http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Xinyu Yu,Liangtao Xia,Qingqing Jiang,Yupeng Wei,Xiang Wei,Shiyi Cao 대한뇌졸중학회 2020 Journal of stroke Vol.22 No.1
Background and Purpose Patients with aortic disease might have an increased risk of intracranial aneurysm (IA). We conducted this research to assess the prevalence of IA in patients with aortopathy, considering the impact of gender, age, and cardiovascular risk factors. Methods We searched PubMed and Scopus from inception to August 2019 for epidemiological studies reporting the prevalence of IA in patients with aortopathy. Random-effect meta-analyses were performed to calculate the overall prevalence, and the effect of risk factors on the prevalence was also evaluated. Anatomical location of IAs in patients suffered from distinct aortic disease was extracted and further analyzed. Results Thirteen cross-sectional studies involving 4,041 participants were included in this systematic review. We reported an estimated prevalence of 12% (95% confidence interval [CI], 9% to 14%) of IA in patients with aortopathy. The pooled prevalence of IA in patients with bicuspid aortic valve, coarctation of the aorta, aortic aneurysm, and aortic dissection was 8% (95% CI, 6% to 10%), 10% (95% CI, 7% to 14%), 12% (95% CI, 9% to 15%), and 23% (95% CI, 12% to 34%), respectively. Gender (female) and smoking are risk factors related to an increased risk of IA. The anatomical distribution of IAs was heterogeneously between participants with different aortic disease. Conclusions According to current epidemiological evidence, the prevalence of IA in patients with aortic disease is quadrupled compared to that in the general population, which suggests that an early IA screening should be considered among patients with aortic disease for timely diagnosis and treatment of IA.
An Effective Framework for Contented-Based Image Retrieval with Multi-Instance Learning Techniques
Yu Peng,Kun-Juan Wei,Da-Li Zhang 대한전자공학회 2007 JUCT : Journal of Ubiquitous Convergence Technolog Vol.1 No.1
Multi-Instance Learning(MIL) performs well to deal with inherently ambiguity of images in multimedia retrieval. In this paper, an effective framework for Contented-Based Image Retrieval(CBIR) with MIL techniques is proposed, the effective mechanism is based on the image segmentation employing improved Mean Shift algorithm, and processes the segmentation results utilizing mathematical morphology, where the goal is to detect the semantic concepts contained in the query. Every sub-image detected is represented as a multiple features vector which is regarded as an instance. Each image is produced to a bag comprised of a flexible number of instances. And we apply a few number of MIL algorithms in this framework to perform the retrieval. Extensive experimental results illustrate the excellent performance in comparison with the existing methods of CBIR with MIL.