This paper describes how the integration between one of the RIS-systems (Adapt) in VGR and the infobroker in the central archive is implemented. The project was presented in 2006 with the title Building an IT Healthcare Enterprise by taking the standards to the limits and sometimes beyond that. The Adapt RIS is used by the Sahlgrenska University Hospital (SU) in Gothenburg and handles 8 different radiology departments. The implementation is based on HL7 version 3 and the message exchange is based on Web Services/SOAP. The base of the RIS-system was developed in the beginning of the 1990:s by a company that no longer exists. SU has always been able to modify the system by changing the source code and we have been responsible for the system-development since late 1990s. We are using IBM Informix Dynamic Server that is running on a Solaris-based cluster with additional software from Veritas/Symantec. The communication is planned to be 2-way. Our RIS-system transfers order promises, various status updates during the workflow and finally reports with various status levels. Our system will be able to receive requests and reports from the broker. The broker in turn receives these messages from other hospitals in VGR (Vastra Gotalands Regionen). We use Axis2 to generate skeleton java-code based on WSDL- and XSD-files that defines the Web Services. Axis2 is an Open Source software that is developed as a part of the Apache project. Eclipse is a development environment for Java that we use and it is also open source. Apache Tomcat is the application server that we use to receive messages from the infobroker.

A variety of software exists to interpret files or directories compliant to the Digital Imaging and Communications in Medicine (DICOM) standard and display them as individual images or volume rendered objects. Some of them offer further processing and analysis features. The surveys that have been published so far are partly not up-to-date anymore, and neither a detailed description of the software functions nor a comprehensive comparison is given. This paper aims at evaluation and comparison of freely available, non-diagnostic DICOM software with respect to the following aspects: (i) data import; (ii) data export; (iii) header viewing; (iv) 2D image viewing; (v) 3D volume viewing; (vi) support; (vii) portability; (viii) workability; and (ix) usability. In total, 21 tools were included: 3D Slicer, AMIDE, BioImage Suite, DicomWorks, EViewBox, ezDICOM, FPImage, ImageJ, JiveX, Julius, MedImaView, MedINRIA, MicroView, MIPAV, MRIcron, Osiris, PMSDView, Syngo FastView, TomoVision, UniViewer, and XMedCon. Our results in table form can ease the selection of appropriate DICOM software tools. In particular, we discuss use cases for the inexperienced user, data conversion, and volume rendering, and suggest Syngo FastView or PMSDView, DicomWorks or XMedCon, and ImageJ or UniViewer, respectively.

The Medical Imaging Informatics (MI²) Data Grid developed at the USC Image Processing and Informatics Laboratory enables medical images to be shared securely between multiple imaging centers. Current applications include an imaging-based clinical trial setting where multiple field sites perform image acquisition and a centralized radiology core performs image analysis, often using computer-aided diagnosis tools (CAD) that generate a DICOM-SR to report their findings and measurements. As more and more CAD tools are being developed in the radiology field, the generated DICOM Structure Reports (SR) holding key radiological findings and measurements that are not part of the DICOM image need to be integrated into the existing Medical Imaging Informatics Data Grid with the corresponding imaging studies. We will discuss the significance and method involved in adapting DICOM-SR into the Medical Imaging Informatics Data Grid. The result is a MI² Data Grid repository from which users can send and receive DICOM-SR objects based on the imaging-based clinical trial application. The services required to extract and categorize information from the structured reports will be discussed, and the workflow to store and retrieve a DICOM-SR file into the existing MI² Data Grid will be shown.

During the last 2 years we have been working on developing a DICOM-RT (Radiation Therapy) ePR (Electronic Patient Record) with decision support that will allow physicists and radiation oncologists during their decision-making process. This ePR allows offline treatment dose calculations and plan evaluation, while at the same time it compares and quantifies treatment planning algorithms using DICOM-RT objects. The ePR framework permits the addition of visualization, processing, and analysis tools, which combined with the core functionality of reporting, importing and exporting of medical studies, creates a very powerful application that can improve the efficiency while planning cancer treatments. Usually a Radiation Oncology department will have disparate and complex data generated by the RT modalities as well as data scattered in RT Information/Management systems, Record & Verify systems, and Treatment Planning Systems (TPS) which can compromise the efficiency of the clinical workflow since the data crucial for a clinical decision may be time-consuming to retrieve, temporarily missing, or even lost. To address these shortcomings, the ACR-NEMA Standards Committee extended its DICOM (Digital Imaging & Communications in Medicine) standard from Radiology to RT by ratifying seven DICOM RT objects starting in 1997 [1,2]. However, they are not broadly used yet by the RT community in daily clinical operations. In the past, the research focus of an RT department has primarily been developing new protocols and devices to improve treatment process and outcomes of cancer patients with minimal effort dedicated to integration of imaging and information systems. Our attempt is to show a proof-of-concept that a DICOM-RT ePR system can be developed as a foundation to perform medical imaging informatics research in developing decision-support tools and knowledge base for future data mining applications.

The asymmetric distribution of PACS equipment and service providers across countries leads typically to the need to hire third party service professionals outside the institutions where the exams were made. In this paper we present a brokerage mechanism that puts customers and remote providers together in a seamless way. The proposed solution, asserted with a case study for the Portuguese national health system, addresses the problems that now impair the optimal provision of those services, enabling a more agile relationship between buyers and sellers, optimizing administrative work and complying with clinical and legal requirements under discussion in the European Union for the free movement of patients and professional health workers. In this document, the detailed process and technical description of the broker functioning is made, and the main benefits for the participants are also evaluated from a technical and economical point of view. Finally, in the discussion chapter, an assessment of the creation of a spot market for imaging studies is made and the integration with other similar markets is discussed.

