Showing papers in "Journal of Digital Imaging in 2007"

Fractal Analysis of Contours of Breast Masses in Mammograms

Abstract: Fractal analysis has been shown to be useful in image processing for characterizing shape and gray-scale complexity. Breast masses present shape and gray-scale characteristics that vary between benign masses and malignant tumors in mammograms. Limited studies have been conducted on the application of fractal analysis specifically for classifying breast masses based on shape. The fractal dimension of the contour of a mass may be computed either directly from the 2-dimensional (2D) contour or from a 1-dimensional (1D) signature derived from the contour. We present a study of four methods to compute the fractal dimension of the contours of breast masses, including the ruler method and the box counting method applied to 1D and 2D representations of the contours. The methods were applied to a data set of 111 contours of breast masses. Receiver operating characteristics (ROC) analysis was performed to assess and compare the performance of fractal dimension and four previously developed shape factors in the classification of breast masses as benign or malignant. Fractal dimension was observed to complement the other shape factors, in particular fractional concavity, in the representation of the complexity of the contours. The combination of fractal dimension with fractional concavity yielded the highest area (Az) under the ROC curve of 0.93; the two measures, on their own, resulted in Az values of 0.89 and 0.88, respectively.

Increasing the number of gray shades in medical display systems--how much is enough?

Abstract: Medical images produced by x-ray detectors, computed tomography (CT) scanners, and other modalities typically contain between 12–16 bits/pixel, which corresponds to 4,096–65,536 shades of gray. On the other hand, we see that these images are visualized by means of medical displays that have much lower available number of gray shades. For a long time medical LCDs only supported 8 bits or 256 shades of gray per pixel. With the introduction of medical displays optimized for mammography, the available number of gray scales increased to 1,024. Recently, several manufacturers announced new display systems with higher bit depth. Because higher bit depth often directly results in higher display cost, it is a logical question to ask if this is required or even useful at all. This paper will give an answer by investigating several aspects such as limitations of the human visual system, digital imaging and communication in medicine grayscale standard display function calibration, and characteristics of medical LCDs.

Protégé: a tool for managing and using terminology in radiology applications.

Abstract: The development of standard terminologies such as RadLex is becoming important in radiology applications, such as structured reporting, teaching file authoring, report indexing, and text mining. The development and maintenance of these terminologies are challenging, however, because there are few specialized tools to help developers to browse, visualize, and edit large taxonomies. Protege (http://protege.stanford.edu) is an open-source tool that allows developers to create and to manage terminologies and ontologies. It is more than a terminology-editing tool, as it also provides a platform for developers to use the terminologies in end-user applications. There are more than 70,000 registered users of Protege who are using the system to manage terminologies and ontologies in many different domains. The RadLex project has recently adopted Protege for managing its radiology terminology. Protege provides several features particularly useful to managing radiology terminologies: an intuitive graphical user interface for navigating large taxonomies, visualization components for viewing complex term relationships, and a programming interface so developers can create terminology-driven radiology applications. In addition, Protege has an extensible plug-in architecture, and its large user community has contributed a rich library of components and extensions that provide much additional useful functionalities. In this report, we describe Protege’s features and its particular advantages in the radiology domain in the creation, maintenance, and use of radiology terminology.

Content-based Retrieval of Mammograms Using Visual Features Related to Breast Density Patterns

Abstract: This paper describes part of content-based image retrieval (CBIR) system that has been developed for mammograms. Details are presented of methods implemented to derive measures of similarity based upon structural characteristics and distributions of density of the fibroglandular tissue, as well as the anatomical size and shape of the breast region as seen on the mammogram. Well-known features related to shape, size, and texture (statistics of the gray-level histogram, Haralick’s texture features, and moment-based features) were applied, as well as less-explored features based in the Radon domain and granulometric measures. The Kohonen self-organizing map (SOM) neural network was used to perform the retrieval operation. Performance evaluation was done using precision and recall curves obtained from comparison between the query and retrieved images. The proposed methodology was tested with 1,080 mammograms, including craniocaudal and mediolateral-oblique views. Precision rates obtained are in the range from 79% to 83% considering the total image set. Considering the first 50% of the retrieved mages, the precision rates are in the range from 78% to 83%; the rates are in the range from 79% to 86% considering the first 25% of the retrieved images. Results obtained indicate the potential of the implemented methodology to serve as a part of a CBIR system for mammography.

