基于DICOM标准的超声图像归档与通讯系统的研制与初步应用

目的 开发超声图像归档与通讯系统(PACS)，实现超声成像设备的网络化，解决超声图像的存储和诊断报告书写的计算机化、标准化。方法 利用C 计算机语言开发超声图像工作站，获取、显示、处理和打印超声动静态图像，将科室内10台超声设备连接成医学数字影像传输(DICOM)网络；中心图像服务器和超声科信息管理系统服务器与各图像工作站组成计算机以太网，构成超声PACS；再通过交换机与医院Internet WWW服务器连接，实现超声彩色图文报告的院内发布。结果 成功实现了DICOM数字图像和高质量视频图像的获取、显示、处理和网络传送，与医院信息系统无缝连接，图像的中心存储，诊断报告书写计算机化以及共享打印等功能。结论 超声图像管理系统的应用提高了工作效率及管理水平，推动了医生工作模式的变革，方便了工作、科研和教学，提高了医疗服务层次。规范化、计算机化的诊断报告质量优于人工书写报告。     

超声影像工作站在超声诊断中的应用价值

目的本文总结了超声影像工作站的具体使用方法,介绍了使用工作站的诸多优点,认为使用工作站可明显简化诊断步骤,节约候诊时间;有利于图文资料的保存和传输,促进会诊和教学;便于质量控制和标准化;作为医院为RIS、HIS和PACS的一个重要组成部分,超声影像工作站正发挥着其不可或缺的作用。     

Update on digital image management and PACS

Information technology is becoming a vital component of all health care enterprises, from managed care services to large hospital networks, that provides the basis of electronic patient records and hospital-wide information. The rationale behind such systems is deceptively simple: physicians want to sit down at a single workstation and call up all information, both clinical data and medical images, concerning a given patient. Picture archiving and communication systems (PACS) are responsible for solving the problem of acquiring, transmitting, and displaying radiologic images. The major benefit of PACS resides in its ability to communicate images and reports to referring physicians in a timely and reliable fashion. With the changes in economics and the shift toward managed and capitated care, the teleradiology component of PACS is rapidly gaining momentum. In allowing remote coverage of multiple sites by the same radiologists and remote consultations and expert opinion, teleradiology is in many instances the only option to maintain economically viable radiologic settings. The technical evolution toward more integrated systems and the shift toward Web-based technology is rapidly merging the two concepts of PACS and teleradiology in global image management and communication systems.     

Development of an integrated filing system for endoscopic images

A new integrated filing system for endoscopic images has been developed, comprising a main image filing system and subsystems located at different stations. A hybrid filing system made up of both digital and analog filing devices was introduced to construct this system that combines the merits of the two filing methods. Each subsystem provided with a video processor, is equipped with a digital filing device, and routine images were recorded in the analog image filing device of the main system. The use of a multi-input adapter enabled simultaneous input of analog images from up to 8 video processors. Recorded magneto-optical disks make it possible to recall the digital images at any station in the hospital; the disks are copied without image degradation and also utilised for image processing. This system promises reliable storage and integrated, efficient management of endoscopic information. It also costs less to install than the so-called PACS (picture archiving and communication system), which connects all the stations of the hospital using optical fiber cables.     

卷积神经网络在骨骼肌肉放射学中的研究进展

人工智能逐渐应用于医学图像诊断，显现出良好的效率和诊断准确率。卷积神经网络（CNN）是人工智能领域的一项突破，在某些方面已可与放射科医师相媲美，展现出巨大的临床应用前景。本文就CNN在骨骼肌肉放射学中的研究进展进行综述。     

基于虚拟网络计算技术的远程放射学诊断系统的建立

目的 建立基于虚拟网络计算技术、遵从DICOM协议的远程放射学诊断系统。方法 运用VC++6.0、Leadtools开发包、VNC源码在Windows 2000操作系统中开发。结果 本系统在Internet网和广域网环境下成功地实现了远程放射学影像的采集、浏览、处理、诊断与书写图文报告功能,在实际应用中取得了良好的效果。结论 基于VNC技术开发的远程放射学系统交互速度快、实时性强、影像清晰度好,在低带宽的网络条件下也能具备优异的速度和性能。本系统能够提升放射诊断学的信息化与网络化水平,促进放射学的远程交流,具有广阔的应用前景和推广价值。     