Content-based image retrieval (CBIR) is the process of retrieving images by directly using image visual characteristics. In this paper, we present a prototype system implemented for CBIR for a uterine cervix image (cervigram) database. This cervigram database is a part of data collected in a multi-year longitudinal effort by the National Cancer Institute (NCI), and archived by the National Library of Medicine (NLM), for the study of the origins of, and factors related to, cervical precancer/cancer. Users may access the system with any Web browser. The system is built with a distributed architecture which is modular and expandable; the user interface is decoupled from the core indexing and retrieving algorithms, and uses open communication standards and open source software. The system tries to bridge the gap between a user's semantic understanding and image feature representation, by incorporating the user's knowledge. Given a user-specified query region, the system returns the most similar regions from the database, with respect to attributes of color, texture, and size. Experimental evaluation of the retrieval performance of the system on "groundtruth" test data illustrates its feasibility to serve as a possible research tool to aid the study of the visual characteristics of cervical neoplasia.

Intensity overlap often occurs in medical images, making it difficult to identify different anatomical structures using intensity alone. Research studies have shown that texture is an important component in quantifying the visual appearance of anatomical structures, and is therefore valuable in the analysis, interpretation, and retrieval of lung nodules. The goal of our research study is to present a comparison between the different texture models: Gabor filters, Markov Random Field (MRF), and global & local co-occurrence. For comparison purposes we utilized Manhattan, Euclidean, and Chebyshev distances for one-dimensional feature vectors (global co-occurrence) while for two-dimensional feature comparison (local co-occurrence, Gabor filters, and MRF) we utilized the similarity measures Chi-Square and Jeffrey- Divergence. Local co-occurrence contains many different variable aspects in its design that can considerably change the success of its results. A thorough examination of local co-occurrence's variables is discussed. All of the discussed texture models are presented in the context of our previous Content-Based Image Retrieval (CBIR) System [1]. BRISC utilizes the Lung Image Database Consortium (LIDC) database. We have found that Gabor and MRF texture descriptors produce the best retrieval results regardless of the nodule size, number of retrieved items or similarity metric with an average precision of 88%. Global co-occurrence performed the worse at 44% precision yet when co-occurrence was performed locally (local co-occurrence) the precision results improved to 64%. A combination of all the features worked the best with 91% precision.

Radiology Information Systems (RIS) contain a wealth of information that can be used for research, education, and practice management. However, the sheer amount of information available makes querying specific data difficult and time consuming. Previous work has shown that a clinical RIS database and its RIS text reports can be extracted, duplicated and indexed for searches while complying with HIPAA and IRB requirements. This project's intent is to provide a software tool, the RadSearch Toolkit, to allow intelligent indexing and parsing of RIS reports for easy yet powerful searches. In addition, the project aims to seamlessly query and retrieve associated images from the Picture Archiving and Communication System (PACS) in situations where an integrated RIS/PACS is in place - even subselecting individual series, such as in an MRI study. RadSearch's application of simple text parsing techniques to index text-based radiology reports will allow the search engine to quickly return relevant results. This powerful combination will be useful in both private practice and academic settings; administrators can easily obtain complex practice management information such as referral patterns; researchers can conduct retrospective studies with specific, multiple criteria; teaching institutions can quickly and effectively create thorough teaching files.

Effective use of new technologies to support healthcare initiatives is important and current research is moving towards implementing secure grid-enabled healthcare provision. In the UK, a large-scale collaborative research project (GIMI: Generic Infrastructures for Medical Informatics), which is concerned with the development of a secure IT infrastructure to support very widespread medical research across the country, is underway. In the UK, there are some 109 breast screening centers and a growing number of individuals (circa 650) nationally performing approximately 1.5 million screening examinations per year. At the same, there is a serious, and ongoing, national workforce issue in screening which has seen a loss of consultant mammographers and a growth in specially trained technologists and other non-radiologists. Thus there is a need to offer effective and efficient mammographic training so as to maintain high levels of screening skills. Consequently, a grid based system has been proposed which has the benefit of offering very large volumes of training cases that the mammographers can access anytime and anywhere. A database, spread geographically across three university systems, of screening cases is used as a test set of known cases. The GIMI mammography training system first audits these cases to ensure that they are appropriately described and annotated. Subsequently, the cases are utilized for training in a grid-based system which has been developed. This paper briefly reviews the background to the project and then details the ongoing research. In conclusion, we discuss the contributions, limitations, and future plans of such a grid based approach.

We compare five common classifier families in their ability to categorize six lung tissue patterns in high-resolution computed tomography (HRCT) images of patients affected with interstitial lung diseases (ILD) but also normal tissue. The evaluated classifiers are Naive Bayes, k-Nearest Neighbor (k-NN), J48 decision trees, Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM). The dataset used contains 843 regions of interest (ROI) of healthy and five pathologic lung tissue patterns identified by two radiologists at the University Hospitals of Geneva. Correlation of the feature space composed of 39 texture attributes is studied. A grid search for optimal parameters is carried out for each classifier family. Two complementary metrics are used to characterize the performances of classification. Those are based on McNemar's statistical tests and global accuracy. SVM reached best values for each metric and allowed a mean correct prediction rate of 87.9% with high class-specific precision on testing sets of 423 ROIs.

