Deep-learning approach for automated thickness measurement of epithelial tissue and scab using optical coherence tomography

Abstract

. Significance: In order to elucidate therapeutic treatment to accelerate wound healing, it is crucial to understand the process underlying skin wound healing, especially re-epithelialization. Epidermis and scab detection is of importance in the wound healing process as their thickness is a vital indicator to judge whether the re-epithelialization process is normal or not. Since optical coherence tomography (OCT) is a real-time and non-invasive imaging technique that can perform a cross-sectional evaluation of tissue microstructure, it is an ideal imaging modality to monitor the thickness change of epidermal and scab tissues during wound healing processes in micron-level resolution. Traditional segmentation on epidermal and scab regions was performed manually, which is time-consuming and impractical in real time. Aim: We aim to develop a deep-learning-based skin layer segmentation method for automated quantitative assessment of the thickness of in vivo epidermis and scab tissues during a time course of healing within a rodent model. Approach: Five convolution neural networks were trained using manually labeled epidermis and scab regions segmentation from 1000 OCT B-scan images (assisted by its corresponding angiographic information). The segmentation performance of five segmentation architectures was compared qualitatively and quantitatively for validation set. Results: Our results show higher accuracy and higher speed of the calculated thickness compared with human experts. The U-Net architecture represents a better performance than other deep neural network architectures with 0.894 at -score, 0.875 at mean intersection over union, 0.933 at Dice similarity coefficient, and at an average symmetric surface distance. Furthermore, our algorithm is able to provide abundant quantitative parameters of the wound based on its corresponding thickness maps in different healing phases. Among them, normalized epidermal thickness is recommended as an essential hallmark to describe the re-epithelialization process of the rodent model. Conclusions: The automatic segmentation and thickness measurements within different phases of wound healing data demonstrates that our pipeline provides a robust, quantitative, and accurate method for serving as a standard model for further research into effect of external pharmacological and physical factors.

MC1R reduces scarring and rescues stalled healing in a preclinical chronic wound model

“…Equipment used in this study were designed and developed by Professor Zhihong Huang, Dr. Kanheng Zhou, Mr. Yubo Ji and Mr. Duo Zhang (University of Dundee (26, 27) ). Mice were anaesthetised at the indicated time points place on a heatpad and ultrasound transmission gel (Anagel, Ana Wiz Ltd, Surrey, UK) was applied between the OCT probe and wound to enhance refractive index coupling.…”

“…Matrigel (50 μL/well) (BD Matrigel Basement Membrane Matrix, BD Biosciences) was added to the wells in a 96-well plate and allowed to polymerize at 37 °C for 30 min. HMEC-1 cells, an immortalised human microvascular endothelial cell line (34) (15,000 cells) previously transfected with siRNA-control or siRNA MC1R were added to the top of the Matrigel and treated with MC1R agonist BMS-470539. After incubation for 8 hr, tube formation was assessed by acquiring four random microscopic fields (magnification ×10) by using Nikon Eclipse Ti inverted microscope.…”

Advances in non-invasive biosensing measures to monitor wound healing progression

“…Optical coherence tomography scatters low-energy, highwavelength light within a specimen to construct an image of the tissue structure and offers high-resolution, multi-sectional Frontiers in Bioengineering and Biotechnology frontiersin.org imaging. This modality has been widely used, in both experimental and clinical settings, to visualize complex microarchitecture assemblies at the micrometer level and has been extensively reviewed (Cannon et al, 2022;Groux et al, 2022;Ji et al, 2022;Sanchez et al, 2022). With regards to ECM characterization, it allows for rapid quantification of the amount of ECM that has been produced, as well as identification of factors that affect production rate such as cell proliferation and assessment of collagen microchannels within the ECM (Bagnaninchi et al, 2007).…”

Segmentation and quantitative analysis of optical coherence tomography (OCT) images of laser burned skin based on deep learning

“…These suggest that deep learning has the potential advantages in the classification and identification of skin diseases over manual recognition. Applying deep learing in OCT to develop efficient, accurate, and automated evaluation and monitoring is an important direction for medical imaging (Gao et al 2022, Ji et al 2022.…”