IPD-Net: Infrared Pedestrian Detection Network via Adaptive Feature Extraction and Coordinate Information Fusion.

Infrared pedestrian detection has important theoretical research value and a wide range of application scenarios. Because of its special imaging method, infrared images can be used for pedestrian detection at night and in severe weather conditions. However, the lack of pedestrian feature information in infrared images and the small scale of pedestrian objects makes it difficult for detection networks to extract feature information and accurately detect small-scale pedestrians. To address these issues, this paper proposes an infrared pedestrian detection network based on YOLOv5, named IPD-Net. Firstly, an adaptive feature extraction module (AFEM) is designed in the backbone network section, in which a residual structure with stepwise selective kernel was included to enable the model to better extract feature information under different sizes of the receptive field. Secondly, a coordinate attention feature pyramid network (CA-FPN) is designed to enhance the deep feature map with location information through the coordinate attention module, so that the network gains better capability of object localization. Finally, shallow information is introduced into the feature fusion network to improve the detection accuracy of weak and small objects. Experimental results on the large infrared image dataset ZUT show that the mean Average Precision (mAP50) of our model is improved by 3.6% compared to that of YOLOv5s. In addition, IPD-Net shows various degrees of accuracy improvement compared to other excellent methods.

MTNet: A combined diagnosis algorithm of vessel segmentation and diabetic retinopathy for retinal images.

Medical studies have shown that the condition of human retinal vessels may reveal the physiological structure of the relationship between age-related macular degeneration, glaucoma, atherosclerosis, cataracts, diabetic retinopathy, and other ophthalmic diseases and systemic diseases, and their abnormal changes often serve as a diagnostic basis for the severity of the condition. In this paper, we design and implement a deep learning-based algorithm for automatic segmentation of retinal vessel (CSP_UNet). It mainly adopts a U-shaped structure composed of an encoder and a decoder and utilizes a cross-stage local connectivity mechanism, attention mechanism, and multi-scale fusion, which can obtain better segmentation results with limited data set capacity. The experimental results show that compared with several existing classical algorithms, the proposed algorithm has the highest blood vessel intersection ratio on the dataset composed of four retinal fundus images, reaching 0.6674. Then, based on the CSP_UNet and introducing hard parameter sharing in multi-task learning, we innovatively propose a combined diagnosis algorithm vessel segmentation and diabetic retinopathy for retinal images (MTNet). The experiments show that the diagnostic accuracy of the MTNet algorithm is higher than that of the single task, with 0.4% higher vessel segmentation IoU and 5.2% higher diagnostic accuracy of diabetic retinopathy classification.

Rare spindle cell hemangioma of bone: Case report and literature review.

Spindle cell hemangioma is a rare benign hemangioma. It is mainly found as small soft tissue nodules in the distal extremities, especially in the hands. The manifestation in bone is extremely rare. We present a case of spindle cell hemangioma of bone in the frontal bone. We also reviewed the literature to find the common imaging findings of intraosseous hamangiomas. The main manifestations of X-ray and CT were osteolytic lesions with soap bubble-like changes, and soft tissue mass formation. Magnetic resonance imaging mainly showed a lobulated mass with clear boundary, uneven hyperintense on T2WI, and obvious enhancement on contrast-enhanced scan. Surgical excision is curative. While this lesion is rare, it can be considered in the differential diagnosis if the characteristic imaging features are present.

Gastrodin Alleviates Cerebral Ischaemia/Reperfusion Injury by Inhibiting Pyroptosis by Regulating the lncRNA NEAT1/miR-22-3p Axis.