Scientific data files have been increasing in size during the past decades. In the medical field, for instance, magnetic resonance imaging and computer aided tomography can yield image volumes of several gigabytes. While secondary storage (hard disks) increases in capacity and its cost per megabyte slumps over the years, primary memory (RAM) can still be a bottleneck in the processing of huge amounts of data. This represents a problem for image processing algorithms, which often need to keep in memory the original image and a copy of it to store the results. Operating systems optimize memory usage with memory paging and enhanced I/O operations. Although image processing algorithms usually work on neighbouring areas of a pixel, they follow pre-determined paths through the image and might not benefit from the memory paging strategies offered by the operating system, which are general purpose and unidimensional. Having the principles of locality and pre-determined traversal paths in mind, we developed an algorithm that uses multi-threaded pre-fetching of data to build a disk cache in memory. Using the concept of a window that slides over the data, we predict the next block of memory to be read according to the path followed by the algorithm and asynchronously pre-fetch such block before it is actually requested. While other out-of-core techniques reorganize the original file in order to optimize reading, we work directly on the original file. We demonstrate our approach in different applications, each with its own traversal strategy and sliding window structure.

The Digital Hand Atlas in Assessment of Skeletal Development is a large-scale Computer Aided Diagnosis (CAD) project for automating the process of grading Skeletal Development of children from 0-18 years of age. It includes a complete collection of 1,400 normal hand X-rays of children between the ages of 0-18 years of age. Bone Age Assessment is used as an index of skeletal development for detection of growth pathologies that can be related to endocrine, malnutrition and other disease types. Previous work at the Image Processing and Informatics Lab (IPILab) allowed the bone age CAD algorithm to accurately assess bone age of children from 1 to 16 (male) or 14 (female) years of age using the Phalanges as well as the Carpal Bones. At the older ages (16(male) or 14(female) -19 years of age) the Phalanges as well as the Carpal Bones are fully developed and do not provide well-defined features for accurate bone age assessment. Therefore integration of the Radius Bone as a region of interest (ROI) is greatly needed and will significantly improve the ability to accurately assess the bone age of older children. Preliminary studies show that an integrated Bone Age CAD that utilizes the Phalanges, Carpal Bones and Radius forms a robust method for automatic bone age assessment throughout the entire age range (1-19 years of age).

Before a radiographic image is sent to a picture archiving and communications system (PACS), its projection information needs to be correctly identified at capture modalities to facilitate image archive and retrieval. Currently, annotating radiographic images is manually performed by technologists. It is labor intensive and cost ineffective. Moreover, man-made annotation errors occur frequently during image acquisition. To address this issue, an automatic image recognition method is developed. It first extracts a set of visual features from the most indicative region in a radiograph for image recognition, and then uses a family of classifiers, each of which is trained for a specific projection to determine the most appropriate projection for the image. The method has been tested on a large number of clinical images and has shown excellent robustness and efficiency.

Last year, we presented methodology to perform knowledge-based medical imaging informatics research on specific clinical scenarios where brain tumor patients are treated with Proton Beam Therapy (PT). In this presentation, we demonstrate the design and implementation of quantification and visualization tools to develop the knowledge base for therapy treatment planning based on DICOM-RT-ION objects. Proton Beam Therapy (PT) is a particular treatment that utilizes energized charged particles, protons, to deliver dose to the target region. Similar to traditional Radiation Therapy (RT), complex clinical imaging and informatics data are generated during the treatment process that guide the planning and the success of the treatment. Therefore, an Electronic Patient Record (ePR) System has been developed to standardize and centralize clinical imaging and informatics data and properly distribute data throughout the treatment duration. To further improve treatment planning process, we developed a set of decision support tools to improve the QA process in treatment planning process. One such example is a tool to assist in the planning of stereotactic PT cases where CT and MR images need to be analyzed simultaneously during treatment plan assessment. These tools are add-on features for DICOM standard ePR system of brain cancer patients and improve the clinical efficiency of PT treatment planning. Additional outcome data collected for PT cases are included in the overall DICOM-RT-ION database design as knowledge to enhance outcomes analysis for future PT adopters.

Bone age assessment (BAA) of children is a clinical procedure frequently performed in pediatric radiology to evaluate the stage of skeletal maturation based on a left hand and wrist radiograph. The most commonly used standard: Greulich and Pyle (G&P) Hand Atlas was developed 50 years ago and exclusively based on Caucasian population. Moreover, inter- & intra-observer discrepancies using this method create a need of an objective and automatic BAA method. A digital hand atlas (DHA) has been collected with 1,400 hand images of normal children from Asian, African American, Caucasian and Hispanic descends. Based on DHA, a fully automatic, objective computer-aided-diagnosis (CAD) method was developed and it was adapted to specific population. To bring DHA and CAD method to the clinical environment as a useful tool in assisting radiologist to achieve higher accuracy in BAA, a web-based system with direct connection to a clinical site is designed as a novel clinical implementation approach for online and real time BAA. The core of the system, a CAD server receives the image from clinical site, processes it by the CAD method and finally, generates report. A web service publishes the results and radiologists at the clinical site can review it online within minutes. This prototype can be easily extended to multiple clinical sites and will provide the foundation for broader use of the CAD system for BAA.

