Dermoscopic Image Classification of Pigmented Nevus under Deep Learning and the Correlation with Pathological Features.

The objective of this study was to explore the image classification and case characteristics of pigmented nevus (PN) diagnosed by dermoscopy under deep learning. 268 patients were included as the research objects and they were randomly divided into observation group (n = 134) and control group (n = 134). Image recognition algorithm was used for feature extraction, segmentation, and classification of dermoscopic images, and the image recognition and classification algorithm were studied as the performance and accuracy of fusion classifier were compared. The results showed that the classifier was optimized, and the linear kernel accuracy was 85.82%. The PN studied mainly included mixed nevus, junctional nevus, intradermal nevus, and acral nevus. The sensitivity under collaborative training was higher than that under feature training and fusion feature training, and the differences among three trainings were significant (P < 0.05). The sensitivity of the observation group was 88.65%, and the specificity was 90.26%, while the sensitivity and the specificity of the control group were 85.65% and 84.03%, respectively; there were significant differences between the two groups (P < 0.05). In conclusion, dermoscopy under deep learning could be applied as a diagnostic way of PN, which helped improve the accuracy of diagnosis. The dermoscopic manifestations of PN showed a certain corresponding relationship with the type of cases and could provide auxiliary diagnosis in clinical practice. It could be applied clinically.

Toxicity mechanism of sevoflurane in neural stem cells of rats through DNA methylation.

The present study investigated the influence of sevoflurane on the cytotoxicity of neural stem cells of rats and deoxyribonucleic acid (DNA) methylation, and analyzed the correlation between degree of methylation and neurotoxicity of sevoflurane. Ten healthy Sprague-Dawley rats aged 6-8 weeks were randomly selected. The neural stem cells in the hippocampus of rats were isolated, followed by multiplication culture and induced differentiation. The nerve-related factors were observed and detected under a microscope. Moreover, the neural stem cells were treated with sevoflurane in different concentrations. Three wells were only added with the normal medium as the control group (C0), 3 wells were added with the low-concentration sevoflurane (0.2 g/ml) prepared by the medium as the low-concentration group (C1), 3 wells were added with the moderate-concentration of sevoflurane (0.5 g/ml) as the moderate-concentration group (C2), and 3 wells were added with the high-concentration sevoflurane (1 g/ml) as the high-concentration group (C3). The apoptosis rate was detected and calculated via Cell Counting Kit-8 (CCK-8) assay, the content of genomic DNA methylation in neural stem cells in each group was detected via high-performance liquid chromatography (HPLC), and the distribution of methylation in the chromosome in each group was compared. During the culture, neurospheres were produced, and the expression levels of four neural markers were increased. With the increase of sevoflurane concentration and the prolongation of time, the apoptosis rate of stem cells was increased. The content of methylation in cells treated with sevoflurane in a higher concentration was higher than that in other groups (P<0.05). According to the Pearsons correlation analysis, the content of methylation in neural stem cells was directly proportional to the concentration of sevoflurane. Methylation mostly occurred in the autosome, and the content of methylation in the high-concentration group was higher than those in the moderate-concentration, low-concentration and control groups (P<0.05). In conclusion, the concentration of sevoflurane can affect the degree of methylation in neural stem cells of rats and produce certain cytotoxicity.