Open-source software in medical imaging: development of OsiriX

Purpose Open source software (oss) development for medical imaging enables collaboration of individuals and groups to produce high-quality tools that meet user needs. This process is reviewed and illustrated with OsiriX, a fast DICOM viewer program for the Apple Macintosh. Materials and methods OsiriX is an oss for the Apple Macintosh under Mac OS X v10.4 or higher specifically designed for navigation and visualization of multimodality and multidimensional images: 2D Viewer, 3D Viewer, 4D Viewer (3D series with temporal dimension, for example: Cardiac-CT) and 5D Viewer (3D series with temporal and functional dimensions, for example: Cardiac-PET-CT). The 3D Viewer offers all modern rendering modes: multiplanar reconstruction, surface rendering, volume rendering and maximum Intensity projection. All these modes support 4D data and are able to produce image fusion between two different series (for example: PET-CT). OsiriX was developed using the Apple Xcode development environment and Cocoa framework as both a DICOM PACS workstation for medical imaging and an image processing software package for medical research (radiology and nuclear imaging), functional imaging, 3D imaging, confocal microscopy and molecular imaging. Results OsiriX is an open source program by Antoine Rosset, a radiologist and software developer, was designed specifically for the needs of advanced imaging modalities. The software program turns an Apple Macintosh into a DICOM PACS workstation for medical imaging and image processing. OsiriX is distributed free of charge under the GNU General Public License and its source code is available to anyone. This system illustrates how open software development for medical imaging tools can be successfully designed, implemented and disseminated. Conclusion oss development can provide useful cost effective tools tailored to specific needs and clinical tasks. The integrity and quality assurance of open software developed by a community of users does not follow the traditional conformance and certification required for commercial medical software programs. However, open software can lead to innovative solutions designed by users better suited for specific tasks.     

数字影像—PACS—远程影像学及其在我国的发展前景

数字影像有别于模拟影像在于可以毫不费力地相互混合,同时或分别地被重复使用,并且可以以光速传输,通过数据压缩和纠正错误的功能,能够在非常昂贵或杂音充斥的信道上准确、快速地传递,这是进行PACS建设所必须的。PACS则是医院管理系统的一部分,包括医学影像的获取、数据库与数据库管理、在线存储、离线归档、图像显示与处理、RIS／HIS的接口、胶片打印,通过PACS的建立能够达到异地访问、图像复制、同步显示、快速传送,并且易于病变的观察和诊断。远程影像学作为一种高科技手段正在蓬勃发展,它将充分发挥专家优势,能够使异地的患者同样享受高水平的影像诊断,并且有利于大样本的医学影像研究和各种教育的需要。目前数字影像除一些大医院正在完成或努力建设中以外,中小型医院还需相当长的一段时间才能够完成。PACS由于技术含量高、各种设备缺乏统一标准,所需费用巨大,造成开发与建设的困难,真正达到HIS系统下使用的PACS尚未见到。对于地域广泛、医疗水平差别较大的我国,远程医学影像是非常有意义,也是非常需要的。但是现有国情下,如果需要建立和完善远程医学影像学则需要国家或公司的大量投入,才能够完成远程医学影像学和远程医学的建设,才能真正提高农村医疗水平。而单纯依靠基层医院,则需要数年,以至10数年才能够完成。     

Evaluation of PACS in ultrasonography.

We review our experience with a picture archiving and communication system to replace film in the ultrasound section of a clinical radiology department. The system includes three ultrasound units connected by a fiberoptic network via acquisition nodes to a central data management system, workstation, and optical jukebox. The system handles 80% of sonographic studies in the department. Image production, interpretation, storage, and retrieval are evaluated. Despite limitations, a picture archiving and communication system can be integrated into a functioning ultrasound section of an active radiology department with minimal disruption and promising results.     

Information Loss Via Visual Assessment of Radiologic Images Using Modified Version of the Low-Contrast Detailed Phantom at Direct DR System

IntroductionQuality in radiology images can be assessed by determining the levels of information retained or lost in an image. Information loss in images has been recently assessed via a method based on information theory and the employment of a contrast-detail (CD) phantom. In this study, the traditional CD phantom (air-Perspex) and a modified CD phantom were used.MethodsUsing the Agfa DX-D 600 digital flat panel system, six phantom radiographs were acquired at 70 kVp and 20 mAs. Three x-ray images were acquired for each phantom.ResultsOur results demonstrate that the material within the CD phantom influences total information loss (TIL) and image quality figure (IQF) measurements. The modified CD phantom provides a more realistic account of TIL and IQF for soft tissue radiology imaging.ConclusionIt is recommended that a low inherent subject contrast phantom, such as this modified CD phantom, be added to the image quality assessment processes of radiology departments. In addition, use of both IQF and TIL to assess image quality will provide radiology departments with greater evidence on which to base decisions.     