With the aim of reducing the radiologists' subjectivity and the high degree of inter-observer variability, Content-based Image Retrieval (CBIR) systems have been proposed to provide visual comparisons of a given lesion to a collection of similar lesions of known pathology. In this paper, we present the effectiveness of shape features versus texture features for calculating lung nodules' similarity in Computed Tomography (CT) studies. In our study, we used eighty-five cases of thoracic CT data from the Lung Image Database Consortium (LIDC). To encode the shape information, we used the eight most commonly used shape features for pulmonary nodule detection and diagnosis by existent CAD systems. For the texture, we used co-occurrence, Gabor, and Markov features implemented in our previous CBIR work. Our preliminary results give low overall precision results for shape compared to texture, showing that shape features are not effective by themselves at capturing all the information we need to compare the lung nodules.

Knee-related injuries involving the meniscal or articular cartilage are common and require accurate diagnosis and surgical intervention when appropriate. With proper techniques and experience, confidence in detection of meniscal tears and articular cartilage abnormalities can be quite high. However, for radiologists without musculoskeletal training, diagnosis of such abnormalities can be challenging. In this paper, the potential of improving diagnosis through integration of computer-aided detection (CAD) algorithms for automatic detection of meniscal tears and articular cartilage injuries of the knees is studied. An integrated approach in which the results of algorithms evaluating either meniscal tears or articular cartilage injuries provide feedback to each other is believed to improve the diagnostic accuracy of the individual CAD algorithms due to the known association between abnormalities in these distinct anatomic structures. The correlation between meniscal tears and articular cartilage injuries is exploited to improve the final diagnostic results of the individual algorithms. Preliminary results from the integrated application are encouraging and more comprehensive tests are being planned.

Increased complexity of scientific research poses new challenges to scientific data management. Meanwhile, scientific collaboration is becoming increasing important, which relies on integrating and sharing data from distributed institutions. We develop SciPort, a Web-based platform on supporting scientific data management and integration based on a central server based distributed architecture, where researchers can easily collect, publish, and share their complex scientific data across multi-institutions. SciPort provides an XML based general approach to model complex scientific data by representing them as XML documents. The documents capture not only hierarchical structured data, but also images and raw data through references. In addition, SciPort provides an XML based hierarchical organization of the overall data space to make it convenient for quick browsing. To provide generalization, schemas and hierarchies are customizable with XML-based definitions, thus it is possible to quickly adapt the system to different applications. While each institution can manage documents on a Local SciPort Server independently, selected documents can be published to a Central Server to form a global view of shared data across all sites. By storing documents in a native XML database, SciPort provides high schema extensibility and supports comprehensive queries through XQuery. By providing a unified and effective means for data modeling, data access and customization with XML, SciPort provides a flexible and powerful platform for sharing scientific data for scientific research communities, and has been successfully used in both biomedical research and clinical trials.

Usually, there were multiple clinical departments providing imaging-enabled healthcare services in enterprise healthcare environment, such as radiology, oncology, pathology, and cardiology, the picture archiving and communication system (PACS) is now required to support not only radiology-based image display, workflow and data flow management, but also to have more specific expertise imaging processing and management tools for other departments providing imaging-guided diagnosis and therapy, and there were urgent demand to integrate the multiple PACSs together to provide patient-oriented imaging services for enterprise collaborative healthcare. In this paper, we give the design method and implementation strategy of developing grid-based PACS (Grid-PACS) for a hospital with multiple imaging departments or centers. The Grid-PACS functions as a middleware between the traditional PACS archiving servers and workstations or image viewing clients and provide DICOM image communication and WADO services to the end users. The images can be stored in distributed multiple archiving servers, but can be managed with central mode. The grid-based PACS has auto image backup and disaster recovery services and can provide best image retrieval path to the image requesters based on the optimal algorithms. The designed grid-based PACS has been implemented in Shanghai Huadong Hospital and been running for two years smoothly.

Policies and regulations in the current health care environment have impacted the manner in which patient data - especially protected health information (PHI) - are handled in the clinical and research settings. Specifically, it is now more challenging to obtain de-identified PHI from the clinic for use in research while still adhering to the requirements dictated by the new policies and regulations. To meet this challenge, we have designed and implemented a novel web-based interface that uses a workflow model to manage the communication of data (for example, biopsy results) between the clinic and research environments without revealing PHI to the research team or associated research identifiers to the clinical collaborators. At the heart of the scheme is a web application that coordinates message passing between researchers and clinical collaborators by use of a protocol that protects confidentiality. We describe the design requirements of the messaging/communication protocol, as well as implementation details of the web application and its associated database. We conclude that this scheme provides a useful communication mechanism that facilitates clinical research while maintaining confidentiality of patient data.