Cerebral ischaemia/reperfusion (I/R) injury-induced irreversible brain injury is a major cause of mortality and functional impairment in ageing people. Gastrodin (GAS), derived from the traditional Chinese herbal medicine Tianma, has been reported to inhibit the progression of stroke, but the mechanism whereby GAS modulates the progression of cerebral I/R remains unclear. The middle cerebral artery occlusion method was used as a model of I/R in vivo. Rats were pretreated with GAS by intraperitoneal injection 7 days before I/R surgery and were then treated with GAS for 7 days after I/R surgery. Additionally, an oxygen-glucose deprivation/reoxygenation model using neuronal cells was established in vitro to simulate I/R injury. 2,3,5-Triphenyltetrazolium chloride and Nissl staining were used to evaluate infarct size and neuronal damage, respectively. Lactate dehydrogenase release and cell counting kit-8 assays were used to assess neuronal cell viability. Enzyme-linked immunosorbent assay, qPCR, flow cytometry and western blotting were performed to analyse the expression levels of inflammatory factors (IL-1ß, IL-18), lncRNA NEAT1, miR-22-3p, NLRP3 and cleaved caspase-1. Luciferase reporter experiments were performed to verify the association between lncRNA NEAT1 and miR-22-3p. The results indicated that GAS could significantly improve the neurological scores of rats and reduce the area of cerebral infarction. Meanwhile, GAS inhibited pyroptosis by downregulating NLRP3, inflammatory factors (IL-1ß, IL-18) and cleaved caspase-1. In addition, GAS attenuated I/R-induced inflammation in neuronal cells through the modulation of the lncRNA NEAT1/miR-22-3p axis. GAS significantly attenuated cerebral I/R injury via modulation of the lncRNA NEAT1/miR-22-3p axis. Thus, GAS might serve as a new agent for the treatment of cerebral I/R injury.

Gastrodin combined with rhynchophylline inhibits cerebral ischaemia-induced inflammasome activation via upregulating miR-21-5p and miR-331-5p.

BACKGROUND: The protective effects of gastrodin and rhynchophylline in ischaemic injury have been reported. However, the underlying mechanism and the effect of the combination of these two drugs in ischaemic injury remain unclear. Herein, we aimed to explore the effects of the combination of gastrodin and rhynchophylline on ischaemia-induced inflammasome activation as well as the underlying mechanism. METHODS: Middle cerebral artery occlusion (MCAO) mice and oxygen glucose deprivation (OGD)-treated BV2 cells were used as in vivo and in vitro models of ischaemia, respectively. Cerebral injury was determined by TTC staining, H&E staining and neurological deficit scores. The effects of the combination of gastrodin and rhynchophylline on inflammasome activation were measured by the MTT assay, Western blotting and ELISA. The expression of miR-21-5p and miR-331-5p was measured by qRT-PCR. The potential binding between miR-21-5p and TXNIP and between miR-331-5p and TRAF6 was analysed with Targetscan and a luciferase assay. RESULTS: MCAO-induced tissue infarction, neurological deficits, inflammasome activation, and downregulation of miR-21-5p and miR-331-5p were all mitigated by the combination of gastrodin and rhynchophylline. In OGD-treated BV2 cells, the combination of gastrodin and rhynchophylline also alleviated inflammasome activation and restored the expression of miR-21-5p and miR-331-5p. TXNIP and TRAF6 were confirmed to be targets of miR-21-5p and miR-331-5p, respectively. Moreover, OGD-induced inflammasome activation was attenuated by the overexpression of either miR-331-5p or miR-21-5p and was further attenuated by the overexpression of both. Finally, we demonstrated that a miR-21-5p inhibitor and/or a miR-331-5p inhibitor counteracted the protective effects of gastrodin and/or rhynchophylline. CONCLUSIONS: The combination of gastrodin and rhynchophylline exerts neuroprotective effects by preventing ischaemia-induced inflammasome activation via upregulating miR-21-5p and miR-331-5p.

The protective role of lutein on isoproterenol-induced cardiac failure rat model through improving cardiac morphology, antioxidant status via positively regulating Nrf2/HO-1 signalling pathway.

