Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategy

In this paper, segmentation of blood vessels from colour retinal images using a novel clustering algorithm with a partial supervision strategy is proposed. The proposed clustering algorithm, which is a RAdius based Clustering ALgorithm (RACAL), uses a distance based principle to map the distributions of the data by utilising the premise that clusters are determined by a distance parameter, without having to specify the number of clusters. Additionally, the proposed clustering algorithm is enhanced with a partial supervision strategy and it is demonstrated that it is able to segment blood vessels of small diameters and low contrasts. Results are compared with those from the KNN classifier and show that the proposed RACAL performs better than the KNN in case of abnormal images as it succeeds in segmenting small and low contrast blood vessels, while it achieves comparable results for normal images. For automation process, RACAL can be used as a classifier and results show that it performs better than the KNN classifier in both normal and abnormal images.     

基于关联规则与熵聚类的清热类中成药组方规律研究

目的:探讨常用清热类中成药组方规律。方法:收录《新编国家中成药》中清热类中成药处方,采用关联规则Apriori算法和复杂系统熵聚类等方法,确定处方中药物的使用频次及药物之间的关联规则等。结果:高频次药物包括甘草、黄芩、冰片、金银花、大黄、连翘等;高频次药物组合包括"甘草、黄芩""甘草、桔梗""连翘、金银花"等;置信度较高的关联规则包括"牛黄->冰片""桔梗->甘草""朱砂->冰片""栀子->黄芩"等。结论:处方用药中除常见的清热类中药外,尚包括具有清热作用的部分开窍药、安神药、泻下药及其他类药物。     

2012年顺义区手足口病聚集性疫情病例及重症病例病原学结果分析

目的：通过对手足口病聚集性病例和重症病例进行病原学检测,发现该地区手足口病原体的类型,为手足口病防控提供病原学依据。方法通过临床医生和流调人员采集符合聚集性疫情的手足口病病例和诊断为重症病例的咽拭子标本,应用RT-PCR方法检测原始样本和分离阳性病毒株中EV、EV71和CoxA16病毒的核酸。结果聚集性疫情病例咽拭子标本共276例,共分离出病毒125例,阳性率为45.29%;其中EV71阳性率为17.75%（49/276）,CoxA16阳性率为26.09%（72/276）,其他EV阳性率为1.45%（4/276）。重症病例咽式子标本共21例,共分离出病毒8例,阳性率为38.09%;其中EV71阳性率为9.52%（2/21）,CoxA16阳性率为23.81%（5/21）,其他EV阳性率为4.76%（1/21）。聚集性疫情病例中散居儿童、学生中CoxA16的检出率高于托幼儿童,其差异有统计学意义（χ2=3.843,P=0.050和χ2=8.048,P=0.005）。结论顺义区手足口病聚集性疫情病例和重症病例均以CoxA16病毒感染为主。聚集性疫情病例以托幼儿童为主,重症病例以散居儿童为主。应加强手足口病的病原学监测,为落实防控措施及明确临床诊断提供实验室依据。     

基于共词分析的我国医学信息学国际发文热点研究

以Web of Science为数据源,检索我国医学信息学领域国际发文量,利用SPSS20．0软件对文献关键词进行因子聚类分析,总结出6大研究主题：核医学图像数据库存储研究;计算机自然语言处理和文本挖掘在中国传统医学诊断中的运用;统计方法和计算机处理对临床医学和研究型数据的分析和系统构建;计算机和网络在医院信息系统、临床管理系统、护理系统研发与管理中的运用;统计方法和计算机技术在临床辅助检查心电图和临床疾病的治疗与诊断、临床决策中的运用;电子医学记录和健康记录的安全管理。     

Clustered data in sports research

Clustered, or dependent, data, arise commonly in sports medicine and sports science research, particularly in studies of sports injury and biomechanics, particularly in sports injury trials that are randomised at team or club level, in cross-sectional surveys in which groups of individuals are studied and in studies with repeated measures designs. Clustering, or positive correlation among responses, arises because responses and outcomes from the same cluster will usually be more similar than from different clusters. Study designs with clustering will usually required an increased sample size when compared to those without clustering. Ignoring clustering in statistical analyses can also lead to misleading conclusions, including incorrect confidence intervals and p-values. Appropriate statistical analyses for clustered data must be adopted. This paper gives some examples of clustered data and discusses the implications of clustering on the design and analysis of studies in sports medicine and sports science research.     

Growing Hierarchical Tree SOM: An unsupervised neural network with dynamic topology

In this paper we introduce a tree structured self-organizing network, called the Growing Hierarchical Tree SOM (GHTSOM), that combines unsupervised learning with a dynamic topology for hierarchical classification of unlabelled data sets. The main feature of the proposed model is a SOM-like self-organizing process that allows the network to adapt the topology of each layer of the hierarchy to the characteristics of the training set. In particular the self-organization is obtained in two steps: the first one concerns the learning phase and is finalized with the creation of a tree of SOMs, while the second one is in regard to the clustering phase and provides the formation of classes for each level of the tree (hence self-organization not only for training but also for the creation of topological connections). As a result the network works without the need for user-defined parameters. Experimental results are proposed on both synthetic and real data sets.     

Density equalized map projections: a method for analysing clustering around a fixed point

Cases plotted on a geopolitical map entail difficulties in interpretation and analysis because of variable population density in the study area. Density equalized map projections (DEMPs) eliminate the distribution of the resident population as an interfering influence by transforming map area to be proportional to population. This paper discusses a transformation algorithm, its properties, and develops statistical methods to detect clustering of cases around a fixed point for data plotted on DEMPs. We suggest two numeric methods where exact solutions are too complicated or do not exist. Finally, we illustrate these methods using data from Denver and Jefferson counties in Colorado to investigate whether lung cancer and leukaemia incidence patterns are associated with plutonium exposure from the Rocky Flats plant site.     

Consecutive outbreaks of Vibrio cholerae O139 and V. cholerae O1 cholera in a fishing village near Karachi, Pakistan

In July 2002 and June 2003, cholera outbreaks were detected by a diarrhoea surveillance system in a village outside Karachi, Pakistan. Specimens were culture confirmed. The first outbreak was caused by Vibrio cholerae O139 (n = 30) and the second outbreak by V. cholerae O1 (n = 39). Demographic and clinical features of patients were recorded and case-control studies were conducted following each outbreak. Clinical information was obtained for 29 of the 30 patients in the first outbreak, and 2 of the patients in the second outbreak were either out of the area or lost to follow-up, leaving 29 and 37 cases in the analysis for the first and second outbreak, respectively. Eighteen (49%) of the 37 V. cholerae O1 patients were under 2 years of age compared with 6 (21%) of the 29 V. cholerae O139 patients (P = 0.02). Vibrio cholerae O139-infected patients were more likely to be febrile (16/29) than those infected with V. cholerae O1 (2/37; P<0.001). A household contact with cholera was a risk factor in both outbreaks; water source was a risk factor in the first outbreak only. Geographically, cases were clustered during the first outbreak but not during the second. Person-to-person contact and water reservoirs appear to be the main transmission routes for cholera in this setting.