浅谈卫生统计信息系统建设

现代社会,人们对卫生统计数据和信息的需求量越来越大,大量的公共卫生管理决策活动已无法离开卫生统计信息的支持.卫生统计信息系统应以计算机和网络为工具,运用多种方法,对卫生统计信息收集、存储、分析、加工、传递和使用,把统计人员从繁重的手工作业中解放出来,提高了卫生统计工作的质量、效率和水平,使卫生统计工作现代化和科学化,提高卫生统计信息对公共卫生管理的决策支持能力,实现卫生统计信息的资源共享.     

Digital Scan在医学影像数字化中的应用

现代计算机及相关技术的迅速发展为医学影像的数字化处理、存储、传输提供了方便.医学影像数字化是当今医学影像技术发展的趋势和需要.对已有的传统医学影像胶片进行数字化处理是医学图像信息进入全面数字化管理系统所必须完成的工作,是为PACS和HIS系统服务.     

一种符合医学数字影像与通讯标准的医学影像管理系统的设计

医学影像的存储与传输在数字化医疗快速发展的今天占据着非常重要的地位。为了实现医学数字影像与通讯（DICOM）医学影像在局域网上的传输和查询,本文设计了一个符合DICOM标准的医学影像管理系统。该系统能对DICOM格式文件进行解析,并在数据库中把DICOM影像文件与对应的病历信息进行关联存储,可以给医院影像科提供完全数字化的影像和数据。此研究工作不仅满足了医院影像中心对大量影像数据存储的需求,同时也促进了PACS系统的发展。     

医学影像归档系统在我院的实现

1　建立医学影像归档系统的意义“PACS”系统 (Picture Archiving and Comm unicationSystem)即医学影像归档及通讯系统 ,它将现代的电子计算机技术应用到医学影像的处理、存储、传输当中 ,采用数字技术将各种类型、不同型号的医学影像设备的图像信息采集并转换成统一的医学图像文件格式 ,可以普通的计算机上进行医学影像的浏览、存储、管理和传输 ,使临床医生通过医生工作站可以即时查阅医学影像信息 ,获得以往只有影像科室才能看到的医学影像资料 ,实现医学影像资源的共享 ,降低了诊断成本 ,并可实现方便且成本极低的远程会诊功能 ,提…     

基于人工智能的正位DR胸片质控体系研究与应用

随着医学诊断、治疗模式的改变,医学影像的质量直接影响着医生对病情的诊断和治疗。因此,通过计算机实现智能影像质控对放射科技师的拍片工作会有较大的辅助作用。本文拟就深度学习领域中的图像分割模型、图像分类模型结合传统图像处理算法应用于医学影像质量评价的研究方法及应用情况予以阐述。我们发现使用深度学习算法对医学影像大数据进行有效训练,提取出来的特征相比于单纯使用传统图像处理算法更加准确、高效,诠释了深度学习在医疗领域的广阔应用前景。本文开发出了一套辅助拍片智能质控系统,并成功应用到了华西医院和其他市、县级医院的放射科,有效验证了该质控系统的可行性与稳定性。     

面向临床研究主题服务的医学影像数据库研制

研制面向临床研究主题服务的医学影像数据库,建立数据库制作流程,实现医学影像按疾病分类存储和在线服务。首先进行医学影像数据库建设的需求分析和数据资源调查,围绕临床研究主题需求设计医学影像数据库的系统结构。然后,应用"数据库—样本数据—影像文件"三级信息组织模型、基于DICOM标准的医学影像数据处理、"数据库索引+Zip文件"的影像文件管理与缓存机制等技术实现该系统。系统支持DICOM、JPG等多种图像格式和组合查询模式,测试运行取得良好效果。     

PACS系统与远程医学影像教学

随着计算机科学与医疗设备的迅猛发展 ,数字化图像技术与现代通讯及计算机技术相结合 ,形成了 PACS(Pic-ture Archiving and Com munication System,影像存储及传输系统 )。它将医学图像资料转化为数字信息 ,通过高速计算机设备及通讯网络 ,完成对图像信息的采集、存储、管理、处理及传输功能 ,使图像资料得以有效管理和充分利用。在更好地为临床医疗服务的同时 ,也为医学影像教学提供了更先进的手段 ,使医学影像教学在原有的基础上又提高了一个层次。 PACS与幻灯、投影、胶片等传统教学媒体相结合 ,使教员讲课更加生动、形象、方便 ,…     

PACS课程实验教学内容初探

目的：PACS是医学影像获取、存储、显示、处理、传输和管理的技术综合与集成。它基于现代计算机和网络通讯技术,以数字化方式获取、管理、应用和共享医学影像和诊断信息。结合实践教学提高大学生全面、综合的PACS知识素质与技能越来越得到重视。因此,本文对高校PACS课程实验教学内容进行初步研究和探索。方法：在分析PACS技术特点及其实践教学重要性的基础上,本文主要从医学信息标准、数字化医学影像应用、医学影像设备和计算机软硬件技术与网络通讯等四方面对PACS课程实验内容进行探索。结果：较为详细地描述了PACS在医学信息标准、数字化医学影像应用、医学影像设备和计算机软硬件技术与网络通讯各技术层面相应的实验内容。结论：本文对于PACS系统课程所需要开展的实验内容进行了初步的研究和探索。由于PACS系统的技术复杂性和临床应用领域的特殊性．目前社会上对PACS课程在实验教学内容设置方面的研究成果较少。虽然文中所提出的实验内容在合理性和实际可行性方面都需要进一步完善提高,但该研究成果具有相当的启发意义和价值。     