Context: Lutein (LU) is a major carotenoid with various pharmacological activities including anti-inflammatory, antioxidant and anti-apoptosis. Objective: The cardioprotective efficacy of LU was determined by evaluating the biochemical and histopathological changes in isoproterenol (ISO) induced myocardial infarction (MI) rat model. Materials and methods: Healthy male albino rats (n = 40) were segregated into 4 equal groups. Group I (control) rats were administered with olive oil, Group II (LU) rats were orally pre-treated with only 40 mg of LU for 28 days, Group III (MI induced) rats were injected (subcutaneously; s.c) with 85 mg/kg of ISO for 2 consecutive days, whereas Group IV (LU + ISO) rats were pre-treated with 40 mg of LU for 28 days before ISO induction. Results: ISO-induced group showed increased infarct size and cardiac/inflammatory/apoptotic markers. However, pre-treatment with LU (28 days) considerably reduced (p < 0.01) the infarct size (14%), lipid peroxidation product (MDA;42%), cardiac markers [(lactate dehydrogenase (LDH) and creatine kinase-MB (CK-MB), cardiac troponin T (cTn T)], inflammatory markers [IL-1ß, IL-6, tumour necrosis factor alpha (TNF-α), nuclear factor kappa B p65 subunit (NF-κB p65)] and apoptotic markers (caspase-3 and -9). Also, LU significantly improved (p < 0.01) the antioxidants [catalase (CAT), superoxide dismutase (SOD)] as well as markedly upregulated (p < 0.01) the protein expression of HO-1 and Nrf2. Moreover, LU considerably reversed all the histopathological changes and thus exhibits its cardioprotective activity. Conclusion: LU exhibits potent cardioprotective activity against ISO-induced cardiotoxicity and might be recommended with standard cardioprotective agents for treating various MI-related complications.

Prevalence of diabetes and predictions of its risks using anthropometric measures in southwest rural areas of China.

BACKGROUND: To examine the prevalence of diabetes and prediabetes in Songming county, Yunnan province, South-west China and examine influences of anthropometric indicators on diabetic risk. METHODS: This study was a population based cross-sectional study of 1031 subjects in Songming County aged 30 years and older. Age-standardization was performed by using the 2010 Songming population as the standard population. After an overnight fasting, participants underwent an oral glucose tolerance test (OGTT), and venous blood glucose levels were measured to identify diabetes and prediabetes. Physicians completed questionnaires and blood pressure measurements; trained nurses measured anthropometric variables. Age-adjusted logistic regression models were used to assess the association between anthropometric variables and diabetes. RESULTS: Total prevalences of diabetes and prediabetes were 10.0% and 11.6%, respectively. In women, prevalence of diabetes and prediabetes significantly increased with body mass index (BMI),waist hip ratio (WHR), and waist-to-height ratio (WHtR). But in men, prevalence of diabetes and prediabetes only significantly increased with WHR and WHtR. Compared to 1st WHR tertile in women, there was a nearly tenfold increase in the risk of diabetes with 3rd WHR tertile (OR 10.50, 95% CI 3.95-27.86). Men with 3rd BMI tertile had 4.8-fold risk of getting diabetes compared to men with 1st WHtR tertile (OR 4.79, 95% CI 1.88-12.26). Only WHtR had significantly higher receiver operating characteristic (ROC) area than BMI in total men (0.668 vs. 0.561, p < 0.05). And in total women, only WHR had significantly higher ROC area than BMI (0.723 vs. 0.628, p < 0.05). In the partial correlation analysis controlling for waist circumference, only WHR had significant correlation with fasting plasma glucose (r = 0.132, p = 0.002) and 2-h plasma glucose (r = 0.162, p = 0.000) in women, and WHtR had a much stronger association with both fasting plasma glucose (r = 0.305, P = 0.000) and 2 h plasma glucose (r = 0.303, P = 0.000) than WHR in men. CONCLUSION: High prevalence of diabetes and prediabetes were found in this underdeveloped region. About half of total subjects with diabetes were undiagnosed. The association of obesity indices and diabetic risk factors varied with gender. The strongest predictors of diabetes were WHR for the female subgroup and WHtR for the male subgroup.