The Image-Guided Surgery Toolkit IGSTK: An Open Source C++ Software Toolkit

Abstract: This paper presents an overview of the image-guided surgery toolkit (IGSTK). IGSTK is an open source C++ software library that provides the basic components needed to develop image-guided surgery applications. It is intended for fast prototyping and development of image-guided surgery applications. The toolkit was developed through a collaboration between academic and industry partners. Because IGSTK was designed for safety-critical applications, the development team has adopted lightweight software processes that emphasizes safety and robustness while, at the same time, supporting geographically separated developers. A software process that is philosophically similar to agile software methods was adopted emphasizing iterative, incremental, and test-driven development principles. The guiding principle in the architecture design of IGSTK is patient safety. The IGSTK team implemented a component-based architecture and used state machine software design methodologies to improve the reliability and safety of the components. Every IGSTK component has a well-defined set of features that are governed by state machines. The state machine ensures that the component is always in a valid state and that all state transitions are valid and meaningful. Realizing that the continued success and viability of an open source toolkit depends on a strong user community, the IGSTK team is following several key strategies to build an active user community. These include maintaining a users and developers’ mailing list, providing documentation (application programming interface reference document and book), presenting demonstration applications, and delivering tutorial sessions at relevant scientific conferences.

A filmless radiology department in a full digital regional hospital: quantitative evaluation of the increased quality and efficiency.

Abstract: Reggio Emilia hospital installed Picture Archiving and Communications Systems (PACS) as the final step towards a completely digital clinical environment completing the HIS/EMR and 1,400 web/terminals for patient information access. Financial benefits throughout the hospital were assessed upfront and measured periodically. Key indicators (radiology exam turnaround time, number of radiology procedures performed, inpatients length of stay before and after the PACS implementation, etc.) were analyzed and values were statistically tested to assess workflow and productivity improvements. The hospital went “filmless” in 28 weeks. Between the half of 2004 and the respective period in 2003, overall Radiology Department productivity increased by 12%, TAT improved by more than 60%. Timelier patient care resulted in decreased lengths of stay. Neurology alone experienced a 12% improvement in average patient stay. To quantify the impact of PACS on the average hospital stays and the expected productivity benefits to inpatient productivity were used a “high level” and a “detailed” business model. Annual financial upsides have exceeded $1.9 millions/year. A well-planned PACS deployment simplifies imaging workflow and improves patient care throughout the hospital while delivering substantial financial benefits. Staff buy-in was the key in this process and on-going training and process monitoring are a must.

Pseudonymization of radiology data for research purposes.

Abstract: Medical image processing methods and algorithms, developed by researchers, need to be validated and tested. Test data would ideally be real clinical data especially that clinical data is varied and exists in large volumes. Nowadays, clinical data is accessible electronically and has important value for researchers. However, the usage of clinical data for research purposes should respect data confidentiality, patient right to privacy, and patient consent. In fact, clinical data is nominative given that it contains information about the patient such as name, age, and identification number. Evidently, clinical data needs to be de-identified to be exported to research databases. However, the same patient is usually followed during a long period of time. The disease progression and the diagnostic evolution represent extremely valuable information for researchers as well. Our objective is to build a research database from de-identified clinical data while enabling the data set to be easily incremented by exporting new pseudonymous data, acquired over a long period of time. Pseudonymization is data de-identification, such that data belonging to an individual in the clinical environment still belong to the same individual in the de-identified research version. In this paper, we explore various software architectures to enable the implementation of an imaging research database that can be incremented in time. We also evaluate their security and discuss their security pitfalls. As most imaging data accessible electronically is available with the digital imaging and communication in medicine (DICOM) standard, we propose a de-identification scheme that closely follows DICOM recommendations. Our work can be used to enable electronic health record (EHR) secondary usage such as public surveillance and research, while maintaining patient confidentiality.

Benefits of using the DCM4CHE DICOM archive.

