing spontaneous neuronal activity. Our findings indicate that incorporating neuronal activity significantly enhances the model's ability to predict blood flow values. Through analysis of the model's behavior, we propose hypotheses regarding the largely unexplored nature of the hemodynamic response to neuronal activity.