Objective To apply the image recognition method based on distance graph convolutional network to the image processing of malaria-infected erythrocytes for realizing the multi-stage recognition of malaria and improving the diagnostic efficiency of malaria.Methods A multi-stage malaria recognition model based on distance graph convolutional network was proposed.A radial basis function was firstly added in KNN graph construction algorithm to construct adjacency matrix and assign weights to the nearest-neighbor nodes according to the similarity between nodes,so as to weaken the effects of the distant nearest-neighbor nodes on the central node.Then,attention mechanism was introduced to update adjacency matrix dynamically in the graph convolutional network for making the model pay attention to near-neighbor nodes with higher similarity,and finally the multi-stage image recognition of malaria-infected erythrocytes was completed.Results Validated on the Malaria-MIT dataset,the experimental results show that compared with original model,the proposed method improved accuracy,precision,recall rate and F1-score to 96.18%,96.23%,96.18%and 96.18%,respectively.Conclusion The proposed approach can effectively accomplish the task of multi-stage image recognition of malaria-infected erythrocytes.

To address the challenges of blurred boundaries and feature loss in the segmentation of small liver tumors in CT images,a novel model named BounDer-Net is proposed based on an improved ResUNet architecture.By constructing a Transformer-based dynamic multi-scale encoder and introducing a channel-spatial dual-path attention mechanism,the model can focus on tumor features across multiple dimensions.Additionally,the model adopts boundary-sensitive dynamic feature fusion strategy which effectively captures the heterogeneous features of tumors.BounDer-Net model firstly generates initial feature maps through low-level feature extraction,then inputs the features into a Transformer-based dynamic multi-scale encoder for extracting multi-level features,and finally restores spatial details via a decoder and improves the segmentation accuracy of small tumor boundaries using a boundary enhancement module.Experimental results on the LiTS2017 dataset show that BounDer-Net model achieves a Dice similarity coefficient of 94.64%,a mean intersection over union of 92.34%,and a Hausdorff distance of 0.35 mm,significantly outperforming existing methods.This study provides a reliable solution for the automatic diagnosis of small tumors in liver CT images.

To address the challenges of blurred boundaries and feature loss in the segmentation of small liver tumors in CT images,a novel model named BounDer-Net is proposed based on an improved ResUNet architecture.By constructing a Transformer-based dynamic multi-scale encoder and introducing a channel-spatial dual-path attention mechanism,the model can focus on tumor features across multiple dimensions.Additionally,the model adopts boundary-sensitive dynamic feature fusion strategy which effectively captures the heterogeneous features of tumors.BounDer-Net model firstly generates initial feature maps through low-level feature extraction,then inputs the features into a Transformer-based dynamic multi-scale encoder for extracting multi-level features,and finally restores spatial details via a decoder and improves the segmentation accuracy of small tumor boundaries using a boundary enhancement module.Experimental results on the LiTS2017 dataset show that BounDer-Net model achieves a Dice similarity coefficient of 94.64%,a mean intersection over union of 92.34%,and a Hausdorff distance of 0.35 mm,significantly outperforming existing methods.This study provides a reliable solution for the automatic diagnosis of small tumors in liver CT images.

Objective To apply the image recognition method based on distance graph convolutional network to the image processing of malaria-infected erythrocytes for realizing the multi-stage recognition of malaria and improving the diagnostic efficiency of malaria.Methods A multi-stage malaria recognition model based on distance graph convolutional network was proposed.A radial basis function was firstly added in KNN graph construction algorithm to construct adjacency matrix and assign weights to the nearest-neighbor nodes according to the similarity between nodes,so as to weaken the effects of the distant nearest-neighbor nodes on the central node.Then,attention mechanism was introduced to update adjacency matrix dynamically in the graph convolutional network for making the model pay attention to near-neighbor nodes with higher similarity,and finally the multi-stage image recognition of malaria-infected erythrocytes was completed.Results Validated on the Malaria-MIT dataset,the experimental results show that compared with original model,the proposed method improved accuracy,precision,recall rate and F1-score to 96.18%,96.23%,96.18%and 96.18%,respectively.Conclusion The proposed approach can effectively accomplish the task of multi-stage image recognition of malaria-infected erythrocytes.

Objective: To explore the role of TLR 9 in intrauterine transmission of hepatitis B virus (HBV) through blood pathway and placenta. Methods: Epidemiological investigation was carried out in 290 HBsAg positive parturients and 45 normal parturients (control group) in Northwest Women and Children Hospital of Shaanxi Province. Enzyme-linked immunosorbent assay (ELISA) was used to detect five serological makers of hepatitis B and TLR 9 levels in peripheral blood of pregnant women and newborns. HBV DNA was detected by real-time fluorescence quantitative PCR. Detection of TLR 9 expression in placenta by immunohistochemical method. A case-control study was conducted to analyze the difference of TLR 9 levels in placenta and peripheral blood of HBsAg- positive pregnant women with intrauterine transmission of HBV. Results: The incidence of dominant HBV infection (DBI), occult HBV infection (OBI) and intrauterine transmission of HBV were 9.28% (27/291), 40.21% (117/291) and 49.48% (144/291) respectively. (1) The level of TLR 9 in peripheral blood of HBsAg-positive parturients, non-HBV intrauterine transmission (NBIT) group and OBI group were significantly lower than that of control group (P<0.001). The level of TLR 9 in DBI group was significantly higher than those in NBIT group and OBI group (P=0.000). (2) The TLR 9 level in HBeAg-negative group was significantly lower than that in HBeAg-positive parturients in OBI group (P=0.01). (3) With the increased severity of intrauterine transmission of HBV in each HBV DNA load group, the TLR 9 level in maternal peripheral blood increased significantly (P<0.05). (4) With the increased severity of intrauterine transmission of HBV, the levels of TLR 9 increased significantly in antiviral therapy, immunoglobulin injection and non-hepatitis B vaccine groups (P<0.05). (5) The expression of TLR 9 in placenta tissues with DBI group was significantly higher than that in OBI group and NBIT group (P<0.05). Conclusions HBV can inhibit the secretion of TLR 9 in parturient to some extent, but HBeAg can stimulate the secretion of TLR 9. However, with the increased severity of intrauterine transmission of HBV, the level of TLR 9 in parturients is increased by intra-group cross-differentiation. Therefore, TLR 9 is not an independent marker for screening and grouping, but it can be used as an reference indicator for the monitoring and management of HBsAg-positive parturients.

