Search

BackgroundPneumonia and tuberculosis are prevalent pulmonary diseases globally, each demanding specific care measures. However, distinguishing between these two conditions imposes challenges due to the high skill requirements for doctors, the impact of imaging positions and respiratory intensity of patients, and the associated high healthcare costs, emphasizing the imperative need for intelligent and efficient diagnostic methods.MethodThis study aims to develop a highly accurate automatic diagnosis and classification method for various lung diseases (Normal, Pneumonia, and Tuberculosis). We propose a hybrid model, which is based on the InceptionV3 architecture, enhanced by introducing Deepwise Separable Convolution after the Inception modules and incorporating the Squeeze-and-Excitation mechanism. This architecture successfully enables the model to extract richer features without significantly increasing the parameter count and computational workload, thereby markedly improving the performance in predicting and classifying lung diseases. To objectively assess the proposed model, external testing and five-fold cross-validation were conducted. Additionally, widely used baseline models in the scholarly community were constructed for comparison.ResultIn the external testing phase, the our model achieved an average accuracy (ACC) of 90.48% and an F1-score (F1) of 91.44%, which is an approximate 4% improvement over the best-performing baseline model, ResNet. In the five-fold cross-validation, our model’s average ACC and F1 reached 88.27% ± 2.76% and 89.29% ± 2.69%, respectively, demonstrating exceptional predictive performance and stability. The results indicate that our model holds promise for deployment in clinical settings to assist in the diagnosis of lung diseases, potentially reducing misdiagnosis rates and patient losses.ConclusionUtilizing deep learning for automatic assistance in the diagnosis of pneumonia and tuberculosis holds clinical significance by enhancing diagnostic accuracy, reducing healthcare costs, enabling rapid screening and large-scale detection, and facilitating personalized treatment approaches, thereby contributing to widespread accessibility and improved healthcare services in the future.

Abstract Background Whether perceived stress is associated with loneliness and depressive symptoms in general adults, and to what extent sleep quality mediates the associations, remains unknown. The aim of this study was to estimate the associations of perceived stress with loneliness and depressive symptoms, and the mediating role of sleep quality in these associations. Methods Cross-sectional data on 734 participants (aged 18–87 years) were analyzed. Perceived stress was assessed using the 10-item Perceived Stress Scale (PSS-10; range 0–40). Sleep quality was assessed using the Pittsburgh Sleep Quality Index (PSQI; range 0–21). Loneliness was assessed using the three-item short form of the Revised University of California, Los Angeles (UCLA) loneliness scale (range 3–9). Depressive symptoms were assessed using the 10-item Center for Epidemiologic Studies Depression (CESD-10) Scale (range 0–30). General linear regression models, multivariable logistic regression models, and formal mediation analysis were performed. Results After adjustment for age and sex, we found that with each 1-point increment in the perceived stress score, both the loneliness score (β = 0.07; 95% confidence interval [CI]: 0.06, 0.08) and depression score (β = 0.45; 95% CI: 0.40, 0.49) increased significantly. Robust results were observed when adjusting for more confounders. Furthermore, sleep quality mediated 5.3% (95% CI: 1.3%, 10.0%; P = 0.014) and 9.7% (95% CI: 6.2%, 14.0%; P

Nitrogen (N) and phosphorus (P) fertilizers change the morphological structure and effectiveness of P in the soil, which in turn affects crop growth, yield, and quality. However, the effects and mechanism of combined N and P application on the content of P fractions and the transformation of effective forms in alfalfa (Medicago sativa L.) production is unclear. This experiment was conducted with four levels of N: 0 (N0), 60 (N1), 120 (N2) and 180 kg·ha-1 (N3); and two levels of P (P2O5): 0 (P0) and 100 kg·ha-1 (P1). The results indicated that, under the same N level, P application significantly increased soil total N, and total P, available P, and content of various forms of inorganic P when compared to no P application, while decreasing the content of various forms of organic P and pH value. In general, under P0 conditions, soil total N content tended to increase with increasing N application, while total P, available P content, pH, inorganic P content in all forms, and organic P content in all forms showed a decreasing trend. When compared to no N application, insoluble P (Fe-P, O-P, Ca10-P) of the N application treatments was reduced 2.80 - 22.72, 2.96 - 20.42, and 5.54 - 20.11%, respectively. Under P1 conditions, soil total N and O-P tended to increase with increasing N application, while, pH, Ca2-P, Al-P, Fe-P, Ca10-P, and organic P content of each form tended to decrease. Total P, available P, and labile organic P (LOP) of N application reduced 0.34 - 8.58, 4.76 - 19.38, and 6.27 - 14.93%, respectively, when compared to no application. Nitrogen fertilization reduced the soil Ca2-P ratio, while P fertilization reduced soil Fe-P, moderately resistant organic P (MROP), and highly resistant P (HROP) ratios, and combined N and P elevated the Ca8-P to LOP ratio. The results of redundancy analysis showed that soil total N content, available P content, and pH were the key factors affecting the conversion of P fractions in the soil. Nitrogen and P reduced the proportion of soil insoluble P, promoted the activation of soil organic P, resulting in accumulation of slow-acting P in the soil, thereby improving the efficiency of soil P in alfalfa production.