In recent years more and more computer aided diagnosis (CAD) systems are being used routinely in hospitals. Image-based knowledge discovery plays important roles in many CAD applications, which have great potential to be integrated into the next-generation picture archiving and communication systems (PACS). Robust medical image segmentation tools are essentials for such discovery in many CAD applications. In this paper we present a platform with necessary tools for performance benchmarking for algorithms of liver segmentation and volume estimation used for liver transplantation planning. It includes an abdominal computer tomography (CT) image database (DB), annotation tools, a ground truth DB, and performance measure protocols. The proposed architecture is generic and can be used for other organs and imaging modalities. In the current study, approximately 70 sets of abdominal CT images with normal livers have been collected and a user-friendly annotation tool is developed to generate ground truth data for a variety of organs, including 2D contours of liver, two kidneys, spleen, aorta and spinal canal. Abdominal organ segmentation algorithms using 2D atlases and 3D probabilistic atlases can be evaluated on the platform. Preliminary benchmark results from the liver segmentation algorithms which make use of statistical knowledge extracted from the abdominal CT image DB are also reported. We target to increase the CT scans to about 300 sets in the near future and plan to make the DBs built available to medical imaging research community for performance benchmarking of liver segmentation algorithms.

A Data Grid for medical images has been developed at the Image Processing and Informatics Laboratory, USC to provide distribution and fault-tolerant storage of medical imaging studies across Internet2 and public domain. Although back-up policies and grid certificates guarantee privacy and authenticity of grid-access-points, there still lacks a method to guarantee the sensitive DICOM images have not been altered or corrupted during transmission across a public domain. This paper takes steps toward achieving full image transfer security within the Data Grid by utilizing DICOM image authentication and a HIPAA-compliant auditing system. The 3-D lossless digital signature embedding procedure involves a private 64 byte signature that is embedded into each original DICOM image volume, whereby on the receiving end the signature can to be extracted and verified following the DICOM transmission. This digital signature method has also been developed at the IPILab. The HIPAA-Compliant Auditing System (H-CAS) is required to monitor embedding and verification events, and allows monitoring of other grid activity as well. The H-CAS system federates the logs of transmission and authentication events at each grid-access-point and stores it into a HIPAA-compliant database. The auditing toolkit is installed at the local grid-access-point and utilizes Syslog [1], a client-server standard for log messaging over an IP network, to send messages to the H-CAS centralized database. By integrating digital image signatures and centralized logging capabilities, DICOM image integrity within the Medical Imaging and Informatics Data Grid can be monitored and guaranteed without loss to any image quality.

LCDs suffer from viewing angle dependency, meaning that characteristics of LCDs change with viewing angle. DICOM GSDF calibration and corresponding quality checks typically take place for on-axis viewing. However, users will use the display for a broad range of viewing angles. Several studies have shown that when calibration is done for on-axis viewing then the display is not accurately complying with the DICOM GSDF standard when viewing off-axis. This paper presents a novel solution: we adapt the DICOM GSDF calibration algorithm to have inherent robustness against change of viewing angle. A validation has been done by means of a 5 Mega Pixel medical display. Results show that it is possible to double the range of viewing angles (18° instead of 9°) for which the display is within the 10% tolerance as defined in the DICOM GSDF standard. This result is very useful because users typically will use their displays also for off-axis viewing angles.

We explore the calibration of a high luminance range, dual-layer, liquid crystal display (LCD) prototype. The operation of the prototype is done by splitting a high luminance resolution image (graylevel > 2⁸) into two 8-bit depth components and sending these images to the two liquid crystal panels stacked over the backlight module. By interpolation of a small set of luminance data gathered using a specialized luminance probe, the look-up table of graylevel pairs of front/back layer LCD and the corresponding luminance values can be generated. To display images, we fit an extended DICOM model to the interpolated luminance table which is adjustable for graylevel and luminance depth. A dynamic look up table is generated in which for each luminance there are several graylevel pair candidates. We show results for one possible calibration strategy involving the pair selection criterion. By selecting the pair that maximizes back-layer smoothness, the images with arbitrary graylevel and luminance depth can be then displayed with equal perceptual distance between luminance levels, while minimizing parallax effects. Other possible strategies that minimize glare and noise are also described. The results can be used for high luminance range display performance characterization and for the evaluation of its clinical significance.

Under typical dark conditions found in reading rooms, a reader's pupils will contract and dilate as the visual focus intermittently shifts between the high luminance monitor and the darker background wall, resulting in increased visual fatigue and the degradation of diagnostic performance. A controlled increase of ambient lighting may, however, minimize these visual adjustments and potentially improve reader comfort and accuracy. This paper details results from two psychophysical studies designed to determine the effect of a controlled ambient lighting increase on observer detection of subtle objects and lesions viewed on a DICOM-calibrated medical-grade LCD. The first study examined the effect of increased ambient lighting on detection of subtle objects embedded within a uniform background, while the second study examined observer detection performance of subtle cancerous lesions in mammograms and chest radiographs. In both studies, observers were presented with images under a dark room condition (1 lux) and an increased room illuminance level (50 lux) for which the luminance level of the diffusely reflected light from the background wall was approximately equal to that of the displayed image. The display was calibrated to an effective luminance ratio of 409 for both lighting conditions. Observer detection performance under each room illuminance condition was then compared. Identification of subtle objects embedded within the uniform background improved from 59% to 67%, while detection time decreased slightly with additional illuminance. An ROC analysis of the anatomical image results revealed that observer AUC values remained constant while detection time decreased under increased illuminance. The results provide evidence that an ambient lighting increase may be possible without compromising diagnostic efficacy.

