No abstract

The quality of tongue images has a significant influence on the performance of tongue diagnosis in Chinese medicine. During the acquisition process, the quality of the tongue image is easily affected by factors such as the illumination, camera parameters, and tongue extension of the subject. To ensure that the quality of the collected images meet the diagnostic criteria of traditional Chinese Medicine practitioners, we propose a deep learning model to evaluate the quality of tongue images. First, we acquired the tongue images of the patients under different lighting conditions, exposures, and tongue extension conditions using the inspection instrument, and experienced Chinese physicians manually screened them into high-quality and unqualified tongue datasets. We then designed a multi-task deep learning network to classify and evaluate the quality of tongue images by adding tongue segmentation as an auxiliary task, as the two tasks are related and can promote each other. Finally, we adaptively designed different task weight coefficients of a multi-task network to obtain better tongue image quality assessment (IQA) performance, as the two tasks have relatively different contributions in the loss weighting scheme. Experimental results show that the proposed method is superior to the traditional deep learning tongue IQA method, and as an additional task of the network, it can output the tongue segmentation area, which provides convenience for follow-up clinical tongue diagnosis. In addition, we used network visualization to verify the effectiveness of the proposed method qualitatively.

Purpose: The effects of combing evolocumab and statin on the clinical outcome and physiological function of coronary arteries in STEMI patients with non-infarct-related artery (NIRA) disease are still unclear. Methods:355 STEMI patients with NIRA were enrolled in this study, who underwent combined anatomical and physiological assessments at baseline and after 12 months of treatment with statin monotherapy or statin plus evolocumab. Plaque composition and functional ischemia were determined via using the quantitative coronary angiography (QCA) and quantitative flow ratio (QFR). Results: Diameter stenosis and lesion length were significantly lower in the group undergoing statin plus evolocumab. While the group exhibited significantly higher minimum lumen diameter (MLD), and QFR values. Statin plus evolocumab (OR=0.350) and plaque lesion length (OR=1.223) were independently associated with rehospitalization for unstable angina (UA) within 12 months. Conclusion: Evolocumab combined with statin therapy can significantly improve the anatomical and physiological function of the coronary arteries and downregulate the re-hospitalization rate due to UA in STEMI patients with NIRA.

Identifying genes significantly related to diseases is a focus in the study of disease mechanisms. In this paper, from the perspective of integrated analysis and dynamic control, a method for identifying genes significantly related to diseases based on logic networks constructed by the LAPP method, referred to as NCCM, is proposed and applied to the study of the mechanism of acute myocardial infarction (AMI). It is found that 82.35% of 17 differential control capability genes (DCCGs) identified by NCCM are significantly correlated with AMI/MI in the literature and DISEASES database. The enrichment analysis of DCCGs shows that AMI is closely related to the positive regulation of vascular-associated smooth muscle cell proliferation and regulation of cytokine production involved in the immune response, in which HBEGF, THBS1, NR4A3, NLRP3, EDN1, and MMP9 play a crucial role. In addition, although the expression levels of CNOT6L and ACYP1 are not significantly different between the control group and the AMI group, NCCM shows that they are significantly associated with AMI. Although this result still needs further verification, it shows that the method can not only identify genes with large differences in expression but also identify genes that are associated with diseases but with small changes in expression.

The structural, optical and magnetic properties of BiFeO3, BiFe0.99Nb0.01O3 and Bi1 − xCaxFe0.99Nb0.01O3 (BCFNO, 0 ≤ x ≤ 0.25) nanoparticles synthesized via sol-gel method are investigated. It has been found that a phase transition from the rhombohedral R3c structure (x ≤ 0.10) to the ideal cubic perovskite structure (x = 0.25) which can be attributed to Ca2+ doping. Increasing Ca2+ dopants results in the increase of oxygen vacancies. As doping amount x increase, the band gap of BCFNO decreases and the valence band spectra indicates that it’s a p-type semiconductor, which indicates their favorable potential in photocatalytic applications. The remnant magnetization Mr of BCFNO reaches a maximum value (0.146 emu/g about 15 times compared with pure BFO) at x = 0.10. This enhancement of magneitic properties in BCFNO can be ascribed to the synergistic effect of A and B site ions co-doping. Higher valance Nb doping cause the size effect and the magnetic polarons bounded to the impurities by Ca ions.