Noninvasive assessment of skin structure using hyperspectral images has been intensively studied in recent years. Due to the high computational cost of the classical methods, such as the inverse Monte Carlo (IMC), much research has been done with the aim of using machine learning (ML) methods to reduce the time required for estimating parameters. This study aims to evaluate the accuracy and the estimation speed of the ML methods for this purpose and compare them to the traditionally used inverse adding-doubling (IAD) algorithm. We trained three models – an artificial neural network (ANN), a 1D convolutional neural network (CNN), and a random forests (RF) model – to predict seven skin parameters. The models were trained on simulated data computed using the adding-doubling algorithm. To improve predictive performance, we introduced a stacked dynamic weighting (SDW) model combining the predictions of all three individually trained models. SDW model was trained by using only a handful of real-world spectra on top of the ANN, CNN and RF models that were trained using simulated data. Models were evaluated based on the estimated parameters’ mean absolute error (MAE), considering the surface inclination angle and comparing skin spectra with spectra fitted by the IAD algorithm. On simulated data, the lowest MAE was achieved by the RF model (0.0030), while the SDW model achieved the lowest MAE on in vivo measured spectra (0.0113). The shortest time to estimate parameters for a single spectrum was 93.05 μs. Results suggest that ML algorithms can produce accurate estimates of human skin optical parameters in near real-time.

. Significance: Hyperspectral imaging (HSI) has emerged as a promising optical technique. Besides optical properties of a sample, other sample physical properties also affect the recorded images. They are significantly affected by the sample curvature and sample surface to camera distance. A correction method to reduce the artifacts is necessary to reliably extract sample properties. Aim: Our aim is to correct hyperspectral images using the three-dimensional (3D) surface data and assess how the correction affects the extracted sample properties. Approach: We propose the combination of HSI and 3D profilometry to correct the images using the Lambert cosine law. The feasibility of the correction method is presented first on hemispherical tissue phantoms and next on human hands before, during, and after the vascular occlusion test (VOT). Results: Seven different phantoms with known optical properties were created and imaged with a hyperspectral system. The correction method worked up to 60 deg inclination angle, whereas for uncorrected images the maximum angles were 20 deg. Imaging hands before, during, and after VOT shows good agreement between the expected and extracted skin physiological parameters. Conclusions: The correction method was successfully applied on the images of tissue phantoms of known optical properties and geometry and VOT. The proposed method could be applied to any reflectance optical imaging technique and should be used whenever the sample parameters need to be extracted from a curved surface sample.

Analysing diffuse reflectance spectra to extract properties of biological tissue requires modelling of light transport within the tissue, considering its absorption, scattering, and geometrical properties. Due to the layered skin structure, skin tissue models are often divided into multiple layers with their associated optical properties. Typically, in the analysis, some model parameters defining these properties are fixed to values reported in the literature to speed up the fitting process and improve its performance. In the absence of consensus, various studies use different approaches in fixing the model parameters. This study aims to assess the effect of fixing various model parameters in the skin spectra fitting process on the accuracy and robustness of a GPU-accelerated two-layer inverse adding-doubling (IAD) algorithm. Specifically, the performance of the IAD method is determined for noiseless simulated skin spectra, simulated spectra with different levels of noise applied, and in-vivo measured reflectance spectra from hyperspectral images of human hands recorded before, during, and after the arterial occlusion. Our results suggest that fixing multiple parameters to a priori known values generally improves the robustness and accuracy of the IAD algorithm for simulated spectra. However, for in-vivo measured spectra, these values are unknown in advance and fixing optical parameters to incorrect values significantly deteriorates the overall performance. Therefore, we propose a method to improve the fitting performance by pre-estimating model parameters. Our findings could be considered in all future research involving the analysis of diffuse reflectance spectra to extract optical properties of skin tissue.

Understanding tumors and their microenvironment are essential for successful and accurate disease diagnosis. Tissue physiology and morphology are altered in

No abstract