Abstract: With advances in digital imaging throughout the 1990s and the rapid adoption of Picture Archiving and Communication Systems (PACS) in the last decade, standards for information exchange have become crucial to effective communication, both within the radiology department and with the larger enterprise and outside institutions and agencies. The original Digital Imaging and Communications in Medicine1 (DICOM) standard was introduced in 1993 and, in the intervening years, has been widely adopted. Interest in DICOM, as well as the continuous integration of new technologies and modalities into medical imaging, has resulted in a series of new and revised DICOM standards. Along with the growing complexity of these standards has come a need for tools that can manipulate and store DICOM information. In 2000, responding to these needs, JDicom, a toolkit written in the Java programming language, was developed for manipulating DICOM. The popularity of this new tool kit persuaded its lead developer to build a full-featured DICOM archive. The mission of the project was to produce a DICOM archive that was free, open-source, and cross-platform and that embraced new directions being drawn up by the Integrating the Health Care Enterprise (IHE) initiative. This ambitious goal attracted more developers, and the DCM4CHE2 project was born. After 7 years of development, the DCM4CHE project has produced two generations of a DICOM archive. The current generation is the result of learned practical experience and reflects the old programmer’s adage: “Build it twice, because you will anyway.” This article reviews DCM4CHE and the DCM4CHE DICOM archive (DCM4CHEE) and evaluates their maturation as a viable platform for training, integration testing, and research.

Level Set Contouring for Breast Tumor in Sonography

Abstract: The echogenicity, echotexture, shape, and contour of a lesion are revealed to be effective sonographic features for physicians to identify a tumor as either benign or malignant. Automatic contouring for breast tumors in sonography may assist physicians without relevant experience, in making correct diagnoses. This study develops an efficient method for automatically detecting contours of breast tumors in sonography. First, a sophisticated preprocessing filter reduces the noise, but preserves the shape and contrast of the breast tumor. An adaptive initial contouring method is then performed to obtain an approximate circular contour of the tumor. Finally, the deformation-based level set segmentation automatically extracts the precise contours of breast tumors from ultrasound (US) images. The proposed contouring method evaluates US images from 118 patients with breast tumors. The contouring results, obtained with computer simulation, reveal that the proposed method always identifies similar contours to those obtained with manual sketching. The proposed method provides robust and fast automatic contouring for breast US images. The potential role of this approach might save much of the time required to sketch a precise contour with very high stability.

Rapid development of medical imaging tools with open-source libraries.

Abstract: Rapid prototyping is an important element in researching new imaging analysis techniques and developing custom medical applications. In the last ten years, the open source community and the number of open source libraries and freely available frameworks for biomedical research have grown significantly. What they offer are now considered standards in medical image analysis, computer-aided diagnosis, and medical visualization. A cursory review of the peer-reviewed literature in imaging informatics (indeed, in almost any information technology-dependent scientific discipline) indicates the current reliance on open source libraries to accelerate development and validation of processes and techniques. In this survey paper, we review and compare a few of the most successful open source libraries and frameworks for medical application development. Our dual intentions are to provide evidence that these approaches already constitute a vital and essential part of medical image analysis, diagnosis, and visualization and to motivate the reader to use open source libraries and software for rapid prototyping of medical applications and tools.

Quality of Compressed Medical Images

Abstract: Previous studies have shown that Joint Photographic Experts Group (JPEG) 2000 compression is better than JPEG at higher compression ratio levels. However, some findings revealed that this is not valid at lower levels. In this study, the qualities of compressed medical images in these ratio areas (∼20), including computed radiography, computed tomography head and body, mammographic, and magnetic resonance T1 and T2 images, were estimated using both a pixel-based (peak signal to noise ratio) and two 8 × 8 window-based [Q index and Moran peak ratio (MPR)] metrics. To diminish the effects of blocking artifacts from JPEG, jump windows were used in both window-based metrics. Comparing the image quality indices between jump and sliding windows, the results showed that blocking artifacts were produced from JPEG compression, even at low compression ratios. However, even after the blocking artifacts were omitted in JPEG compressed images, JPEG2000 outperformed JPEG at low compression levels. We found in this study that the image contrast and the average gray level play important roles in image compression and quality evaluation. There were drawbacks in all metrics that we used. In the future, the image gray level and contrast effect should be considered in developing new objective metrics.

BRISC—An Open Source Pulmonary Nodule Image Retrieval Framework

Abstract: We have created a content-based image retrieval framework for computed tomography images of pulmonary nodules. When presented with a nodule image, the system retrieves images of similar nodules from a collection prepared by the Lung Image Database Consortium (LIDC). The system (1) extracts images of individual nodules from the LIDC collection based on LIDC expert annotations, (2) stores the extracted data in a flat XML database, (3) calculates a set of quantitative descriptors for each nodule that provide a high-level characterization of its texture, and (4) uses various measures to determine the similarity of two nodules and perform queries on a selected query nodule. Using our framework, we compared three feature extraction methods: Haralick co-occurrence, Gabor filters, and Markov random fields. Gabor and Markov descriptors perform better at retrieving similar nodules than do Haralick co-occurrence techniques, with best retrieval precisions in excess of 88%. Because the software we have developed and the reference images are both open source and publicly available they may be incorporated into both commercial and academic imaging workstations and extended by others in their research.

