Search

Abstract Automated coronary angiography assessment requires precise vessel segmentation, a task complicated by uneven contrast filling and background noise. Our research introduces an ensemble U-Net model, SE-RegUNet, designed to accurately segment coronary vessels using 100 labeled angiographies from angiographic images. SE-RegUNet incorporates RegNet encoders and squeeze-and-excitation blocks to enhance feature extraction. A dual-phase image preprocessing strategy further improves the model's performance, employing unsharp masking and contrast-limited adaptive histogram equalization. Following fivefold cross-validation and Ranger21 optimization, the SE-RegUNet 4GF model emerged as the most effective, evidenced by performance metrics such as a Dice score of 0.72 and an accuracy of 0.97. Its potential for real-world application is highlighted by its ability to process images at 41.6 frames per second. External validation on the DCA1 dataset demonstrated the model's consistent robustness, achieving a Dice score of 0.76 and an accuracy of 0.97. The SE-RegUNet 4GF model's precision in segmenting blood vessels in coronary angiographies showcases its remarkable efficiency and accuracy. However, further development and clinical testing are necessary before it can be routinely implemented in medical practice.

Abstract Large-artery atherosclerosis (LAA) is a leading cause of cerebrovascular disease. However, LAA diagnosis is costly and needs professional identification. Many metabolites have been identified as biomarkers of specific traits. However, there are inconsistent findings regarding suitable biomarkers for the prediction of LAA. In this study, we propose a new method integrates multiple machine learning algorithms and feature selection method to handle multidimensional data. Among the six machine learning models, logistic regression (LR) model exhibited the best prediction performance. The value of area under the receiver operating characteristic curve (AUC) was 0.92 when 62 features were incorporated in the external validation set for the LR model. In this model, LAA could be well predicted by clinical risk factors including body mass index, smoking, and medications for controlling diabetes, hypertension, and hyperlipidemia as well as metabolites involved in aminoacyl-tRNA biosynthesis and lipid metabolism. In addition, we found that 27 features were present among the five adopted models that could provide good results. If these 27 features were used in the LR model, an AUC value of 0.93 could be achieved. Our study has demonstrated the effectiveness of combining machine learning algorithms with recursive feature elimination and cross-validation methods for biomarker identification. Moreover, we have shown that using shared features can yield more reliable correlations than either model, which can be valuable for future identification of LAA.

Abstract Astaxanthin (AST), a super antioxidant with coloring and medical properties, renders it a beneficial feed additive for shrimp. This study conducted a white shrimp feeding trial of 3S, 3’S isoform AST, which was derived from metabolic-engineered Kluyveromyces marxianus fermented broth (TB) and its extract (TE) compared to sources from two chemically synthetic ASTs (Carophyll Pink [CP] and Lucantin Pink [LP]), which contain 3S, 3’S, 3R, 3’S (3S, 3’R) and 3R, 3’R isoforms ratio of 1:2:1. The effects on red coloration, immune parameters and resistance to Vibrio infection were evaluated. Four AST sources were incorporated into the diets at concentrations of 0 (control), 100 mg kg−1 (TB100, TE100, CP100, and LP100), and 200 mg kg−1 (TB200, TE200, CP200, and LP200). Results revealed that in week 4, shrimps that received AST-supplemented feeds, especially TB100, TB200, and TE200, significantly increased redness (a*) values. Immune responses including phagocytosis activity, superoxide-anion production, phenoloxidase activity, and immune-related genes were examined on days 0, 1, 2, 4, 7, 14, 21, and 28. Generally, shrimps that received AST-supplemented feeds exhibited higher immune responses on days 7 and 14 than the control feed. Gene expression levels of superoxide dismutase and glutathione peroxidase were significantly upregulated on days 7 and 14 in shrimps that received AST-supplemented feeds, while genes of penaeidins, antilipopolysaccharide factor, and lysozyme were upregulated on days 4, 7, and 14, especially received TB200 and TE200. Furthermore, shrimps that received TB100, TE100, CP100, and LP100 7 days were then challenged with Vibrio parahaemolyticus and the result demonstrated higher survival rates especially TB100 at 168 h than the control feed. In conclusion, incorporating AST into the diets enhanced shrimp red coloration, immune parameters, and resistance against V. parahaemolyticus infection. The K. marxianus-derived AST exhibited higher performance than did chemical AST to be a potential feed additive in shrimp aquaculture.

Abstract Spatial variations in tuna population and abundance are strongly linked to large-scale climate fluctuations, such as the Pacific decadal oscillation (PDO) and Atlantic multidecadal oscillation (AMO). However, the mechanisms underlying the association of climate indices with yellowfin tuna (YFT) abundance and habitat preference remain unclear. We analysed long-term longline fishery data for YFT and oceanic climate variability index data for 1971–2018. The standardized catch per unit effort (CPUE) of Indo-Pacific Ocean YFT was higher during negative AMO and positive PDO phases. In tropical Pacific Ocean, the trend of YFT habitat preference exhibited seesaw patterns because of the distinct environmental factors influenced by the PDO phase. The PDO changed the environmental parameters throughout the tropical Indian Ocean such that the habitat preference of YFT remained consistent throughout. However, the variations in habitat suitability did not correspond to the distribution or standardized CPUE of YFT throughout the Pacific Ocean during AMO events. Moreover, the changes in habitat suitability had a positive periodicity of 8–16 years with AMO in the Indian Ocean, but revealed opposite trends with the distribution or standardized CPUE of YFT. Our results provide sufficient information to distinguish the variations between PDO phase changing and YFT standardized CPUE/ habitat preference. Furthermore, the AMO phase shift period 60–100 years longer than that of the PDO (20–30 years), and models employing time series of fishery and environmental data must be extended the time period of our study to make the AMO match the fishery data more complete.