GA-Net: Ghost convolution adaptive fusion skin lesion segmentation network.

Automatic segmentation of skin lesions is a pivotal task in computer-aided diagnosis, playing a crucial role in the early detection and treatment of skin cancer. Despite the existence of numerous deep learning-based segmentation methods, the extraction of lesion features remains inadequate as a result of the segmentation process. Consequently, skin lesion image segmentation continues to face challenges regarding missing detailed information and inaccurate segmentation of the lesion region. In this paper, we propose a ghost convolution adaptive fusion network for skin lesion segmentation. First, the neural network incorporates a ghost module instead of the ordinary convolution layer, generating a rich skin lesion feature map for comprehensive target feature extraction. Subsequently, the network employs an adaptive fusion module and bilateral attention module to connect the encoding and decoding layers, facilitating the integration of shallow and deep network information. Moreover, multi-level output patterns are used for pixel prediction. Layer feature fusion effectively combines output features of different scales, thus improving image segmentation accuracy. The proposed network was extensively evaluated on three publicly available datasets: ISIC2016, ISIC2017, and ISIC2018. The experimental results demonstrated accuracies of 96.42%, 94.07%, and 95.03%, and kappa coefficients of 90.41%, 81.08%, and 86.96%, respectively. The overall performance of our network surpassed that of existing networks. Simulation experiments further revealed that the ghost convolution adaptive fusion network exhibited superior segmentation results for skin lesion images, offering new possibilities for the diagnosis of skin diseases.

[Colorectal polyp segmentation method based on fusion of transformer and cross-level phase awareness].

In order to address the issues of spatial induction bias and lack of effective representation of global contextual information in colon polyp image segmentation, which lead to the loss of edge details and mis-segmentation of lesion areas, a colon polyp segmentation method that combines Transformer and cross-level phase-awareness is proposed. The method started from the perspective of global feature transformation, and used a hierarchical Transformer encoder to extract semantic information and spatial details of lesion areas layer by layer. Secondly, a phase-aware fusion module (PAFM) was designed to capture cross-level interaction information and effectively aggregate multi-scale contextual information. Thirdly, a position oriented functional module (POF) was designed to effectively integrate global and local feature information, fill in semantic gaps, and suppress background noise. Fourthly, a residual axis reverse attention module (RA-IA) was used to improve the network's ability to recognize edge pixels. The proposed method was experimentally tested on public datasets CVC-ClinicDB, Kvasir, CVC-ColonDB, and EITS, with Dice similarity coefficients of 94.04%, 92.04%, 80.78%, and 76.80%, respectively, and mean intersection over union of 89.31%, 86.81%, 73.55%, and 69.10%, respectively. The simulation experimental results show that the proposed method can effectively segment colon polyp images, providing a new window for the diagnosis of colon polyps.

Maternal pre-pregnancy/early-pregnancy smoking and risk of congenital heart diseases in offspring: A prospective cohort study in Central China.

Background: Prior studies suggested that maternal smoking before and during pregnancy could be associated with increased risks of congenital heart diseases (CHDs) in offspring. However, the results were inconsistent, and the existence of a causal relationship was not confirmed. Our study aimed to estimate the associations of maternal active and passive smoking during the pre-pregnancy/early-pregnancy period with CHDs as well as its common phenotypes in offspring. Methods: This study was based on data from a prospective cohort study conducted in Central China. A total of 49 158 eligible pregnant women between the 8th and 14th weeks of gestation were invited to join the cohort and were planned to be followed up until 3 months postpartum. The exposure of interest was maternal smoking status, including active and passive smoking status in 3 months before pregnancy as well as in early pregnancy. Self-reported maternal smoking status was ascertained via an in-person interview after recruitment. CHDs were diagnosed by pediatric cardiologists and classified according to ICD-10. Multivariable Poisson regression models were used to estimate the relative risks (RRs) with 95% confidence intervals (CIs) of all CHDs and their common phenotypes associated with maternal smoking status, adjusting for potential confounding factors identified by directed acyclic graphs. Results: CHDs were diagnosed in 564 children. After adjusting for potential confounding factors and comparing with the unexposed groups, CHDs incidence was 165% higher (adjusted RR = 2.65; 95% CI = 1.76-3.98) in offspring exposed to maternal active smoking in 3 months before pregnancy, 69% higher (adjusted-RR = 1.69; 95% CI = 1.39-2.05) in offspring exposed to maternal passive smoking in 3 months before pregnancy, 133% higher (adjusted RR = 2.33; 95% CI = 1.46-3.70) for offspring exposed to maternal active smoking in early pregnancy, and 98% higher (adjusted-RR = 1.98; 95% CI = 1.56-2.51) for offspring exposed to maternal passive smoking in early pregnancy. More specifically, the offspring exposed to maternal active smoking in early pregnancy had the highest risk of Tetralogy of Fallot (adjusted RR = 9.84; 95% CI = 2.49-38.84). These findings were recapitulated in analyses that further adjusted for other behaviour variables apart from the characteristic being assessed and were also confirmed by sensitivity analyses. Conclusions: Our findings add to the existing body of evidence that implicates maternal pre-pregnancy/early-pregnancy smoking as a significant risk factor for CHDs and their select phenotypes.