A picture archival and communication system shortens delays in obtaining radiographic information in a medical intensive care unit

OBJECTIVE: To assess whether variables such as unit occupancy and aggregate severity of illness that reflect increased work demands on physicians in medical intensive care units (MICU) are associated with increased delays in their obtaining information about nonroutine chest radiographic examinations. To determine whether the presence of a picture archiving and communication system (PACS) workstation in the MICU shortens those delays. DESIGN: A prospective cohort study stratified for presence or absence of PACS. SETTING: MICU of a university hospital. PATIENTS: A total of 118 patients admitted to the MICU who had nonroutine bedside chest radiographs. MEASUREMENTS AND MAIN RESULTS: Multivariate analyses were conducted to determine how unit occupancy, patient acuity, the time of day the examination was taken, and the presence of a PACS workstation influenced the time from radiographic examination completion to the time when MICU physicians first obtained image information. In a multivariate analysis, patient acuity, unit occupancy, the aggregate level of severity of illness in the study cohort, whether the examination was taken at night or day, and the presence of a PACS workstation were significant predictors of the elapsed time from examination completion until review by MICU physicians. Without the PACS workstation, higher occupancy, higher aggregate severity of illness, and examinations taken during the day were associated with longer delays. Overall, the multivariate analysis showed a 24-min decrease in the elapsed time to obtain information during periods with the PACS workstation compared with periods without the workstation (p = .03). CONCLUSIONS: A PACS workstation significantly decreased the delays in obtaining image information that occurred with high unit occupancy and high aggregate severity of illness and may improve unit efficiency under conditions of high physician workload.     

Designing user interfaces to enhance human interpretation of medical content-based image retrieval: application to PET-CT images

Purpose Content-based image retrieval (CBIR) in medicine has been demonstrated to improve evidence-based diagnosis, education, and teaching. However, the low clinical adoption of CBIR is partially because the focus of most studies has been the development of feature extraction and similarity measurement algorithms with limited work on facilitating better understanding of the similarity between complex volumetric and multi-modality medical images. In this paper, we present a method for defining user interfaces (UIs) that enable effective human user interpretation of retrieved images. Methods We derived a set of visualisation and interaction requirements based on the characteristics of modern volumetric medical images. We implemented a UI that visualised multiple views of a single image, displayed abstractions of image data, and provided access to supplementary non-image data. We also defined interactions for refining the search and visually indicating the similarities between images. We applied the UI for the retrieval of multi-modality positron emission tomography and computed tomography (PET-CT) images. We conducted a user survey to evaluate the capabilities of our UI. Results Our proposed method obtained a high rating ( $\ge $ 4 out of 5) in the majority of survey questions. In particular, the survey responses indicated the UI presented all the information necessary to understand the retrieved images, and did so in an intuitive manner. Conclusion Our proposed UI design improved the ability of users to interpret and understand the similarity between retrieved PET-CT images. The implementation of CBIR UIs designed to assist human interpretation could facilitate wider adoption of medical CBIR systems.     

PACS在放射科图像管理中的应用

目的:探讨图像存档及通信系统(PACS)在现代化医院放射科图像管理中的应用价值。材料和方法:通过数字化图像管理与传统的放射科胶片管理两种完全不同的管理模式进行比较。结果:传统的胶片管理模式显露出许多缺点,数字化图像管理是唯一出路。结论:随着PACS在放射科中的应用,数字化图像管理模式必将取代传统的胶片管理模式。医学影像领域的“无胶片”时代即将来临。     

System solutions for the integration of devices in the OR

Summary

The technical complexity of the surgical arena, as well as of related specialised fields, has increased significantly. A look at the current situation in various surgical disciplines shows that, despite existing high-tech equipment, the operating room (OR) can still not be considered an ergonomic and optimised work environment. Industrial suppliers have integrated new procedures and techniques into surgical disciplines, often without consulting other manufacturers and without establishing or implementing appropriate standards. This paper describes the development of an integrated workstation for the OR and its related technical and clinical aspects, e.g. process analysis, system integration, standardisation, image processing, user interfaces, communication protocols (CANopen, DICOM) and networking. The first introduction of the prototype to our clinical partners has confirmed that the implementation of an optimised system workstation in the OR results in improved processes. The standardised and simplified user guidance leads to improved ergonomy. The selected communication standard between the subsystems of the diverse industrial suppliers gives the user more flexibility in configuring the individual OR system. Intensive collaboration between industry and clinical partners will continue to be vital for the further development of such complex system workstations in medicine.     

Medical consultations and the sharing of medical images involving spinal injury over mobile phone networks

Background

The transmission of medical images and other data over mobile phone networks may facilitate remote medical consultations between neurosurgeons and regional hospitals treating spinal injury patients. The aim of this study was to compare the efficacy of mobile phone consultations with standard hospital workstation consultations in spinal injury patients.

