Application of the active shape model in a commercial medical device for bone densitometry

Osteoporosis is a common disorder characterised mainly by low bone mineral density (BMD), and leading to an increased risk of fracture. We have developed a new device that estimates BMD from ordinary hand radiographs. A crucial element of this method is the reconstruction of the metacarpals. This paper describes how this was solved using the active shape model (ASM). Standard ASM is unable to locate the metacarpal shafts in the direction along the bones. Therefore ASM was extended with a translation operator, which solved the problem. A hierarchical filtering method was used to construct a sufficient list of initial guesses for the ASM. The performance of ASM and the experience with the integration of ASM in a commercial medical device is reported. The ASM achieves 99.5% reconstruction success and is able to validate its own reconstruction in 97% of the cases. The system (Pronosco X-posure system, version 2.0) has been approved by the FDA, and more than 100 units have been sold.The concept of the translation operator is generalised to the more active shape model (MASM), which also allows a natural integration with the active appearance model.     

On optimal pairwise linear classifiers for normal distributions: the d-dimensional case

We consider the well-studied pattern recognition problem of designing linear classifiers. When dealing with normally distributed classes, it is well known that the optimal Bayes classifier is linear only when the covariance matrices are equal. This was the only known condition for classifier linearity. In a previous work, we presented the theoretical framework for optimal pairwise linear classifiers for two-dimensional normally distributed random vectors. We derived the necessary and sufficient conditions that the distributions have to satisfy so as to yield the optimal linear classifier as a pair of straight lines.In this paper we extend the previous work to d-dimensional normally distributed random vectors. We provide the necessary and sufficient conditions needed so that the optimal Bayes classifier is a pair of hyperplanes. Various scenarios have been considered including one which resolves the multi-dimensional Minsky’s paradox for the perceptron. We have also provided some three-dimensional examples for all the cases, and tested the classification accuracy of the corresponding pairwise-linear classifier. In all the cases, these linear classifiers achieve very good performance. To demonstrate that the current pairwise-linear philosophy yields superior discriminants on real-life data, we have shown how linear classifiers determined using a maximum-likelihood estimate (MLE) applicable for this approach, yield better accuracy than the discriminants obtained by the traditional Fisher's classifier on a real-life data set. The multi-dimensional generalization of the MLE for these classifiers is currently being investigated.     

用电阻网络对医用传感器的特性进行补偿

医用传感器的特性补偿方法非常多。文章介绍了采用简单的电阻网络对一些医用传感器的特性进行补偿的技术     

医疗档案的多条件随机组合查询

介绍一种医疗档案管理系统中的多条件随机组合查询程序的设计方法。     

Design of a Medical Non‐Linear Drilling Device: The Influence of Twist and Wear on the Fatigue Behaviour of NiTi Wires Subjected to Bending Rotation

This paper considers fundamental and experimental aspects associated with the engineering design of a medical, non‐linear drilling device which exploits shape memory pseudoelasticity of NiTi wires. For this application it is important that the NiTi wires have a good fatigue resistance. This is why the present authors have previously determined the influence of various parameters on cyclic life, crack growth and stress state of pseudoelastic wires subjected to bending rotation fatigue. The actual drilling device has to withstand twist in addition to bending rotation because the free rotation is constrained by friction between the drill head and the bone material. In addition, friction between the wire and a NiTi guiding tube results in wear and this may well promote fatigue crack nucleation. In this paper, we explain the function of the medical drill. We then report results on the effect of the additional parameters (1) twist and (2) wear on the fatigue life of thin pseudoelastic NiTi wires. We finally discuss the implications of our experimental results for the design process of the medical drilling device.     

高校医院保健机构开展社区卫生服务的思考

本文从高校医疗保健机构开展社区卫生服务的必要性和可行性出发,结合本校实际,对高校医疗保健机构的工作重点,深化改革,开展社区化服务提出了一些具体的措施和建议。     

核与辐射事件医学应急管理体系国际比较

介绍了我国核与辐射事件医学应急管理体系的构成,并将之与日本、美国、法国、俄罗斯和加拿大的核与辐射事件医学应急管理体系进行比较,分析其优缺点,同时介绍了WHO和IAEA在核与辐射事件医学应急中的作用,在此基础上提出建立健全我国核与辐射应急医学管理体系、提升医学应急救援能力的建议。     

三维医学可视化分析平台的研究

本文介绍西北大学可视化研究所研制的三维医学可视化分析系统。该系统可用于医学影像数据库、手术计划系统、远程会诊系统和计算机医学辅助教学系统的开发平台,为医学图像可视化提供了有力的工具。     

医保管理信息系统的研究与开发

文章介绍了医保管理信息系统的设计目标 ,着重分析了系统涉及适应性的主要不确定性因素 ,提出了相应的解决方案     

数字化医院的研究及核心解决方案

数字化医院是当前数字化进程中的一个重要分支，医院信息系统对于医院的发展提供了一个更为有效的发展平台，文中对于数字化医院进行了相关的研究，从当前医院信息系统中存在的挑战性问题入手，从需求分析和设计的角度分析了医院信息系统的框架结构和基本功能。