Computer assistance in image-based diagnosis and therapy are continuously growing fields that have gained importance in several medical disciplines. Today, various free and commercial tools are available. However, only few are routinely applied in clinical practice. Especially tools that provide a flsupport of the whole design process from development and evaluation to the actual deployment in a clinical environment are missing. In this work, we introduce a categorization of the design process into different types and fields of application. To this end, we propose a novel framework that allows the development of software assistants that can be integrated into the design process of new algorithms and systems. We focus on the specific features of software prototypes that are valuable for engineers and clinicians, rather than on product development. An important aspect in this work is the categorization of the software design process into different components. Furthermore, we examine the interaction between these categories based on a new knowledge flow model. Finally, an encapsulation of these tasks within an application framework is proposed. We discuss general requirements and present a layered architecture. Several components for data- and workflow-management provide a generic functionality that can be customized on the developer and the user level. A flexible handling of is offered through the use of a visual programming and rapid prototyping platform. Currently, the framework is used in 15 software prototypes and as a basis of commercial products. More than 90 clinical partners all over the world work with these tools.

The Information Management Toolkit (ImTK) Consortium is an open source initiative to develop robust, freely available tools related to the information management needs of basic, clinical, and translational research. An open source framework and agile programming methodology can enable distributed software development while an open architecture will encourage interoperability across different environments. The ISIS Center has conceptualized a prototype data sharing network that simulates a multi-center environment based on a federated data access model. This model includes the development of software tools to enable efficient exchange, sharing, management, and analysis of multimedia medical information such as clinical information, images, and bioinformatics data from multiple data sources. The envisioned ImTK data environment will include an open architecture and data model implementation that complies with existing standards such as Digital Imaging and Communications (DICOM), Health Level 7 (HL7), and the technical framework and workflow defined by the Integrating the Healthcare Enterprise (IHE) Information Technology Infrastructure initiative, mainly the Cross Enterprise Document Sharing (XDS) specifications.

Digital Imaging and Communications in Medicine (DICOM) has standardized structure reports (SR) to fully support conventional free-text reports, images, and structured information, thus enhancing the precision, clarity, and value of clinical documents. The SR standard provides the capacity to link key images, region of interest within images, and measurement as result of Computer-Aided Diagnosis (CAD) process. Accordingly, SR bridges the traditional gap between CAD and PACS. Last year we presented an open and universal CAD-PACS integration toolkit that could seamlessly integrate standalone Computer-Aided Diagnosis (CAD) workstations with a clinical PACS based on Structure Report (SR) and IHE Post-Processing. In this presentation, we illustrate the workflow and procedures of CAD-PACS integration by showing examples from some available CAD applications using the toolkit. This proper integration will improve usage of the CAD applications for more accurate analysis and faster assessment in the clinical decisionmaking process.

The integration of imaging devices, diagnostic workstations, and image servers into Picture Archiving and Communication Systems (PACS) has had an enormous effect on the efficiency of radiology workflows. The standardization of the information exchange between the devices with the DICOM standard has been an essential precondition for that development. For surgical procedures, no such infrastructure exists. With the increasingly important role computerized planning and assistance systems play in the surgical domain, an infrastructure that unifies the communication between devices becomes necessary. In recent publications, the need for a modularized system design has been established. A reference architecture for a Therapy Imaging and Model Management System (TIMMS) has been proposed. It was accepted by the DICOM Working Group 6 as the reference architecture for DICOM developments for surgery. In this paper we propose the inclusion of implant planning systems into the PACS infrastructure. We propose a generic information model for the patient specific selection and positioning of implants from a repository according to patient image data. The information models are based on clinical workflows from ENT, cardiac, and orthopedic surgery as well as technical requirements derived from different use cases and systems. We show an exemplary implementation of the model for application in ENT surgery: the selection and positioning of an ossicular implant in the middle ear. An implant repository is stored in the PACS. It makes use of an experimental implementation of the Surface Mesh Module that is currently being developed as extension to the DICOM standard.

The situation today in most operating theaters is characterized by a large number of highly specialized but isolated surgical-assist systems. Integration of these systems into a complete solution is the key to maximize their usefulness and cost-effectiveness through optimization of the data flow and reuse of existing hardware. Goal of the integration is the design of a distributed assist system by connecting multiple independent components using standard protocols for communication and data exchange. Required surgical functionalities are created by combining the appropriate components. Such a distributed assist system induces fundamental changes in the nature of the data flow among individual components. Today, components tend to exchange more-or-less independent and self-contained units of information which they process once the complete data set has arrived. However, with distributed functionalities and tighter integration necessary to complete a surgical process, increased continuous data transfer and processing will be required. To handle this type of data transmission, the system will have to support streaming of continuous data. We present a general framework for the integration of data streaming into the Digital Operating Room. The approach presented provides a two level system in which the management and supervision of the data producing and consuming devices is independent of the actual mechanisms used to transmit the data. This approach allows the use of infrastructure and transmission technologies specially adapted to the specific needs of the streamed data.

Endoscopy is a medical technology used to inspect the inner surface of organs such as the colon. During endoscopic inspection of the colon or colonoscopy, a tiny video camera generates a video signal, which is displayed on a monitor for manual interpretation by physicians. In practice, these images are not typically captured, which may be attributed by lack of tools for automatic capturing, automatic analysis of important contents, and quick and easy access to these contents. However, this lack of tools is being addressed by recent research efforts. This paper presents the description and evaluation results of novel software that automates the capture of all images of a single colonoscopy into a single digitized video file. The system uses metrics based on color and motion over time to determine whether the images are derived from inside a single patient. During testing our system extracted 173 videos totaling 70 hours of endoscopic video, out of 230 hours of raw video, with a segment-based sensitivity of 100% and specificity of 99%. No procedures were missed. Two video files contained only a non-patient video signal. The features of our system are robust enough to be suitable for day-to-day use in medical practice.