人工智能在医学影像诊断中的应用

人工智能在处理大数据、复杂非确定性数据、深入挖掘数据潜在信息等方面有着超越人类的优势。医学影像数据包含丰富的人体健康信息,是医生做出医学诊断的重要依据。面对复杂的医学影像信息和持续增长的医学影像诊断需求,医生人工影像解读暴露出的易受主观认知影响、效率低且误诊率高等诸多缺点愈加明显。本文从人工智能技术特点出发,结合具体病症分析人工智能在人体结构、病灶区的分割,疾病的早期诊断,解剖结构、病灶区的检测等方面的研究成果,最后总结现阶段人工智能在医学影像诊断中尚存在的问题,包括诊断结果可解释性差、医学数据量少及系统性评估标准缺失等,并进一步分析未来人工智能在医学影像诊断中的发展方向。     

PACS在医院建设的方法与应用体会

PACS将数字化的医学影像通过计算机和网络设备,实现对医学影像的采集、存储、管理、处理及传输.本文介绍了PACS在医院建设的方法和实际应用中的体会.     

Designing a Wearable Navigation System for Image-Guided Cancer Resection Surgery

A wearable surgical navigation system is developed for intraoperative imaging of surgical margin in cancer resection surgery. The system consists of an excitation light source, a monochromatic CCD camera, a host computer, and a wearable headset unit in either of the following two modes: head-mounted display (HMD) and Google glass. In the HMD mode, a CMOS camera is installed on a personal cinema system to capture the surgical scene in real-time and transmit the image to the host computer through a USB port. In the Google glass mode, a wireless connection is established between the glass and the host computer for image acquisition and data transport tasks. A software program is written in Python to call OpenCV functions for image calibration, co-registration, fusion, and display with augmented reality. The imaging performance of the surgical navigation system is characterized in a tumor simulating phantom. Image-guided surgical resection is demonstrated in an ex vivo tissue model. Surgical margins identified by the wearable navigation system are co-incident with those acquired by a standard small animal imaging system, indicating the technical feasibility for intraoperative surgical margin detection. The proposed surgical navigation system combines the sensitivity and specificity of a fluorescence imaging system and the mobility of a wearable goggle. It can be potentially used by a surgeon to identify the residual tumor foci and reduce the risk of recurrent diseases without interfering with the regular resection procedure.     

Computer applications in thermoregulatory research

Thermoregulatory information is a frequently used parameter in both physiological and psychophysiological research. Specific software programs using accepted formulae are not readily available to the scientist as is the hardware. The program described here uses the well-established physiological model by Burton, calculating mean skin temperature and mean body temperature. The primary goal of this microsoft Basic program is to aid the researcher through speed of execution and quantitative reliability. A few command alterations will allow this program to be used with most microcomputer systems currently available. The time saved using this program will greatly enhance the efficiency of the researcher's thermoregulatory data analyses.     

Evaluation of a computer based interactive diabetes education program designed to train the estimation of the energy or carbohydrate contents of foods.

The objective of this study was to evaluate a computer based interactive diabetes education program designed to train patients with diabetes to correctly estimate the energy or carbohydrate contents of foods. The acceptance and the operator convenience of the program were evaluated with an integrated program and written questionnaires. The training success was calculated for each user from the data sets after multiple repetitions of the same exercise. Age, weight, type of diabetes, previous training and computer experience of 126 patients with type 1 or 2 diabetes from three different German diabetes centres were documented.The evaluation of the computer program indicated a good acceptance and operator convenience. Moreover, there was a significant training success in patients who have never used a structured diabetes education program before. Therefore, the potential impact of the program is to support but not to replace structured diabetes education programs and to further motivate and attract patients to diabetes education programs.     

The Bioperl toolkit: Perl modules for the life sciences

The Bioperl project is an international open-source collaboration of biologists, bioinformaticians, and computer scientists that has evolved over the past 7 yr into the most comprehensive library of Perl modules available for managing and manipulating life-science information. Bioperl provides an easy-to-use, stable, and consistent programming interface for bioinformatics application programmers. The Bioperl modules have been successfully and repeatedly used to reduce otherwise complex tasks to only a few lines of code. The Bioperl object model has been proven to be flexible enough to support enterprise-level applications such as EnsEMBL, while maintaining an easy learning curve for novice Perl programmers. Bioperl is capable of executing analyses and processing results from programs such as BLAST, ClustalW, or the EMBOSS suite. Interoperation with modules written in Python and Java is supported through the evolving BioCORBA bridge. Bioperl provides access to data stores such as GenBank and SwissProt via a flexible series of sequence input/output modules, and to the emerging common sequence data storage format of the Open Bioinformatics Database Access project. This study describes the overall architecture of the toolkit, the problem domains that it addresses, and gives specific examples of how the toolkit can be used to solve common life-sciences problems. We conclude with a discussion of how the open-source nature of the project has contributed to the development effort.     