Methods

The images were exported over the Internet from surrounding local hospitals through the Picture Archiving and Communication System, in DICOM III format, to the central hospital server. The xVision browser was used to view the acquired images on a standard workstation. The data were also exported to the secured hospital Web server IIS60 and converted to JPEG format to enable remote physician access and consultation. The remote consulting physician connected to this server by mobile phone using the phone's Internet browser. A second physician, blind to the mobile phone results, evaluated the same images at a workstation in the hospital. The results of the mobile phone consultations were compared with the results from standard workstation consultations.

Results

There was no difference in the quality of spinal computed tomographic/magnetic resonance images viewed on the phone screen compared with on the workstation. More importantly, the final diagnoses made by mobile phone did not differ from those made by workstation consultations. A transfer to the department of neurosurgery was required after consultation in 11 patients.

Conclusion

Mobile phone consultations for patients with spinal injuries was as effective as workstation consultations. Mobile phone consultations can increase the expertise available to regional hospitals, which are often the first responders to medical emergencies.     

Machine learning and radiology

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers.     

医学影像处理、分析和可视化技术

随着医学成像设备的不断发展和医院数字化进程的不断推进，医院数字影像的采集、通信、归档、存储等基本设施日趋完善。数字影像不仅便于存贮和检索，而且能够提供更多的诊断信息。为了挖掘图像中更多的诊断信息，并提供计算机辅助诊断功能，必需首先研究数字影像的处理、分析及可视化技术。为此，本文简要介绍与此有关的算法、工程实现方法及注意事项，交流技术思想和研究心得。     

Medical imaging part of multi-media

The main objective of CEN/TC251/WG4 is to create standards for image communication to allow interoperability between heterogeneous systems in a distributed environment. The scope includes all forms of medical imaging (not only radiology) and also the image related data. The Working Group (WG) is monitoring developments in the whole field of medical imaging and multimedia, in particular image formats, image management, image processing, interface control, security and multimedia (including related standards). International co-operation is crucial resulting in one internationally acceptable standard. Technology independents for cost and evolution reasons is a perquisite of the approach, which results in a focus towards more generic standards. The work items define concrete steps, where the WG considers it important and feasible to produce a deliverable (ENV or CEN Report) within a definite time schedule. New work items will be proposed where needed. The first two Project Teams, which have finished their work, are: - Medical Image and Related Data interchange format standards (WI 4.3) - Profiles for Medical Image interchange (EWOS/EG MED, PTN-024). In both work items (WI), contributions from the United States and Europe are brought together. Europe is presenting a framework which includes an image communication model and a registration procedure for the objects. This ‘road map’ for migration towards the use of IT & T base-standards also contains a medical ISP based on ISO-IPI (Image Processing Interchange (ISO 10227)). Two other Project Teams have been launched at the beginning of 1994: - Medical Image Management standard (WI 4.2) - Medical Data Interchange: HIS/RIS-PACS and HIS/RIS Modality Interface (WI 4.9). These Project Teams have almost completed their tasks and produced ENVs on committed storage of images and on the connection of image producing modalities to information systems respectively. A next step will be the integration of other more dynamic imaging domains like cardiology and endoscopy.     

Acquisition of ICU data: concepts and demands

As the issue of data overload is a problem in critical care today, it is of utmost importance to improve acquisition, storage, integration, and presentation of medical data, which appears only feasible with the help of bedside computers.The data originates from four major sources: (1) the bedside medical devices, (2) the local area network (LAN) of the ICU, (3) the hospital information system (HIS) and (4) manual input. All sources differ markedly in quality and quantity of data and in the demands of the interfaces between source of data and patient database.The demands for data acquisition from bedside medical devices, ICU-LAN and HIS concentrate on technical problems, such as computational power, storage capacity, real-time processing, interfacing with different devices and networks and the unmistakable assignment of data to the individual patient.The main problem of manual data acquisition is the definition and configuration of the user interface that must allow the inexperienced user to interact with the computer intuitively. Emphasis must be put on the construction of a pleasant, logical and easy-to-handle graphical user interface (GUI). Short response times will require high graphical processing capacity. Moreover, high computational resources are necessary in the future for additional interfacing devices such as speech recognition and 3D-GUI.Therefore, in an ICU environment the demands for computational power are enrmous. These problems are complicated by the urgent need for friendly and easy-to-handle user interfaces. Both facts place ICU bedside computing at the vanguard of present and future workstation development leaving no room for solutions based on traditional concepts of personal computers.For a truely paperless documentation a new integrated computational paradigm has to be developed that might required a new dimension of computational and graphical power at the bedside.