Usefulness of Texture Analysis for Computerized Classification of Breast Lesions on Mammograms

Abstract: This work presents the usefulness of texture features in the classification of breast lesions in 5518 images of regions of interest, which were obtained from the Digital Database for Screening Mammography that included microcalcifications, masses, and normal cases. Sixteen texture features were used, i.e., 13 were based on the spatial gray-level dependence matrix and 3 on the wavelet transform. The nonparametric K-NN classifier was used in the classification stage. The results obtained from receiver operating characteristic analysis indicated that the texture features can be used for separating normal regions and lesions with masses and microcalcifications, yielding the area under the curve (AUC) values of 0.957 and 0.859, respectively. However, the texture features were not very effective for distinguishing between malignant and benign lesions because the AUC was 0.617 for masses and 0.607 for microcalcifications. The study showed that the texture features can be used for the detection of suspicious regions in mammograms.

A CT Database for Research, Development and Education: Concept and Potential

Abstract: Both in radiology and in surgery, numerous applications are emerging that enable 3D visualization of data from various imaging modalities. In clinical practice, the patient's images are analyzed on work stations in the Radiology Department. For specific preclinical and educational applications, however, data from single patients are insufficient. Instead, similar scans from a number of individuals within a collective must be compiled. The definition of standardized acquisition procedures and archiving formats are prerequisite for subsequent analysis of multiple data sets. Focusing on bone morphology, we describe our concept of a computer database of 3D human bone models obtained from computed tomography (CT) scans. We further discuss and illustrate deployment areas ranging from prosthesis design, over virtual operation simulation up to 3D anatomy atlases. The database of 3D bone models described in this work, created and maintained by the AO Development Institute, may be accessible to research institutes on request.

CAVASS: A Computer-Assisted Visualization and Analysis Software System

Abstract: The Medical Image Processing Group at the University of Pennsylvania has been developing (and distributing with source code) medical image analysis and visualization software systems for a long period of time. Our most recent system, 3DVIEWNIX, was first released in 1993. Since that time, a number of significant advancements have taken place with regard to computer platforms and operating systems, networking capability, the rise of parallel processing standards, and the development of open-source toolkits. The development of CAVASS by our group is the next generation of 3DVIEWNIX. CAVASS will be freely available and open source, and it is integrated with toolkits such as Insight Toolkit and Visualization Toolkit. CAVASS runs on Windows, Unix, Linux, and Mac but shares a single code base. Rather than requiring expensive multiprocessor systems, it seamlessly provides for parallel processing via inexpensive clusters of work stations for more time-consuming algorithms. Most importantly, CAVASS is directed at the visualization, processing, and analysis of 3-dimensional and higher-dimensional medical imagery, so support for digital imaging and communication in medicine data and the efficient implementation of algorithms is given paramount importance.

Comparison of Color LCD and Medical-grade Monochrome LCD Displays in Diagnostic Radiology

Abstract: In diagnostic radiology, medical-grade monochrome displays are usually recommended because of their higher luminance. Standard color displays can be used as a less expensive alternative, but have a lower luminance. The aim of the present study was to compare image quality for these two types of displays. Images of a CDRAD contrast-detail phantom were read by four radiologists using a 2-megapixel (MP) color display (143 cd/m2 maximum luminance) as well as 2-MP (295 cd/m2) and 3-MP monochrome displays. Thirty lumbar spine radiographs were also read by four radiologists using the color and the 2-MP monochrome display in a visual grading analysis (VGA). Very small differences were found between the displays when reading the CDRAD images. The VGA scores were −0.28 for the color and −0.25 for the monochrome display (p = 0.24; NS). It thus seems possible to use color displays in diagnostic radiology provided that grayscale adjustment is used.

Open source in imaging informatics.

Abstract: The open source community within radiology is a vibrant collection of developers and users working on scores of collaborative projects with the goal of promoting the use of information technology within radiology for education, clinical, and research purposes. This community, which includes many commercial partners, has a rich history in supporting the success of the digital imaging and communication in medicine (DICOM) standard and today is pioneering interoperability limits by embracing the Integrating the Healthcare Enterprise. This article describes only a small portion of the more successful open source applications and is written to help end users see these projects as practical aids for the imaging informaticist and picture archiving and communication system (PACS) administrator.

