Machine learning in multiexposure laser speckle contrast imaging can replace conventional laser Doppler flowmetry

Abstract

Laser speckle contrast imaging (LSCI) enables video rate imaging of blood flow. However, its relation to tissue blood perfusion is nonlinear and depends strongly on exposure time. By contrast, the perfusion estimate from the slower laser Doppler flowmetry (LDF) technique has a relationship to blood perfusion that is better understood. Multiexposure LSCI (MELSCI) enables a perfusion estimate closer to the actual perfusion than that using a single exposure time. We present and evaluate a method that utilizes contrasts from seven exposure times between 1 and 64 ms to calculate a perfusion estimate that resembles the perfusion estimate from LDF. The method is based on artificial neural networks (ANN) for fast and accurate processing of MELSCI contrasts to perfusion. The networks are trained using modeling of Doppler histograms and speckle contrasts from tissue models. The importance of accounting for noise is demonstrated. Results show that by using ANN, MELSCI data can be processed to LDF perfusion with high accuracy, with a correlation coefficient R ¼ 1.000 for noise-free data, R ¼ 0.993 when a moderate degree of noise is present, and R ¼ 0.995 for in vivo data from an occlusionrelease experiment. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Real-time video-rate perfusion imaging using multi-exposure laser speckle contrast imaging and machine learning

“…(4) and (5), we estimated perfusion from the multi-exposure contrast in each pixel using a technique we have presented previously. 6 Using 100,000 randomized tissue models spanning a wide range of properties such as blood flow speed distribution, blood amount, skin layer thickness, etc., together with Monte Carlo simulations of the light transport in these models, we created a large dataset from which we calculated both multi-exposure contrast and laser Doppler perfusion. We then trained an ANN to estimate laser Doppler perfusion from the multi-exposure contrast in each pixel, i.e.…”

“…However, conventional LSCI has drawbacks such as a nonlinear response to perfusion, dependency to static scattering contrast, and a high variability in the presence of noise. 5,6 Recent work has gone into calibrating and correcting for these issues to make LSCI a more accurate technique. 7 Despite this, while it is generally accepted that LSCI is related to microcirculatory perfusion, the relationship is complex and a direct mapping is still not known.…”

“…This process must be performed individually in each pixel for full field perfusion images, which is not feasible in real-time with satisfactory frame rates. 6 We have previously presented a method using machine learning and simulated data from thousands of Monte Carlo tissue models from which we train an artificial neural network (ANN) to translate multi-exposure contrast to laser Doppler perfusion. We showed that this technique not only achieves a model-inference time of <30 ms per image, but also has higher accuracy and less susceptibility to noise than other available models.…”

“…We showed that this technique not only achieves a model-inference time of <30 ms per image, but also has higher accuracy and less susceptibility to noise than other available models. 6 The aim of this paper is to present a complete system for continuous real-time video-rate perfusion imaging using both our previous methods in an integrated processing pipeline. We validate the accuracy of the perfusion estimate in a controlled phantom experiment and present results from an occlusion-release provocation of the forearm of a healthy subject.…”

To See or Not to See : A Study on Capillary Refill

“…Multiexposure Laser Speckle Contrast Imaging (MELSCI) is an emerging, alternative, laserbased method of measuring skin perfusion and possibly blood flow. It uses the technique of laser speckle contrast imaging for video rate imaging of blood flow combining it with different exposure times to increase both temporal and spatial resolution 100 . It is a non-contact equipment and measures over full field areas (30x30 cm) 100 enabling the study of microcirculatory heterogeneity in critically ill patients.…”