Automatic Segmentation of Laser-Induced Injury OCT Images Based on a Deep Neural Network Model

Optical coherence tomography (OCT) has considerable application potential in noninvasive diagnosis and disease monitoring. Skin diseases, such as basal cell carcinoma (BCC), are destructive; hence, quantitative segmentation of the skin is very important for early diagnosis and treatment. Deep neural networks have been widely used in the boundary recognition and segmentation of diseased areas in medical images. Research on OCT skin segmentation and laser-induced skin damage segmentation based on deep neural networks is still in its infancy. Here, a segmentation and quantitative analysis pipeline of laser skin injury and skin stratification based on a deep neural network model is proposed. Based on the stratification of mouse skins, a laser injury model of mouse skins induced by lasers was constructed, and the multilayer structure and injury areas were accurately segmented by using a deep neural network method. First, the intact area of mouse skin and the damaged areas of different laser radiation doses are collected by the OCT system, and then the labels are manually labeled by experienced histologists. A variety of deep neural network models are used to realize the segmentation of skin layers and damaged areas on the skin dataset. In particular, the U-Net model based on a dual attention mechanism is used to realize the segmentation of the laser-damage structure, and the results are compared and analyzed. The segmentation results showed that the Dice coefficient of the mouse dermis layer and injury area reached more than 0.90, and the Dice coefficient of the fat layer and muscle layer reached more than 0.80. In the evaluation results, the average surface distance (ASSD) and Hausdorff distance (HD) indicated that the segmentation results are excellent, with a high overlap rate with the manually labeled area and a short edge distance. The results of this study have important application value for the quantitative analysis of laser-induced skin injury and the exploration of laser biological effects and have potential application value for the early noninvasive detection of diseases and the monitoring of postoperative recovery in the future.

Classification of gastric cancerous tissues by a residual network based on optical coherence tomography images

Optical coherence tomography (OCT) is a noninvasive, radiation-free, and high-resolution imaging technology. The intraoperative classification of normal and cancerous tissue is critical for surgeons to guide surgical operations. Accurate classification of gastric cancerous OCT images is beneficial to improve the effect of surgical treatment based on the deep learning method. The OCT system was used to collect images of cancerous tissues removed from patients. An intelligent classification method of gastric cancerous tissues based on the residual network is proposed in this study and optimized with the ResNet18 model. Four residual blocks are used to reset the model structure of ResNet18 and reduce the number of network layers to identify cancerous tissues. The model performance of different residual networks is evaluated by accuracy, precision, recall, specificity, F1 value, ROC curve, and model parameters. The classification accuracies of the proposed method and ResNet18 both reach 99.90%. Also, the model parameters of the proposed method are 44% of ResNet18, which occupies fewer system resources and is more efficient. In this study, the proposed deep learning method was used to automatically recognize OCT images of gastric cancerous tissue. This artificial intelligence method could help promote the clinical application of gastric cancerous tissue classification in the future.

Evaluation of a 3.8-µm laser-induced skin injury and their repair with in vivo OCT imaging and noninvasive monitoring

To explore a 3.8-µm laser-induced damage and wound healing effect, we propose using optical coherence tomography (OCT) and a noninvasive monitoring-based in vivo evaluation method to quantitatively and qualitatively analyze the time-dependent biological effect of a 3.8-µm laser. The optical attenuation coefficient (OAC) is computed using a Fourier-domain algorithm. Three-dimensional (3-D) visualization of OCT images has been implemented to visualize the burnt spots. Furthermore, the burnt spots from the 3-D volumetric data was segmented and visualized, and the quantitative parameters of the burnt spots, such as the mean OACs, areas, and volumes, were computed. Then, OCT images and histological sections were analyzed to compare the structural changes. Within a certain radiation range, there is a linear relationship between radiation dose and temperature. Dermoscopic images, OCT images, and histological sections showed that, within a certain dose range, as the radiation doses increased, the cutaneous damage became more serious. One hour after laser radiation, the mean OACs increased and then decreased; the areas of burnt spots always increased and were 0.95 ± 0.07, 1.01 ± 0.06, 1.025 ± 0.07, 0.99 ± 0.07, 0.98 ± 0.07, 1.00 ± 0.07, 0.96 ± 0.05, and 0.98 ± 0.06 mm^-1, respectively; the areas were 2.10 ± 0.63, 3.75 ± 1.85, 5.95 ± 1.62, 8.35 ± 0.88, 9.44 ± 1.28, 10.29 ± 0.49, 12.27 ± 0.96, and 13.127 ± 1.90 mm²; and the volumes were 1.54 ± 0.41, 2.86 ± 0.09, 3.73 ± 0.49, 4.14 ± 0.80, 7.21 ± 0.52, 6.77 ± 0.45, 8.36 ± 0.25, and 10.65 ± 0.51 mm³; and 21 days after laser radiation, the volumes were 0.67 ± 0.18, 1.64 ± 0.08, 1.87 ± 0.12, 2.57 ± 0.34, 3.43 ± 0.26, 3.64 ± 0.04, 3.84 ± 0.15, and 4.16 ± 0.53 mm³, respectively. We investigated the time-dependent biological effect of 3.8-µm laser-induced cutaneous damage and wound healing using the quantitative parameters of OCT imaging and noninvasive monitoring. The real-time temperature reflects the photothermal effect during laser radiation of mouse skin. OCT images of burnt spots were segmented to compute the mean OACs, burnt area, and quantitative volumes. This study has the potential for in vivo noninvasive and quantitative clinical evaluation in the future.