DicomWorks: Software for Reviewing DICOM Studies and Promoting Low-cost Teleradiology

Abstract: DicomWorks is freeware software for reading and working on medical images [digital imaging and communication in medicine (DICOM)]. It was jointly developed by two research laboratories, with the feedback of more than 35,000 registered users throughout the world who provided information to guide its development. We detail their occupations (50% radiologists, 20% engineers, 9% medical physicists, 7% cardiologists, 6% neurologists, and 8% others), geographic origins, and main interests in the software. The viewer’s interface is similar to that of a picture archiving and communication system viewing station. It provides basic but efficient tools for opening DICOM images and reviewing and exporting them to teaching files or digital presentations. E-mail, FTP, or DICOM protocols are supported for transmitting images through a local network or the Internet. Thanks to its wide compatibility, a localized (15 languages) and user-friendly interface, and its opened architecture, DicomWorks helps quick development of non proprietary, low-cost image review or teleradiology solutions in developed and emerging countries.

The Impact of PACS on Radiologists’ Work Practice

Abstract: This paper identifies and analyzes how the implementation and use of picture archiving and communication system impacts radiologists’ work practice. The study is longitudinal from 1999 to 2005 and have a qualitative perspective were data were collected by structured interviews in a total of 46. The interviews were transcribed, analyzed, and coded using grounded theory as an organizing principle. In radiologists’ work practice, three main categories were defined: professional role, diagnostic practice, and technology in use. The changing trends within the professional role indicated that radiologists moved from a more individual professional expertise to become more of an actor in a network. The diagnostic practice changed, as reading x-ray films was seen as an art form in 1999, requiring years of training. Once everyone could view digital images, including 3-dimensional technology, it was easier for other clinicians to see and interpret the images and the skills become accessible to everyone. The change in technology in use as a result of the shift to digital images led to an increased specialization of the radiologist.

PDA-phone-based instant transmission of radiological images over a CDMA network by combining the PACS screen with a Bluetooth-interfaced local wireless link.

Abstract: Remote teleconsultation by specialists is important for timely, correct, and specialized emergency surgical and medical decision making. In this paper, we designed a new personal digital assistant (PDA)–phone-based emergency teleradiology system by combining cellular communication with Bluetooth-interfaced local wireless links. The mobility and portability resulting from the use of PDAs and wireless communication can provide a more effective means of emergency teleconsultation without requiring the user to be limited to a fixed location. Moreover, it enables synchronized radiological image sharing between the attending physician in the emergency room and the remote specialist on picture archiving and communication system terminals without distorted image acquisition. To enable rapid and fine-quality radiological image transmission over a cellular network in a secure manner, progressive compression and security mechanisms have been incorporated. The proposed system is tested over a code division Multiple Access 1×-Evolution Data-Only network to evaluate the performance and to demonstrate the feasibility of this system in a real-world setting.

Contrast Enhancement in Dense Breast Images to Aid Clustered Microcalcifications Detection

Abstract: This paper presents a method to provide contrast enhancement in dense breast digitized images, which are difficult cases in testing of computer-aided diagnosis (CAD) schemes Three techniques were developed, and data from each method were combined to provide a better result in relation to detection of clustered microcalcifications Results obtained during the tests indicated that, by combining all the developed techniques, it is possible to improve the performance of a processing scheme designed to detect microcalcification clusters It also allows operators to distinguish some of these structures in low-contrast images, which were not detected via conventional processing before the contrast enhancement This investigation shows the possibility of improving CAD schemes for better detection of microcalcifications in dense breast images

Effect of Automated Image Registration on Radiologist Interpretation

Abstract: In this study, we present preliminary data on the effect of automated 3D image alignment on the time to arrive at a decision about an imaging finding, the agreement of multiple of multiple observers, the prevalence of comparison examinations, and technical success rates for the image alignment algorithm. We found that automated image alignment reduced the average time to make a decision by 25% for cases where the structures are rigid, and when the scanning protocol is similar. For cases where these are not true, there is little or no benefit. In our practice, 54% of cases had prior examinations that could be automatically aligned. The overall benefit seen in our department for highly similar exams might be 20% for neuro and 10% for body; the benefit seen in other practices is likely to vary based on scanning practices and prevalence of prior examinations.

