CapillaryNet: An Automated System to Quantify Skin Capillary Density and Red Blood Cell Velocity from Handheld Vital Microscopy
This system addresses the bottleneck of clinical microvascular analysis for diseases such as COVID-19, pancreatitis, and acute heart diseases, though it is incremental as it automates existing manual tasks with improved speed and accuracy.
The paper tackled the problem of manual analysis of skin capillary density and red blood cell velocity from microscopy videos, which is time-consuming and requires specialist training, by developing CapillaryNet, an automated system that detects capillaries in ~0.9 seconds per frame with ~93% accuracy and quantifies novel parameters like capillary hematocrit and flow velocity heterogeneity.
Capillaries are the smallest vessels in the body responsible for delivering oxygen and nutrients to surrounding cells. Various life-threatening diseases are known to alter the density of healthy capillaries and the flow velocity of erythrocytes within the capillaries. In previous studies, capillary density and flow velocity were manually assessed by trained specialists. However, manual analysis of a standard 20-second microvascular video requires 20 minutes on average and necessitates extensive training. Thus, manual analysis has been reported to hinder the application of microvascular microscopy in a clinical environment. To address this problem, this paper presents a fully automated state-of-the-art system to quantify skin nutritive capillary density and red blood cell velocity captured by handheld-based microscopy videos. The proposed method combines the speed of traditional computer vision algorithms with the accuracy of convolutional neural networks to enable clinical capillary analysis. The results show that the proposed system fully automates capillary detection with an accuracy exceeding that of trained analysts and measures several novel microvascular parameters that had eluded quantification thus far, namely, capillary hematocrit and intracapillary flow velocity heterogeneity. The proposed end-to-end system, named CapillaryNet, can detect capillaries at $\sim$0.9 seconds per frame with $\sim$93\% accuracy. The system is currently being used as a clinical research product in a larger e-health application to analyse capillary data captured from patients suffering from COVID-19, pancreatitis, and acute heart diseases. CapillaryNet narrows the gap between the analysis of microcirculation images in a clinical environment and state-of-the-art systems.