Deep learning automatically assesses 2-µm laser-induced skin damage OCT images
Authors:
- 18 April 2024
- journal article
- research article
- Published by Springer Nature in Lasers in Medical Science
- Vol. 39 (1) , 1-11
Abstract
The present study proposed a noninvasive, automated, in vivo assessment method based on optical coherence tomography (OCT) and deep learning techniques to qualitatively and quantitatively analyze the biological effects of 2-µm laser-induced skin damage at different irradiation doses. Different doses of 2-µm laser irradiation established a mouse skin damage model, after which the skin-damaged tissues were imaged non-invasively in vivo using OCT. The acquired images were preprocessed to construct the dataset required for deep learning. The deep learning models used were U-Net, DeepLabV3+, PSP-Net, and HR-Net, and the trained models were used to segment the damage images and further quantify the damage volume of mouse skin under different irradiation doses. The comparison of the qualitative and quantitative results of the four network models showed that HR-Net had the best performance, the highest agreement between the segmentation results and real values, and the smallest error in the quantitative assessment of the damage volume. Based on HR-Net to segment the damage image and quantify the damage volume, the irradiation doses 5.41, 9.55, 13.05, 20.85, 32.71, 52.92, 76.71, and 97.24 J/cm² corresponded to a damage volume of 4.58, 12.56, 16.74, 20.88, 24.52, 30.75, 34.13, and 37.32 mm³. The damage volume increased in a radiation dose-dependent manner.Keywords
This publication has 33 references indexed in Scilit:
- A systematic review and meta-analysis of efficacy, safety, and satisfaction rates of laser combination treatments vs laser monotherapy in skin rejuvenation resurfacingLasers in Medical Science, 2023
- Pulmonary nodule detection based on Hierarchical-Split HRNet and feature pyramid network with atrous convolutionBiomedical Signal Processing and Control, 2023
- A holistic overview of deep learning approach in medical imagingMultimedia Systems, 2022
- Evaluation of a 3.8-µm laser-induced skin injury and their repair with in vivo OCT imaging and noninvasive monitoringLasers in Medical Science, 2021
- Imaging sebaceous gland using optical coherence tomography with deep learning assisted automatic identificationJournal of Biophotonics, 2021
- Quantitative analysis of collagen and capillaries of 3.8-μm laser-induced cutaneous thermal injury and wound healingLasers in Medical Science, 2020
- Improving imaging depth by dynamic laser speckle imaging and topical optical clearing for in vivo blood flow monitoringLasers in Medical Science, 2020
- Signs of the Biological Effect of ~2 μm Low-Intensity Laser Radiation in Raman and Absorption Spectra of BloodJournal of Applied Spectroscopy, 2016
- Actively Q-switched, diode pumped thulium laserLaser Physics Letters, 2007
- Methods for imaging the structure and function of living tissues and cells: 1. Optical coherence tomographyThe Journal of Pathology, 2000