Artificial neural networks trained on simulated multispectral data for real-time imaging of skin microcirculatory blood oxygen saturation

作者：Marcus Larsson, Maria Ewerlöf, E. G. Salerud, Tomas Strömberg, Ingemar Fredriksson · 发表于：Journal of Biomedical Optics · 年份：2024 · DOI：10.1117/1.jbo.29.s3.s33304 · 被引用次数：11 · 研究领域：Medicine、Engineering

Abstract. Significance Imaging blood oxygen saturation (SO2) in the skin can be of clinical value when studying ischemic tissue. Emerging multispectral snapshot cameras enable real-time imaging but are limited by slow analysis when using inverse Monte Carlo (MC), the gold standard for analyzing multispectral data. Using artificial neural networks (ANNs) facilitates a significantly faster analysis but requires a large amount of high-quality training data from a wide range of tissue types for a precise estimation of SO2. Aim We aim to develop a framework for training ANNs that estimates SO2 in real time from multispectral data with a precision comparable to inverse MC. Approach ANNs are trained using synthetic data from a model that includes MC simulations of light propagation in tissue and hardware characteristics. The model includes physiologically relevant variations in optical properties, unique sensor characteristics, variations in illumination spectrum, and detector noise. This approach enables a rapid way of generating high-quality training data that covers different tissue types and skin pigmentation. Results The ANN implementation analyzes an image in 0.11 s, which is at least 10,000 times faster than inverse MC. The hardware modeling is significantly improved by an in-house calibration of the sensor spectral response. An in-vivo example shows that inverse MC and ANN give almost identical SO2 values with a mean absolute deviation of 1.3%-units. Conclusions ANN can repl...