Part 1. Automated change detection and characterization in serial MR studies of brain-tumor patients.

Abstract: The goal of this study was to create an algorithm which would quantitatively compare serial magnetic resonance imaging studies of brain-tumor patients A novel algorithm and a standard classify–subtract algorithm were constructed The ability of both algorithms to detect and characterize changes was compared using a series of digital phantoms The novel algorithm achieved a mean sensitivity of 087 (compared with 059 for classify–subtract) and a mean specificity of 098 (compared with 092 for classify–subtract) with regard to identification of voxels as changing or unchanging and classification of voxels into types of change The novel algorithm achieved perfect specificity in seven of the nine experiments The novel algorithm was additionally applied to a short series of clinical cases, where it was shown to identify visually subtle changes Automated change detection and characterization could facilitate objective review and understanding of serial magnetic resonance imaging studies in brain-tumor patients

GridIMAGE: a novel use of grid computing to support interactive human and computer-assisted detection decision support.

Abstract: This paper describes a Grid-aware image reviewing system (GridIMAGE) that allows practitioners to (a) select images from multiple geographically distributed digital imaging and communication in medicine (DICOM) servers, (b) send those images to a specified group of human readers and computer-assisted detection (CAD) algorithms, and (c) obtain and compare interpretations from human readers and CAD algorithms. The currently implemented system was developed using the National Cancer Institute caGrid infrastructure and is designed to support the identification of lung nodules on thoracic computed tomography. However, the infrastructure is general and can support any type of distributed review. caGrid data and analytical services are used to link DICOM image databases and CAD systems and to interact with human readers. Moreover, the service-oriented and distributed structure of the GridIMAGE framework enables a flexible system, which can be deployed in an institution (linking multiple DICOM servers and CAD algorithms) and in a Grid environment (linking the resources of collaborating research groups). GridIMAGE provides a framework that allows practitioners to obtain interpretations from one or more human readers or CAD algorithms. It also provides a mechanism to allow cooperative imaging groups to systematically perform image interpretation tasks associated with research protocols.

Open source software projects of the caBIG In Vivo Imaging Workspace Software special interest group.

Abstract: The Cancer Bioinformatics Grid (caBIG™) program was created by the National Cancer Institute to facilitate sharing of IT infrastructure, data, and applications among the National Cancer Institute-sponsored cancer research centers. The program was launched in February 2004 and now links more than 50 cancer centers. In April 2005, the In Vivo Imaging Workspace was added to promote the use of imaging in cancer clinical trials. At the inaugural meeting, four special interest groups (SIGs) were established. The Software SIG was charged with identifying projects that focus on open-source software for image visualization and analysis. To date, two projects have been defined by the Software SIG. The eXtensible Imaging Platform project has produced a rapid application development environment that researchers may use to create targeted workflows customized for specific research projects. The Algorithm Validation Tools project will provide a set of tools and data structures that will be used to capture measurement information and associated needed to allow a gold standard to be defined for the given database against which change analysis algorithms can be tested. Through these and future efforts, the caBIG™ In Vivo Imaging Workspace Software SIG endeavors to advance imaging informatics and provide new open-source software tools to advance cancer research.

Part 2. Automated change detection and characterization applied to serial MR of brain tumors may detect progression earlier than human experts.

Abstract: An algorithm was developed which compares serial MRI brain examinations of brain tumor patients and judges them as either “stable” or “progressing”. A set of 88 serial MR cases were obtained, consisting of cases which were stable and remained stable for at least 8 months, cases which were stable but progressed in less than 8 months, and cases which were progressing. The algorithm was run and its output was compared to the original clinical interpretation. Of the exam pairs which were judged stable and which remained stable at least 8 months after the later examination, the algorithm diagnosed 45/46 as stable. For exam pairs judged to be progressing, the algorithm judged 15/17 to be progressing. Of the exam pairs which were judged stable, but which went on to progress less than 8 months after the later of the pair, 16/25 were judged by the algorithm to be progressing.

Medical imaging informatics: how it improves radiology practice today.

