Deep learning automatically assesses 2-µm laser-induced skin damage OCT images.

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.

Correlations between serum amyloid A, C-reactive protein and clinical indices of patients with acutely exacerbated chronic obstructive pulmonary disease.

BACKGROUND: To explore the correlations between SAA, CRP, and clinical indices of patients with acutely exacerbated chronic obstructive pulmonary disease (AECOPD). METHODS: A total of 120 patients with AECOPD and another 120 with remitted COPD were enrolled in an AECOPD group and a COPD remission group, respectively. Meanwhile, 120 healthy subjects were included as a control group. SAA, CRP, PCT, Fbg, IL-8, IL-6, TNF-α, and IP-10 levels were detected. FEV1 and FEV1 /FVC were measured. RESULTS: Compared with control group, the serum levels of SAA, CRP, PCT, Fbg, IL-8, IL-6, TNF-α, and IP-10 significantly increased in COPD remission group (P < 0.05). The levels of AECOPD group significantly exceeded those of COPD remission group (P < 0.05). The levels of AECOPD patients with different GOLD grades were significantly different (P < 0.05). AECOPD group had significantly lower FEV1 and FEV1 /FVC than those of COPD remission group (P < 0.05). The CAT score of AECOPD patients was (18.41 ± 2.55) points. The levels of SAA, CRP, PCT, Fbg, IL-8, IL-6, TNF-α, and IP-10 were negatively correlated with FEV1 and FEV1 /FVC, and positively correlated with CAT score. The area under receiver operating characteristic curve of SAA was largest (0.931). The cutoff values for SAA, CRP, PCT and Fbg were 18.68 mg/L, 14.70 mg/L, 0.39 µg/L, 3.91 g/L, 0.46 µg/L, 24.17 µg/L, 7.18 mg/L, and 83.19 ng/L, respectively. CONCLUSIONS: Serum levels of SAA, CRP, PCT, Fbg, IL-8, IL-6, TNF-α, and IP-10 in AECOPD patients were elevated, which may undermine pulmonary functions. SAA can be used as an effective index for AECOPD diagnosis and treatment.