Label-Free Intraoperative Imaging of Hemodynamics using Deep Learning

TL;DR

This paper introduces a deep learning-based method to generate hemodynamic maps from label-free imaging modalities, enabling real-time vascular assessment and blood flow analysis during neurosurgery without contrast agents.

Contribution

It presents a novel cross-modal deep learning framework that synthesizes MTT maps from LSCI and WLI, allowing artery-vein differentiation and flow direction inference intraoperatively.

Findings

Achieves clear vasculature visualization and accurate artery-vein differentiation.

Reduces imaging time by 95.8% compared to traditional ICG methods.

Demonstrates reliable blood flow direction decoding in rat brains.

Abstract

Intraoperative visualization of hemodynamics is crucial for accurate diagnosis and informed surgical decision-making. In neurosurgery, indocyanine green fluorescence imaging (ICG-FI) is the gold standard for assessing blood flow and identifying vascular structures. However, it is limited by time-consuming data acquisition, mandatory waiting periods, potential allergic reactions, and operational complexities. Label-free alternatives, such as laser speckle contrast imaging (LSCI) and white light imaging (WLI), offer real-time vascular assessment but cannot resolve arterial-venous differentiation or blood flow direction determination. To address these challenges, we present a label-free cross-modal generation framework to synthesize mean transition time (MTT) maps from LSCI and WLI. MTT maps encode local hemodynamics, enabling artery-vein differentiation and flow direction inference. Experimental validation in rat brains demonstrates that the proposed method presents clear vasculature delineation, accurate artery-vein differentiation, and reliable blood flow direction decoding, while reducing total imaging time by 95.8% compared to conventional ICG protocols. This approach offers a fast, efficient, and contrast-free solution for continuous intraoperative surgical guidance.