Reconstructing the Hemodynamic Response Function via a Bimodal Transformer

TL;DR

This paper introduces a novel bimodal transformer model that predicts blood flow from neuronal activity and past blood flow data, providing new insights into the hemodynamic response at the neuronal population level.

Contribution

It presents the first explicit neuronal population-level predictive model of blood flow using a bimodal transformer architecture based on in vivo mouse data.

Findings

Neuronal activity improves blood flow prediction accuracy.

The model reveals new hypotheses about the hemodynamic response.

In vivo data validates the model's effectiveness.

Abstract

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.