Abstract: “Great case, next case.” —Private practice radiologists’ mantra “Faster, better, cheaper...” —Business paradigm Radiologists are under pressure to add more value to medical imaging—to provide more educated, accurate, useful, and efficient interpretations in the face of increasingly large and complex imaging studies and to communicate this information quickly and in the most useful manner. The radiology department and radiologist both need to be better, faster, and cheaper. Medical imaging informatics (MII) includes many of the processes radiologists need to reach these goals. MII is the development, application, and assessment of information technology (IT) for clinical medical imaging. It includes the interfaces of IT and people.1–3 In practical terms, MII already occurs at a basic level throughout radiology practice, from the moment a clinician considers ordering an imaging study, until images and interpretation are used to plan the patient’s treatment. MII is not an academic exercise. Every radiologist should appreciate its basics. Radiologists do not need to write computer code, but their lives will be better if they comprehend MII benefits, products, and processes and how to implement and integrate these systems at visionary and managerial levels. Picture archiving and communication systems (PACS) and Radiology information systems (RIS) are the most visible parts, but MII is more than that. Radiologists were intimately involved in PACS and RIS throughout their evolution. Now, as basic PACS/RIS become commodities in radiology practices, radiologists may lose their informatics focus. They delegate it to the IT department, radiology administrator, or certified imaging informatics professional (CIIP). To deal with the current workload, and to maintain income, radiologists often feel driven solely to interpret imaging studies. They keep their eyes on images and dictate; anything that detracts from that pattern they delegate. As in many fields, radiologists are expected to know exponentially more about new imaging techniques, findings, and clinical applications. Why, then, should they learn about MII, a potentially large and complex field that is not applicable to one’s interpretation skills, and at first glimpse, does not tie directly to patient care or revenue production? Our private practice radiology group works at disparate sites that encompass multiple PACS, dictation systems, and RISs. Qualitative observation of these various situations suggest between 25 and 100% difference in radiologist efficiency between the best and worst of our combinations. Even between two sites with supposedly the most efficient, mainline PACS, radiologist efficiency varies perceptibly. Why? Causes for this are hard to quantify. In one setting, radiologists with MII knowledge participated in PACS from the start, through design, RFP, implementation, and continued oversight. In the second setting, the hospital corporation and its IT department drove MII decisions and implementation. The second setting’s IT department is fine, and their PACS vendor is excellent. Both systems run well, are reliable, and on the surface, provide “a state-of-the-art, filmless, radiology department.” Radiologists are most efficient, however, at the hospital with an involved, designated, MII radiologist. Eliot Siegel, MD of the VA Maryland Health Care System gives a well-received talk on the tsunami wave of increasing radiology work crashing over radiologists.4 His talk contains a movie clip of Lucille Ball on the chocolate factory assembly line and her travails as chocolates on a conveyor belt rush by ever more rapidly. This analogy is painfully apt for radiologists, with their eyes on images, dictation mike in hand, who race to interpret thousands of images in time to get home for dinner. What follows is an unabashedly radiologist-centric examination of the radiologist on the assembly line and examples of how MII can improve a radiologist’s life. In a simplified model of the radiology assembly line, one may define the patient and information about him as the “entire patient entity” (EPE) that moves through the radiology department. Stations on the radiology assembly line, upstream from the radiologist, perform functions on the EPE, such as add demographic information and history, place an IV, scan the patient, post-process images, and attach relevant priors. The patient’s images and clinical information eventually arrive at the radiologist station on the assembly line. The radiologist’s responsibility is to synthesize all available information in the EPE and translate it into a clinically relevant written interpretation that, combined with relevant images, helps the treating physician decide what to do next. This interpretation is just another (albeit important) process performed on the EPE. Then, the patient and his image information, now with a report attached, move on down the line—the report distributed as needed, and the patient to the appropriate treatment. Like Lucy in the chocolate factory, the radiology assembly line is increasingly demanding and in need of improvement. One established approach to improve an assembly line is to decrease by even a tiny amount the time it takes to perform an individual step.5 If that step repeats often, the total time saving is significant. In a simplified example, for a radiologist who reads a two-view chest radiograph every 2 min, cutting out 12 s per case means that during a 10-h day, the radiologist either earns 10% more or gets home an hour earlier. Done correctly, MII can cut tiny time fragments from every facet of the radiologist’s tasks. The key concept, however, is “done correctly”. This is critical. What a radiologist does can be described simply, but beneath that description is a rich, deep set of knowledge, habits and processes every radiologist uses to perform the practice of radiology. Nobody except the radiologist will appreciate MII’s subtleties that will cut minor time increments from each task the radiologist performs for every case. If radiologists delegate decisions on planning, vendor selection, and implementation of MII components and systems, the result may be good for many things, but it will not optimize radiologists’ efficiency. A current example of nonradiologist-centric MII is voice recognition (VR) dictation of the radiology report. Errors in original project planning, vendor selection, or implementation of VR can make radiologists up to 25% less efficient.6–8 On this issue, one hospital administrator facing a group of frustrated radiologists declared, “...but VR only adds a minute or two of radiologist time to each case.” Only the radiologist has enough at stake to refocus MII onto radiologist efficiency. Four issues illustrate how an II radiologist can improve every radiologist’s experience on the assembly line. First, how should the EPE be processed before it arrives at the radiologist station, or phrased differently, what should already be attached and what steps performed before the imaging study arrives for the radiologist’s interpretation? Second, what tools does the radiologist need to maximize the time spent to get all possible information from the images or “quality eyes-on-images time?” Third, what tools and process allow the radiologist to synthesize efficiently and robustly the images, clinical data, and his medical knowledge database into a cohesive, accurate, helpful interpretation? Finally, what should be the report format as the EPE leaves the radiologist station, to enhance fast, correct, and efficient patient treatment?

