Significance: Multi-exposure laser speckle contrast imaging (MELSCI) estimates microcirculatory blood perfusion more accurately than single-exposure LSCI. However, the technique has been hampered by technical limitations due to massive data throughput requirements and nonlinear inverse search algorithms, limiting it to an offline technique where data must be postprocessed. Aim: To present an MELSCI system capable of continuous acquisition and processing of MELSCI data, enabling real-time video-rate perfusion imaging with high accuracy. Approach: The MELSCI algorithm was implemented in programmable hardware (field programmable gate array) closely interfaced to a high-speed CMOS sensor for real-time calculation. Perfusion images were estimated in real-time from the MELSCI data using an artificial neural network trained on simulated data. The MELSCI perfusion was compared to two existing single-exposure metrics both quantitatively in a controlled phantom experiment and qualitatively in vivo. Results: The MELSCI perfusion shows higher signal dynamics compared to both single-exposure metrics, both spatially and temporally where heartbeat-related variations are resolved in much greater detail. The MELSCI perfusion is less susceptible to measurement noise and is more linear with respect to laser Doppler perfusion in the phantom experiment (R2 = 0.992). Conclusions: The presented MELSCI system allows for real-time acquisition and calculation of high-quality perfusion at 15.6 frames per second.

中文翻译：

---

使用多曝光激光散斑对比度成像和机器学习的实时视频速率灌注成像

意义：多次曝光激光散斑对比成像 (MELSCI) 比单次曝光 LSCI 更准确地估计微循环血液灌注。然而，由于海量数据吞吐量要求和非线性逆向搜索算法，该技术受到技术限制的阻碍，将其限制为必须对数据进行后处理的离线技术。目的：提出一种能够连续采集和处理 MELSCI 数据的 MELSCI 系统，实现高精度的实时视频速率灌注成像。方法：MELSCI 算法在可编程硬件（现场可编程门阵列）中实现，与高速 CMOS 传感器紧密连接以进行实时计算。灌注图像是使用在模拟数据上训练的人工神经网络从 MELSCI 数据实时估计的。将 MELSCI 灌注与两个现有的单次暴露指标在受控幻像实验中进行定量和体内定性比较。结果：与单次曝光指标相比，MELSCI 灌注显示出更高的信号动态，在空间和时间上都可以更详细地解决与心跳相关的变化。MELSCI 灌注不太容易受到测量噪声的影响，并且在体模实验中相对于激光多普勒灌注更为线性 (R2 = 0.992)。结论：所提出的 MELSCI 系统允许以每秒 15.6 帧的速度实时采集和计算高质量灌注。与单次曝光指标相比，MELSCI 灌注显示出更高的信号动态，在空间和时间上都可以更详细地解决与心跳相关的变化。MELSCI 灌注不太容易受到测量噪声的影响，并且在体模实验中相对于激光多普勒灌注更为线性 (R2 = 0.992)。结论：所提出的 MELSCI 系统允许以每秒 15.6 帧的速度实时采集和计算高质量灌注。与单次曝光指标相比，MELSCI 灌注显示出更高的信号动态，在空间和时间上都可以更详细地解决与心跳相关的变化。MELSCI 灌注不太容易受到测量噪声的影响，并且在体模实验中相对于激光多普勒灌注更为线性 (R2 = 0.992)。结论：所提出的 MELSCI 系统允许以每秒 15.6 帧的速度实时采集和计算高质量灌注。