RESUMEN

Health care must be understood in a way that facilitates a rational, consistent coverage and payment policy. Telephone care, telemedicine care, and in-person consultation are all useful ways of providing health care services. Because improved health and reasonable costs are the universally desired outcomes of medical consultations, reimbursement policies should favor the most efficient means of providing care. This view suggests that health care reimbursement should be made technologically neutral. That is, a covered service should produce the best clinical outcome at the lowest possible cost, irrespective of the technology used. The logic and implications of technological neutrality and its application to telemedicine are discussed.

Asunto(s)

RESUMEN

Teledermatology can be defined as the use of imaging and telecommunications technologies to provide skin care services at a distance. The potential value of teledermatology is especially great in rural and medically underserved areas that do not have, or cannot support, providers specializing in the diagnosis and management of skin diseases. Rural patients and primary care providers should be able to use teledermatology as a greatly simplified and potentially less expensive means of referral to an urban dermatologist. In an effort to gauge the impact of a simple teledermatology system on referral patterns and the management of rural patients with skin disorders, we studied baseline rates of referral to dermatologists from five primary care clinics in rural Oregon. Economical, easy-to-use teledermatology systems were subsequently installed, and the effects on patient referral and management were recorded over time. The interim results suggest that primary care providers (PCPs) are reluctant to refer patients with skin conditions, even when the primary care providers confidence in the correct diagnosis and treatment plan for that condition are relatively low. The installation of a teledermatology system increases the number of patients referred for specialist evaluation dramatically, even while the number of in-person visits to specialists fell. Although diagnostic agreement between dermatologists and primary care providers was mixed, a marked difference was found in their recommended treatment plans. A number of cases were found in which use of the telemedicine technology system resulted in reversing conditions that had been poorly controlled for a number of years prior to teleconsultation. This work is important as an indicator that referral rates to dermatologists may be inappropriately low in rural areas of the U.S., and that use of teledermatology may improve this trend.

Asunto(s)

RESUMEN

Change is not necessarily progress. Few physicians- and still fewer specialists-would characterize the wrenching changes occurring in health care over the past decade as progress. When is the last time you heard about a change in the provision of health care that gave providers more time, made practice more profitable, reduced paperwork, or made your life generally easier? Still thinking? So am I. Bad news of one sort or another has come in an unbroken stream for years now, or at least it seems that way. Payments to providers are continually reduced. Managed care has steadily reduced specialists' access to patients. The paperwork associated with referrals, billing, and laboratories continues to mount for most of us.

Asunto(s)

RESUMEN

BACKGROUND/AIMS: This paper is the second of a series describing research and development performed by the SPOTS project towards automating the process of monitoring pigmented lesions for change over time. Several parameters of the system are introduced along with the methods used for determining appropriate settings. We then describe our experimental setup and present a detailed statistical analysis to evaluate system performance. METHODS: There exist three sets of parameters in our system related to image segmentation, classification, and a region-growing step that can be individually tuned. The multiresolution hierarchical segmentation algorithm contains both a set of weights for the tristimulus color values used in calculating color differences and a contrast threshold used to identify root nodes that represent image segments. These were tuned using a synthetic image to simulate a pigmented lesion with irregular border and by estimating the parameters by successive approximations. The neural network classification used to detect lesion segments was trained using a 10-fold cross-validation, and the output classification threshold was set to yield a small false negatives ratio. Finally, there is a growing threshold used to determine whether neighbor regions should be merged in the region-growing step that was selected to minimize the change in area for different translations of a synthetic lesion. In order to evaluate the performance of the system, we compared the identified lesions with manually localized lesions. Ten images of the same area were taken from two subjects presenting lesions of varying size and different background skin texture. A sample of two images from the set was used to simulate variations in acquisition. Five operators were asked to trace lesion boundaries in two passes, separated by a few days, to evaluate the consistency of operators among themselves. The system was then run on the images using the optimal set of parameters. The results were analyzed for independent observation, matched pass, and doubly-matched pass data. CONCLUSIONS: Independent observation data indicates that the system finds significantly more objects than any of the human operators, but the areas reported are not significantly different on average. Matched pass data show that the correlations of the system with human operators is quite high. The system agrees with humans only slightly less than they do among themselves and has a tendency to report slightly smaller areas. The correlation between system and human peformance was further reinforced by the doubly-matched arrangement. These results indicate that our system is as reliable and consistent as our human reference, yielding similar performance.

Asunto(s)

RESUMEN

An on-line information service, the Telemedicine Information Exchange (TIE), was established to provide a comprehensive source of telemedicine information. The TIE comprised a number of frequently updated, searchable, linked databases, each dealing with an important aspect of telemedicine. These included an extensive bibliography on telemedicine consisting of more than 2000 citations, many with abstracts. There was also a series of topical sections describing current telemedicine projects, products and services, legislation, funding, research activities, and news in the field. The TIE was designed to exploit the features of electronic information storage: hypertext linking between related pieces of information; specialized views (technical, legal, and business) of the bibliographic database; and usage monitoring to determine which data were most frequently accessed and therefore where any enhancement should be done. The TIE was made available via the World Wide Web, by remote telnet access over the Internet, and via modern. The rapid increase in the usage of the TIE since its introduction in April 1995 indicated that the TIE satisfied a need in the telemedicine community.