Creation of a CT Image Library for the Lung Screening Study of the National Lung Screening Trial

Abstract: The CT Image Library (CTIL) of the Lung Screening Study (LSS) network of the National Lung Screening Trial (NLST) consists of up to three annual screens using CT imaging from each of 17,308 participants with a significant history of smoking but no evidence of cancer at trial enrollment (Fall 2002–Spring 2004). Screens performed at numerous medical centers associated with 10 LSS-NLST screening centers are deidentified of protected health information and delivered to the CTIL via DVD, external hard disk, or Internet/Virtual Private Network transmission. The collection will be completed in late 2006. The CTIL is of potential interest to clinical researchers and software developers of nodule detection algorithms. Its attractiveness lies in its very specific, well-defined patient population, scanned via a common CT protocol, and in its collection of evenly spaced serial screens. In this work, we describe the technical details of the CTIL collection process from screening center retrieval through library storage.

White matter fiber tracking computation based on diffusion tensor imaging for clinical applications.

Abstract: Fiber tracking allows the in vivo reconstruction of human brain white matter fiber trajectories based on magnetic resonance diffusion tensor imaging (MR-DTI), but its application in the clinical routine is still in its infancy. In this study, we present a new software for fiber tracking, developed on top of a general-purpose DICOM (digital imaging and communications in medicine) framework, which can be easily integrated into existing picture archiving and communication system (PACS) of radiological institutions. Images combining anatomical information and the localization of different fiber tract trajectories can be encoded and exported in DICOM and Analyze formats, which are valuable resources in the clinical applications of this method. Fiber tracking was implemented based on existing line propagation algorithms, but it includes a heuristic for fiber crossings in the case of disk-shaped diffusion tensors. We successfully performed fiber tracking on MR-DTI data sets from 26 patients with different types of brain lesions affecting the corticospinal tracts. In all cases, the trajectories of the central spinal tract (pyramidal tract) were reconstructed and could be applied at the planning phase of the surgery as well as in intraoperative neuronavigation.

An integrated approach to a teaching file linked to PACS.

Abstract: To meet the educational needs of a medical imaging department with a strong teaching commitment, a teaching file that uses digital data supplied by the institutional picture archiving and communications system (PACS) was required. This teaching file had to be easily used by the end users, have a simple submission process, be able to support multiple users, be searchable on all data fields, and implementing the teaching file must not incur any additional software or hardware costs. The teaching file developed to address this problem takes advantage of the database structure and capabilities of several components included in the commercial PACS installed at the hospital. MS Access is used to seamlessly integrate with the digital imaging and communication in medicine (DICOM) database of a normal work station that is part of the PACS. This integration allows relevant patient and study demographics to be copied from images of interest and then to be stored in a separate database as the back-end of the digital teaching file. When images for a particular teaching file case need to be reviewed, they are automatically retrieved and displayed from the main PACS database using an open application programming interface (API) connection defined on the PACS web server. Utilizing this open API connection means the teaching file contains only the relevant demographic information of each teaching file case; no image data is stored locally. The open API connection allows access to imaging data usually not encountered in a teaching file, allowing more comprehensive imaging case files to be developed by the radiologist. Other advantages of this teaching file design are that it does not duplicate image data, it is small allowing simple ongoing backup, and it can be opened with multiple users accessing the database without compromising data access or integrity.