Labeling cerebral vessels requires domain knowledge in neurology and could be extremely laborious, and there is a scarcity of public annotated cerebrovascular datasets. Traditional machine learning or statistical models could yield decent results on thick vessels with high contrast while having poor performance on those regions of low contrast. In our work, we employ a statistic model as noisy labels and propose a Transformer-based architecture which utilizes Hessian shape prior as soft supervision. It enhances the learning ability of the network to tubular structures, so that the model can make more accurate predictions on refined cerebrovascular segmentation. Furthermore, to combat the overfitting towards noisy labels as model training, we introduce an effective label extension strategy that only calls for a few manual strokes on one sample. These supplementary labels are not used for supervision but only as an indicator to tell where the model keeps the most generalization capability, so as to further guide the model selection in validation. Our experiments are carried out on a public TOF-MRA dataset from MIDAS data platform, and the results demonstrate that our method shows superior performance on cerebrovascular segmentation which achieves Dice of 0.831±0.040 in the dataset.

Emotional ability is an important symbol of human intelligence. Human’s understanding of emotions, from subjective consciousness to continuous or discrete emotional dimensions, and then to physiological separability, has shown a trend of gradually diverging from psychological research to the field of intelligent human-computer interaction. This article is aimed at studying the effects of smart sensor-based emotion recognition technology and badminton on physical health. It proposes a method of using smart sensor technology to recognize badminton movements and emotions during the movement. And the impact of emotion recognition based on smart sensors and badminton sports on physical health is carried out in this article. Experimental results show that the emotion recognition technology based on smart sensors can well recognize the changes in people’s emotions during badminton sports, and the accuracy of emotion recognition is higher than 70%. At the same time, experiments show that badminton can greatly improve people’s physical fitness and strengthen people’s physique.

No abstract

Automatically delineating Organs-at-Risks (OARs) on computed tomography (CT) has the benefit of both reducing the time and improving the quality of radiotherapy (RT) planning. A 3D convolutional deep learning framework for multi-organs segmentation is proposed in this work; moreover, for the small volume OARs, a robust 3D squeeze-and-excitation (SE) feature extraction mechanism and a new Dice loss function are incorporated in the traditional 3D U-Net. We collected 60 thorax CT images set with annotations and expanded to 260 patients by the augmented method of randomly rotating [Formula: see text]6 degrees with a 1/3 probability and adding Gaussian noise. The objective is to segment five important organs: esophagus, spinal cord, heart, and bilateral lungs. Compared with 3D U-Net, 3D-2D U-Net proposed in our work increases the Dice similarity coefficient by 5% on average for the heart and bilateral lungs, and 3D Small Volume U-Net can further increase the Dice similarity coefficient to above 80% for the spinal cord. The experiment results demonstrate that the proposed model can improve the delineation accuracy of OARs from CT images.

Objectives To describe the changes in serum folate concentration and assess the influence of individual methylenetetrahydrofolate reductase (MTHFR) C677T on the changes of serum folate concentration that resulted from 8 weeks of supplementation with folic acid in Chinese hypertensive patients.Methods We conducted a multicenter, randomized, double-blind controlled clinical trial of different dosages folate supplementation in Chinese hypertensive patients.A total of 1657 patients with mild or moderate essential hypertension were randomly assigned to one of eight treatment groups corresponding to eight different doses of folic acid, ranging from 0 mg to 2.4 mg,once daily for 8 weeks. Individual serum folate levels were measured at baseline, and at 4 and 8 weeks posttreatment.Results compared with patients with 677CC genotype, those with TT genotype had significantly lower folate concentrations at baseline.After 4 or 8 weeks of treatment, increases in serum folate were seen across all genotypes and FA dosage groups. At 8 weeks posttreatment ,there was no statistically significant difference in folate levels between groups according genotypes,and patients with CC genotype showed an attenuated response compared with those with TT genotype.( CC,0.45 vs. TT,0.56 ,P< 0.05).Conclusion We demonstrated that MTHFR C677T polymorphisms affected folate levels at the baseline and the therapeutic response of folic acid intervention. Patients with TT genotype benefited more after folic acid supplementation in Chinese hypertensive population.