Objective: To investigate the expression of IL-18 in peripheral blood of HBsAg positive parturients in intrauterine transmission of HBV. Methods: A case-control study was conducted in 282 HBsAg positive parturients and 43 health parturients (control group) in Northwest Women and Children Hospital of Shaanxi Province. Enzyme-linked immunosorbent assay (ELISA) was used to detect five serological makers of hepatitis B, real time PCR was used to detect HBV DNA, and flow liquid chip method was used to detect IL-18 levels in peripheral blood of parturients and newborns. Results: The incidence of dominant HBV infection (DBI), occult HBV infection (OBI) and intrauterine transmission of HBV were 8.42% (24/285), 40.00% (114/285) and 48.42% (138/285), respectively. The level of IL-18 in peripheral blood of HBsAg-negative parturients were significantly lower than those of HBsAg-positive parturients (P=0.001), non-HBV intrauterine transmission (NBIT) group (P=0.001) and OBI group (P<0.001). The level of IL-18 in HBeAg negative group was significantly lower than that in HBeAg positive group (P=0.023). When HBV DNA load was ≥10³ copies/ml, the level of IL-18 was significantly higher than that in HBsAg-negative group (P<0.01). With the increase of HBV DNA load in maternal blood, the level of IL-18 increased (P=0.024). When HBV DNA load was 10³-10⁶ copies/ml, the level of IL-18 in DBI group was significantly lower than that in NBIT group (P=0.022), and increased with the increase of HBV DNA load in maternal blood (P=0.016). With the increased severity of intrauterine transmission of HBV, the level of IL-18 in non-hepatitis B vaccine group decreased significantly (P=0.044). The level of IL-18 in non-hepatitis B vaccine group and immunoglobulin injection group was significantly higher than that in NBIT group (P<0.05). Multivariate analysis showed that the linear relationship between maternal HBeAg status and maternal IL-18 levels had statistical significance (P=0.01). Conclusions IL-18 is a higher level balance regulator of Th1/Th2 immune network. Monitoring the level of IL-18 in HBsAg-positive parturients can be used not only for predicting the probability of DBI and OBI, but also as an intervention mean, especially for those who are HBeAg-positive and had HBV DNA load ≥10³ copies/ml, to improve maternal cellular immune function, which is conducive to interrupting intrauterine transmission and providing a theoretical basis for the prevention and control of HBV intrauterine transmission.

Objective: To investigate the influence of IFN-γ and IL-12 levels in prenatal peripheral blood of HBsAg-positive parturients on intrauterine transmission of hepatitis B virus (HBV). Methods: A case-control study was conducted in 282 HBsAg positive parturients and 43 health parturients (control group) in Northwest Women and Children Hospital of Shaanxi Province. Enzyme-linked immunosorbent assay (ELISA) was used to detect five serological makers of hepatitis B in peripheral blood of parturients. HBV DNA was detected by real-time fluorescence quantitative PCR. Detection of cytokines IFN-γ and IL-12 levels were conducted with liquid chip-based flow cytometry method. The serum levels of five serological markers of hepatitis B and HBV DNA in 285 newborns were detected within 24 hours after birth. Results: The incidence of intrauterine dominant infection (DBI), occult infection (OBI) and intrauterine transmission of HBV in HBsAg positive parturients were 7.37% (21/285), 40.70% (116/285) and 48.07% (137/285), respectively. The level of IFN-γ in peripheral blood of HBsAg-negative parturients was significantly lower than those of HBsAg-positive parturients (t=-2.55, P=0.011), NBIT group (t=-2.54, P=0.012) and OBI group (t=-2.33, P=0.021). In HBV DNA load of 10³-10⁶ copies/ml group, the levels of IFN-γ in the DBI group were significantly lower than those in OBI group and NBIT group (P<0.01). The level of IFN-γ in maternal peripheral blood decreased significantly with the increased severity of intrauterine transmission of HBV (χ²=6.40, P=0.041). In the antiviral treatment group, the level of IL-12 in maternal peripheral blood decreased significantly with the increased severity of intrauterine transmission of HBV (χ²=8.90, P=0.012). Multivariate analysis showed that there was a significant linear relationship between maternal IFN-γ level and maternal age, placenta previa and hepatitis B vaccine injection (P<0.05). The linear relationship between the level of maternal IL-12 and the mode of rupture and hepatitis B vaccine injection had statistical significance (P<0.05). Conclusions HBV can stimulate the expression of IFN-γ and inhibit the secretion of IL-12 in pregnant and lying-in women, but the expression of IFN-γ in HBsAg-positive parturients showed intra-group differentiation, and the maternal level of IFN-γ will decrease in HBeAg-positive and high-HBV DNA loadstatus. Increasing the levels of IFN-γ and IL-12 in HBsAg-positive parturients is beneficial to block intrauterine transmission of HBV, especially DBI.