ABSTRACT
The new coronavirus disease 2019 (COVID19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread worldwide at a rapid rate. There is no clinically automated tool to quantify the infection of COVID-19 patients. Automatic segmentation of lung opacification from computed tomography (CT) images provides excellent potential, which is of great significance for judging the disease development and treatment response of the patients. However, the segmentation of lung opacification from CT slices still faces some challenges, including the complexity and variability features of the opacity regions, the small difference between the infected and healthy tissues, and the noise of CT images. Besides, due to the limited medical resources, it is impractical to obtain a large amount of data in a short time, which further hinders the training of deep learning models. To answer these challenges, we proposed a novel spatial and channel-wise coarse-to-fine attention network (SCOAT-Net) inspired by the biological vision mechanism, which is for the segmentation of COVID-19 lung opacification from CT Images. SCOAT-Net has the spatial-wise attention module and the channel-wise attention module to attract the self-attention learning of the network, which serves to extract the practical features at the pixel and channel level successfully. Experiments show that our proposed SCOAT-Net achieves better results compared to state-of-the-art image segmentation networks.
ABSTRACT
ObjectiveTo evaluate the value of 24 h dynamic electrocardiogram (DCG) and treadmill exercise testing(TET) in diagnosing coronary heart disease(CHD),and analyze relevant index between coronary arteriography(CAG) and treadmill exercise testing.MethodsOne hundred and forty-nine borderline cases of coronary heart disease were enrolled.Every patient was examined by DCG,TET,and CAG,compared the diagnostic value of TET combined with DCG and TET or DCG alone,and record the increased heart rate during the first minute( △ HRl min) of TET and systolic blood pressure(SBP) recovery.The patients were divided into a CHD group and a non-CHD group according to the results of coronary angiography.ResultsThe sensitivity rate was 78.57％ and specific rate was 70.77％ by means of TET.The sensitivity rate was 61.90％ and specific rate was 66.15％ by means of DCG.The sensitivity rate was 95.23％ ,specific rate was 55.38％,positive predictive value was 73.39％ and negative predictive value was 90.00％ by parallel way of DCG and TET,its sensitivity rate (95.23％) and negative predictive value (90.00％ ) were more than those of DCG or TET alone.The sensitivity rate was 52.38％,specific rate was 95.38％,positive predictive value was 93.62％ and negative predictive value was 60.78％ by serial way of DCG and TET,its specific rate (95.38％) and positive predictive value (93.62％ ) were more than those of DCG or TET alone.The number of men in the CHD group was higher than the number of women.Ratio of systolic blood pressure recovery(rSBPR) in the CHD group was significantly higher than that in the non-CHD group ( P ＜ 0.01 ).Conclusion It can obviously enhance the sensitivity rate and specific rate if combined TET with DCG.Patients with CHD have a delayed decline in SBP during recovery which can be one of the indexes to estimate the extent of myocardial ischemia and coronary artery lesion.
ABSTRACT
Objective To explore the relationship between serum thyrotropin and the components of metabolic syndrome.Methods A total of 1534 adult inhabitants in Dadong district of Shenyang were asked to fulfill the questionnaires and have physical examination and oral glucose tolerance test(OGTT).The vein blood was drawn to measure thyrotropin(TSH),fasting plasma glucose(FPG),OGTT 2hPG,fasting insulin,triglyceride(TG) and high density lipoprotein cholesterol(HDL-C).Results Serum TSH in the MS group was higher than in the Non-MS group(2.54 vs 2.22 mU/L,P