Workflow analysis can be used to record the steps taken during clinical interventions with the goal of identifying bottlenecks and streamlining the procedure efficiency. In this study, we recorded the workflow for uterine fibroid embolization (UFE) procedures in the interventional radiology suite at Georgetown University Hospital in Washington, DC, USA. We employed a custom client/server software architecture developed by the Innovation Center for Computer Assisted Surgery (ICCAS) at the University of Leipzig, Germany. This software runs in a JAVA environment and enables an observer to record the actions taken by the physician and surgical team during these interventions. The data recorded is stored as an XML document, which can then be further processed. We recorded data from 30 patients and found a mean intervention time of 01:49:46 (+/- 16:04) minutes. The critical intervention step, the embolization, had a mean time of 00:15:42 (+/- 05:49) minutes, which was only 15% of the total intervention time.

The image-guided surgery toolkit (IGSTK) is an open source C++ library that provides the basic components required for developing image-guided surgery applications. While the initial version of the toolkit has been released, some additional functionalities are required for certain applications. With increasing demand for real-time intraoperative image data in image-guided surgery systems, we are adding a video grabber component to IGSTK to access intraoperative imaging data such as video streams. Intraoperative data could be acquired from real-time imaging modalities such as ultrasound or endoscopic cameras. The acquired image could be displayed as a single slice in a 2D window or integrated in a 3D scene. For accurate display of the intraoperative image relative to the patient's preoperative image, proper interaction and synchronization with IGSTK's tracker and other components is necessary. Several issues must be considered during the design phase: 1) Functions of the video grabber component 2) Interaction of the video grabber component with existing and future IGSTK components; and 3) Layout of the state machine in the video grabber component. This paper describes the video grabber component design and presents example applications using the video grabber component.

This work focuses on image retrieval utilizing principal component analysis (PCA) and linear discriminant analysis (LDA) techniques for brain tumors from Magnetic Resonance (MR) studies. The research has been broken into three stages. Stage 1 consists of developing the PCA and LDA algorithms to be used for content based image retrieval (CBIR) systems. Stage 2 consists of evaluation of PCA and LDA algorithms on synthetic tumor images with added noise and shading artifacts. Stage 3 consists of tailoring the algorithm specifically for automated detection and CBIR system of MR contrast enhancing tumors matching a given query image. The algorithm has been developed and tested successfully for synthetic tumor images and actual contrast enhanced tumors. We hope to integrate the PCA and LDA algorithms to perform an indexing of the tumor shapes derived from actual MR images. Two relevant indices: size and location will also be used to index the data.

PACS display workstations usually display medical image volumes in one single pattern at one time. Though some image workstations may offer three orthogonal views for orientation, users are not allowed to view different patterns of three dimensional objects simultaneously. In this paper, we propose a novel framework that integrates different rendering methods by utilizing the pipeline mechanism of Visualization Toolkit (VTK). VTK is an open source software system for 3D computer graphics, image processing, and visualization. On the basis of VTK, this image display framework can display multidimensional medical images in two different patterns, Multi-Planar Reformation (MPR) and Maximum/Minimum Intensity Projection (MIP), at the same time with most freedom by allowing users to configure viewpoint freely, what we call Free-MPR, and to shift between different patterns unlimitedly. Furthermore, the framework can be easily applied to medical image workstation or Web-based network application for it is provide as a plug-in that can be integrated conveniently. The preliminary testing results showed that our developed MedViewCtrl display framework can be integrated into any Windows Program based display software or Internet Explore Web Browser to provide multiwindow and multidimensional medical image visualization functionality for higher volume medical image data sets.

The demand for sharing medical information has kept rising. However, the transmission and displaying of high resolution medical images are limited if the network has a low transmission speed or the terminal devices have limited resources. In this paper, we present an approach based on JPEG2000 Interactive Protocol (JPIP) to browse high resolution medical images in an efficient way. We designed and implemented an interactive image communication system with client/server architecture and integrated it with Picture Archiving and Communication System (PACS). In our interactive image communication system, the JPIP server works as the middleware between clients and PACS servers. Both desktop clients and wireless mobile clients can browse high resolution images stored in PACS servers via accessing the JPIP server. The client can only make simple requests which identify the resolution, quality and region of interest and download selected portions of the JPEG2000 code-stream instead of downloading and decoding the entire code-stream. After receiving a request from a client, the JPIP server downloads the requested image from the PACS server and then responds the client by sending the appropriate code-stream. We also tested the performance of the JPIP server. The JPIP server runs stably and reliably under heavy load.

We have been advancing the study of method to quantitatively systematize nodules by conducting the statistical comparison survey of relation between image features and clinical pathological features, reason of postoperative recurrence and death. But necessary research data is huge, and because of this problem, the management and use of image information such as diagnostic information, image features is difficult. Nodule systematization using database is being proposed as the solution. We think that more efficient nodule schematization can be realized by managing, searching and comparing image information efficiently using database. In this paper, we describe nodule systematization using database and describe the construction of database as the core, and user interface which can be easily operated on GUI. We also describe operational result and evaluation, making it as the prototype.