Solid state amplifier (SSA) has been increasingly applicated in accelerators facilities in recent years. However, with the improvement of the power level, equipment failure caused by reflected power becomes the main risk in long-term operation of SSA. A high-power SSA is usually composed of multiple power amplifier modules through power combiner nets. When the power amplifier modules with unequal amplitudes and SSA operate under a full reflection caused by arcing of the cavity, the modules may be easily damaged due to excessive reflected power. The optimization of the power combiners is an effective means for improving the stability of SSAs under high power reflection. In this paper, the mechanisms and conditions under which reflection power arises were analyzed by using the scattering parameter of the combiner, and the optimization scheme of the combiner to reduce the maximum reflected power was proposed. In addition, a set of 500 MHz 8-way power combiner experimental facility was designed to verify the result of theoretical calculation under various working conditions. Simulation and experimental results show that the reflected power of the power amplifier module not only is related to the matching state of SSA, but also is related to the output state of the power amplifier module itself and parameters of combiner. The total reflected power of the power amplifier module is the sum of the reflected power from the mismatched load and the combined power from the other modules. When all the power amplifier modules of the SSA working perfectly, the reflected power of its own signal of a module is exactly compensated by the sum of the power with opposite phase from all other modules. In this case, the reflected power of the module is only related to the matching state of the SSA, and its maximum value is equivalent to the rated output power of the module. In another case, when one of the SSA’s power amplifier modules is switched off, the reflected power received by some of the modules may be as high as nearly 4 times the rated power of a single module, which will lead to severe overloading of the circulator loads and risk of damage to the modules. Eventually, by optimizing the parameters of the combiner, the maximum reflection power is effectively reduced due to suppress in-phase superposition of the reflected power coupled form other modules. The experimental results are in good agreement with the theoretical calculations, which proves the effectiveness of the optimization scheme. Therefore, this research can provide some valuable references for the subsequent development of higher power SSA for CSNS, SAPS and other accelerator facilities.

ABSTRACT: The Wingless-types/beta-catenin (Wnt/β-catenin) signaling pathway plays an important role in embryonic development and affects the physiological development processes of feather follicles. To investigate the role of Wnt/β-catenin pathway in regulating feather follicles morphogenesis, in ovo injection of CHIR-99021, an activator of the Wnt/β-catenin signaling pathway, was conducted in chick embryo model. Initially, a total of 40 embryos were used to assess feather follicles morphogenesis and the expression of β-catenin (E9–E17). The histological results showed that feather follicle morphogenesis was mainly completed from E9 to E17. β-catenin was involved in the processing of the appearance of dermal cell condensation (E9) and the completion of the feather follicles morphogenesis (E17). Next, a total of 160 fertilized eggs were randomly divided into 8 groups for in ovo injection at E9, including a Normal Saline injected group (CON) and the 500, 1,000, 2,000, 5,000, 10,000, 50,000, and 100,000 ng CHIR-99021 groups. Dorsal skin tissue samples were collected at E17 for investigating feather follicles morphology and expressions of β-catenin and lymphoid enhancerbinding factor-1 (LEF1) at gene and protein levels. The results showed that feather follicle diameter in the injected groups were significantly (P < 0.05) increased with limit dose-independence compared to the CON group. CHIR-99021 significantly (P < 0.05) influenced the mRNA expressions of catenin beta-1 (CTNNB1) and downstream target LEF1. In ovo injection of CHIR-99021 caused that β-catenin and LEF1 were significantly (P < 0.05) increased followed the increased doses as determined by western blotting. The immunochemical results showed that β-catenin was detected in the dermal papilla of feather follicles. Given these results, this study suggests to developmental biology that in ovo injection of CHIR-99021 promoted feather follicles morphogenesis and development via activating Wnt/β-catenin signaling pathway and upregulating downstream target LEF1 during embryonic period in chick embryo model. Moreover, CHIR-99021 may be a strong candidate to promote the animal feather/hair industry, especially as a reference for bird feather production.