基于IAEA430号报告的射线剂量学参数比较软件开发

目的:快速比较计划系统建模后百分深度剂量（PDD）和离轴剂量（OAD）的计算值和测量值以及每年加速器年检中两次测量值的PDD和OAD,用以判断加速器建模数据准确性和测量数据一致性。方法:运用基于面向对象Python程序开发了基于IAEA 430号报告的比对软件ComparePO（CPO）,该软件由文件准备、PDD模块、OAD模块、比对参数可视化和报告生成模块构成。结果:在临床上首先验证CPO的运行情况和结果报告的正确性,其次对新安装的两台加速器验收和加速器机头更换电离室后的数据测试都用到了该软件,该软件都能快速得出PDD和OAD的比较报告,为放射治疗物理师提供判断指导。结论:该软件界面友好,功能强大,能快速计算生成PDD和OAD比较报告,大大节约核查时间,提高放射治疗物理师的工作效率。     

Using the desk top computer in cellular toxicity and mutagenesis

A series of programs applicable to in vitro test symptoms in environmental toxicology are described for the Tektronix 4050 series graphic system computer. The file structure, experimental design and identification, the program library, data entry program, and programs to compile data from separate experiments are presented. Experimental design information and test data are stored on magnetic tape. The programs are designed to compute cell number and viability, adenosine triphosphate level, and protein and DNA synthetic activity from raw data obtained from cellular toxicity experiments; and cloning efficiency, mutation yield, mutation frequency, and other parameters for mutagenicity. A set of subprograms can be used for statistical analysis of the data and for construction of frequency distributions. The applicability of the programs is illustrated by data obtained from exposure of Chinese hamster ovary cells to cadmium chloride or N-methyl-N′-nitro-N-nitroso-guanidine.     

The clinical laboratory training after the graduate in local training hospital setting

As clinical training has become a compulsory element of the training of physicians, all doctors are now required to undergo training in basic abilities of diagnosis and treatment. Clinical training has become possible in local medical organizations as well as university hospitals and large hospitals. There are full-time clinical pathologists in the laboratory staff of large hospitals, but they have little time for clinical trainees in the present educational system in the field of clinical laboratory. In mid-size and small hospitals, there is no clinical pathologist at the central diagnostic and treatment division, and clinical laboratory technicians are expected to play roles of trainers. It is important for the training administrator to prepare an environment in which clinical trainees can learn the selection of examinations, execution of examinations, interpretation of results, and actual handling of patients and, particularly in the execution of examinations, to cooperate with the director of the examination division and see that trainees can learn the necessary skills that they must acquire. The training administrator must also formulate a program to help clinical trainees to develop the abilities necessary for them to function as a member of team care. Such a program must not only be effective for the training of physicians but also contribute to the development of laboratory technicians and to improvements in the quality of medical care that is provided.     

Towards automated generation and execution of clinical guidelines: engine design and implementation through the ICU Modified Schofield use case

As the complexity and amount of medical information keeps increasing, it is difficult to maintain the same quality of care. Therefore, clinical guidelines are used to structure best practices and care, but they also support physicians and nurses in the diagnostic and treatment process. Currently, no standardized format exists to represent these guidelines. Translating guidelines into a computer interpretable format can overcome problems in the physicians' workflow and improve clinician's uptake. An engine is proposed to automatically translate and execute clinical guidelines. These guidelines are represented as flowcharts, expressed in either (i) a computer interpretable guideline format or (ii) a UML diagram. A detailed overview of the architecture is presented and algorithms, aiming at grouping several components and distributing the guidelines, are proposed to optimize the execution of the guidelines. The Modified Schofield guideline for the calculation of the calorie need for burn patients was used for evaluation. Results show that the execution of guidelines using the engine is very efficient. Using optimization algorithms the execution times can be lowered.     

Implementation of a Semi-automated Post-processing System for Parametric MRI Mapping of Human Breast Cancer

Magnetic resonance imaging (MRI) investigations of breast cancer incorporate computationally intense techniques to develop parametric maps of pathophysiological tissue characteristics. Common approaches employ, for example, quantitative measurements of T ₁, the apparent diffusion coefficient, and kinetic modeling based on dynamic contrast-enhanced MRI (DCE-MRI). In this paper, an integrated medical image post-processing and archive system (MIPAS) is presented. MIPAS demonstrates how image post-processing and user interface programs, written in the interactive data language (IDL) programming language with data storage provided by a Microsoft Access database, and the file system can reduce turnaround time for creating MRI parametric maps and provide additional organization for clinical trials. The results of developing the MIPAS are discussed including potential limitations of the use of IDL for the application framework and how the MIPAS design supports extension to other programming languages and imaging modalities. We also show that network storage of images and metadata has a significant (p < 0.05) increase in data retrieval time compared to collocated storage. The system shows promise for becoming both a robust research picture archival and communications system working with the standard hospital PACS and an image post-processing environment that extends to other medical image modalities.