[Association between maternal reduced folate carrier gene polymorphisms and congenital heart disease in offspring: a case-control study].

OBJECTIVE: To study the association between maternal reduced folate carrier (RFC) gene polymorphisms and congenital heart disease (CHD) in offspring. METHODS: A hospital-based case-control study was conducted. The mothers of 683 infants with CHD who attended the Department of Cardiothoracic Surgery, Hunan Children's Hospital, from November 2017 to March 2020 were enrolled as the case group. The mothers of 740 healthy infants without any deformity who attended the hospital during the same period of time were enrolled as the control group. A questionnaire survey was performed to collect the exposure data of subjects. Venous blood samples of 5 mL were collected from the mothers for genetic polymorphism detection. A multivariate logistic regression analysis was used to evaluate the association of RFC gene polymorphisms and their haplotypes with CHD. A generalized multifactor dimensionality reduction method was used to analyze gene-gene interactions. RESULTS: After control for confounding factors, the multivariate logistic regression analysis showed that maternal RFC gene polymorphisms at rs2236484 (AG vs AA:OR=1.91, 95%CI:1.45-2.51; GG vs AA: OR=1.96, 95%CI:1.40-2.75) and rs2330183 (CT vs CC:OR=1.39, 95%CI:1.06-1.83) were significantly associated with the risk of CHD in offspring. The haplotypes of G-G (OR=1.21, 95%CI:1.03-1.41) and T-G (OR=1.25, 95%CI:1.07-1.46) in mothers significantly increased the risk of CHD in offspring. The interaction analysis showed significant gene-gene interactions between different SNPs of the RFC gene in CHD (P < 0.05). CONCLUSIONS: Maternal RFC gene polymorphisms and interactions between different SNPs are significantly associated with the risk of CHD in offspring.

Mother-to-child transmission prevention of human immunodeficiency virus, syphilis and hepatitis B virus.

BACKGROUND: China is the first country to initiate a nationwide program for prevention of mother-to-child transmission of human immunodeficiency virus, syphilis and hepatitis B virus by an integrated approach. However, the progress of this program remains unreported at national or local level for China. Therefore, we performed a hospital-based longitudinal study to assess the integrated prevention effect in Hunan, South-central China. METHODS: This study was conducted at 123 counties in Hunan and covered all local hospitals providing midwifery and antenatal care services from 2010 to 2016. We used the Cochran-Armitage test to examine the temporal changes of the indicators related with prevention of mother-to-child transmission. Besides, we used Spearman rank correlation analysis to assess the association between mother-to-child transmission rates and the process indicators related with prevention of mother-to-child transmission. RESULTS: After implementation of integrated prevention program, the indicators related with prevention of mother-to-child transmission are moving in the right direction. From 2010 to 2016, mother-to-child transmission rates significantly decreased from 19.4% to 9.6% for human immunodeficiency virus, and from 116.3 to 13.6 cases per 100,000 live births for syphilis. The proportion of children receiving hepatitis B immunoglobulin injection within 24h after birth increased from 95.2% to 98.9% among exposed neonates. Mother-to-child transmission rates were negatively associated with the process indicators related with prevention of mother-to-child transmission (all P<0.05). CONCLUSIONS: Our prevention program of mother-to-child transmission for three diseases by an integrated approach proved to be viable and effective. Our model may be of interest to other countries.

Gas chromatography-mass spectrometric method-based urine metabolomic profile of rats with pelvic inflammatory disease.

Pelvic inflammatory disease (PID) can lead to a poor outcome of severe sequelae, and the current methods of clinical diagnosis are not satisfactory. Metabolomics is an effective method for the identification of disease-related metabolite biomarkers to facilitate disease diagnosis. However, to the best of our knowledge, no PID-associated metabolomic study has yet been carried out. The metabolomic changes of rats with PID were investigated in the present study. A PID model was constructed by the multi-pathogenic infection of the upper genital tract in rats. Infiltration of inflammatory cells and elevated expression levels of the cytokines interleukin (IL)-1ß and IL-6 in the uterus and fallopian tubes validated the disease model. Gas chromatography-mass spectrometry coupled with derivatization was used to determine the urine metabolomic profile. Principal component analysis and partial least squares-discriminant analysis of the data sets showed a clear separation of metabolic profiles between rats with PID and control rats. Eighteen differentiating metabolites were found, including four amino acids, three fatty acids, nine organic acids, and two sugars, which indicated alterations in sugar metabolism, the citric acid cycle, amino acid metabolism and fatty acid metabolism. These metabolites could be potential biomarkers of PID, and this research may offer a new approach to evaluate the effect of anti-PID drugs in pre-clinical or clinical trials.