In this work, a concept for coupling a system for content-based image retrieval in medical applications (IRMA) with hospital information systems is presented. We aim at improving the work flow of radiologists and evaluating the recognition performance of the IRMA system in clinical routine. The integration is designed such that a failure of IRMA does not affect the routine operation of the other systems. The coupling is realized by generic communication modules with the radiology information system, and the picture archiving and communication system (PACS) over the standard protocols Digital Imaging and Communications in Medicine (DICOM) and Health Layer 7 (HL7). An optional plug-in for the radiological viewing station further enhances the usability. Based on this concept, the pre-fetching of relevant images for recurrent examinations is improved. When an examination is scheduled, all previous images of the patient are read by the IRMA system with DICOM query/retrieve. If the images were not present before in our database, features are extracted, stored, and indexed. After the acquisition of new images from the imaging modality, the new images are automatically retrieved by the IRMA system with DICOM query/retrieve and similar images are selected based on the stored global signatures. These images are then loaded into the online storage of the PACS and are available for diagnostic purposes together with those images already pre-selected by the PACS. Thus the radiologist can avoid further delays resulting from manually fetching further images from archives which have not been automatically selected by alphanumerical meta data. In addition, he is able to sort all fetched images by the computed IRMA-similarity. Furthermore, the hanging of images in the viewing software is planned to be organized by IRMA suggestions automatically, further shortening the time for the examination and reducing manual interactions. Based on the generality of our integration concept, a CBIR-based second opinion to support the diagnostics, and computer-based training of radiologists will be established in near future.

The current study describes the experience in the implementation of a mobile HIS/PACS workstation to assist critical cardiac patients in an Intensive Care Unit (ICU). Recently, mobile devices connected to a WiFi network were incorporated to the Hospital information System, providing the same functionalities of common desktop counterpart. However, the use of commercially devices like PDAs and Pocket PCs presented a series of problems that are more emphasized in the ICUs 1) low autonomy of the batteries, which need constant recharges; 2) low robustness of the devices; 3) insufficient display area to show medical images and vital signals; 4) data entry remains a major problem and imposes an extra time consumption to the staff; 5) high cost when fully equipped with WiFi connection, optical reader to access bar codes and memory. To address theses problems we developed a mobile workstation (MedKart) that provides access the HIS and PACS systems, with all resources and an ergonomic and practical design to be used by physicians and nurses inside the ICU. The system fulfills the requirements to assist, in the point-of-care, critical cardiac patients in Intensive Care Units.

Mass screening based on multi-helical CT images requires a considerable number of images to be read. It is this time-consuming step that makes the use of helical CT for mass screening impractical at present. To overcome this problem, we have provided diagnostic assistance methods to medical screening specialists by developing a lung cancer screening algorithm that automatically detects suspected lung cancers in helical CT images, a coronary artery calcification screening algorithm that automatically detects suspected coronary artery calcification and a vertebra body analysis algorithm for quantitative evaluation of osteoporosis likelihood by using helical CT scanner for the lung cancer mass screening. The function to observe suspicious shadow in detail are provided in computer-aided diagnosis workstation with these screening algorithms. We also have developed the telemedicine network by using Web medical image conference system with the security improvement of images transmission, Biometric fingerprint authentication system and Biometric face authentication system. Biometric face authentication used on site of telemedicine makes "Encryption of file" and Success in login" effective. As a result, patients' private information is protected. Based on these diagnostic assistance methods, we have developed a new computer-aided workstation and a new telemedicine network that can display suspected lesions three-dimensionally in a short time. The results of this study indicate that our radiological information system without film by using computer-aided diagnosis workstation and our telemedicine network system can increase diagnostic speed, diagnostic accuracy and security improvement of medical information.

The transition of a development prototype to a product is a challenging task. There are several shortcomings of a prototype such as the difficulty of client deployment, configuration issues and memory usage. The Eclipse RCP is a platform for development that offers many advantages such as: multiplatform nature; small memory footprint usage and extensible architecture. In this work we present the use of the Eclipse Rich Client Platform (RCP) as the basis for the deployment of a Contextual Medical Image Viewer. The Contextual Viewer is a concept of interface for medical/clinical information visualization that uses different contexts to enhance the user's capability and experience. We present the contextual viewer for X-Ray Angiographic images, based on Eclipse RCP, which can use information from two different sources. We conclude that the Eclipse RCP is a promising platform for final-user quality software, improving the Contextual Medical Image Viewer features.

Bone age assessment is most commonly performed with the use of the Greulich and Pyle (G&P) book atlas, which was developed in the 1950s. The population of theUnited States is not as homogenous as the Caucasian population in the Greulich and Pyle in the 1950s, especially in the Los Angeles, California area. A digital hand atlas (DHA) based on 1,390 hand images of children of different racial backgrounds (Caucasian, African American, Hispanic, and Asian) aged 0-18 years was collected from Children's Hospital Los Angeles. Statistical analysis discovered significant discrepancies exist between Hispanic and the G&P atlas standard. To validate the usage of DHA as a clinical standard, diagnostic radiologists performed reads on Hispanic pediatric hand and wrist computed radiography images using either the G&P pediatric radiographic atlas or the Children's Hospital Los Angeles Digital Hand Atlas (DHA) as reference. The order in which the atlas is used (G&P followed by DHA or vice versa) for each image was prepared before actual reading begins. Statistical analysis of the results was then performed to determine if a discrepancy exists between the two readings.