Asunto(s)

Asunto(s)

RESUMEN

Evaluating telemedicine systems and services is a complex task. Safety and efficacy must be measured in a relatively controlled laboratory environment, while measurement of clinical utility and medical effectiveness requires extensive field testing. The need for large clinical trials to demonstrate utility and effectiveness presents a dilemma. Substantial numbers of cases are needed to achieve statistically valid results, yet most telemedicine programs are based in rural settings with small patient populations. One potential solution is to pool data from multiple programs by using common data collection instruments and protocols. A promising model for the performance of multi-centered collaborative telemedicine research is described. The Clinical Telemedicine Cooperative Group (CTCG) is based on the successful use of collaborative research by clinical oncology research groups such as the Southwest Oncology Group (SWOG).

Asunto(s)

RESUMEN

BACKGROUND AND DESIGN: Electronic medical imaging is important for medical informatics, computerized learning, and especially for the growing field of telemedicine. The image resolution necessary for a clinical application can be determined by use of receiver operating characteristic (ROC) experiments. Completely profiling display systems is a tedious process, requiring multiple ROC experiments. We have developed a multiple-choice ROC analysis technique to compare the relative informativeness of digital image formats for a spectrum of cutaneous lesions simultaneously. The technique makes use of logical competitor sets (LCSs) of clinical conditions to redefine multiple-choice responses into the present/absent framework required for conventional ROC curve construction. The study divided 180 slides and digital images into three LCSs: pigmented lesions, flesh-colored papules, and papulosquamous conditions. Eight dermatologists diagnosed the lesions presented in two randomized viewing sessions. Accuracy profiles, independent of individual observer sensitivities, were derived from the responses. RESULTS: The informativeness of color slides and digital images was statistically similar, even when the conditions were stratified by difficulty of diagnosis. Results for nine specific skin conditions represented in the three LCSs were obtained simultaneously. CONCLUSIONS: Digital images appear to be as informative as slides for specific dermatologic diagnoses in the three LCSs tested. The use of LCSs allows stratification of results by diagnosis with greater efficiency than multiple repeated ROC experiments. Multiple-choice ROC analysis used in conjunction with logical competitor sets is the best currently available method for comparing imaging media for use in visual disciplines such as dermatology, radiology, pathology, and others.

Asunto(s)

Asunto(s)

RESUMEN

Telemedicine can be defined as the use of telecommunications technologies to provide medical information and services. This field has recently begun a period of explosive growth. Oregon's teledermatology program within the National Library of Medicine's high-performance computing and communications initiative is designed to generate much-needed basic and clinical research information about one specific telemedicine application. The background of this program is discussed, and the research objectives are described.

Asunto(s)

RESUMEN

BACKGROUND/AIMS: This paper is the first of a series describing research and development performed by the SPOTS project towards automating the process of monitoring pigmented lesions for change over time. A comprehensive overview of digital image processing techniques used for the systematic approach to segmentation of large-area skin images, including the description and classification of skin features, is presented. METHODS: The multiresolution hierarchical segmentation technique, which makes use of image pyramid data structures and cooperative computation with unforced linking, was used to group pixels with similar color properties. This technique was further enhanced to enforce contiguity of segments by determining connected components. The resulting segmentation was then classified by using representative properties of pyramid nodes as input to a cascade of multilayer perceptron neural networks trained using the classical backpropagation algorithm. In order to make our system more resistant to imaging distortions, a technique was developed to grow regions based upon the resulting classification. CONCLUSIONS: This system produces a segmentation at multiple resolutions based upon color, where each segment is a contiguous group of pixels on the image. The classification makes use of both spatial and color properties, as well as parent-child relationships within the pyramid. The addition of classification-driven region growing reduces the change in lesion area where the boundary fades into surrounding skin. Furthermore, the system contains parameters that can be tuned to provide desirable results.

RESUMEN

Computerized comparison of serial skin images is a potentially valuable tool for melanoma screening. In automating this process, matching or "registering" each lesion in a pair of images plays an important role in looking for clinically significant change. We have investigated three practical techniques--a point pattern correlation, a 2-point geometrical transformation, and a 3-point geometrical transformation--for their effectiveness in matching and identifying lesions in pairs of skin images. These techniques view the spots in each image as a point pattern to be matched from image to image. Each of these methods is shown to be quite effective as long as one or more known initial match points can be provided. Experiments performed by imaging actual patients under realistic conditions indicate that the 3-point transformation algorithm performs the best overall, achieving an average matching accuracy of 97%. The nature of these algorithms, their relative performance under a range of conditions, and possible methods for improving accuracies are discussed.

Asunto(s)

RESUMEN

Computerized matching of skin images has been suggested as a means of screening for changes indicative of malignant melanoma. Matching or "registering" each lesion in a pair of images plays an important role in this process. Point-pattern matching algorithms based upon correlation or geometric transformations of the image pairs have been shown to be effective for this registration but require knowledge of one or more "initial match" points which are known to be the same on both images. A method is described for automatically finding these initial match points with a high degree of success. Our algorithm uses the so-called "Gabriel graph" representation of the paired images to select sets of probable matching points. Performance of the algorithm has been measured in realistic trials, using images of patients with large numbers of pigmented lesions. Results show that the single best match chosen is correct greater than 99% of the time, while over 93% of the first three consecutive matches will be chosen correctly. It is likely that these results can be improved through the use of additional nonpositional information or additional image processing.

Asunto(s)

RESUMEN

BACKGROUND AND DESIGN: The diagnosis of skin lesions is a three-part process of (1) screening for abnormalities, (2) examining lesions closely for the presence of important clinical characteristics, and (3) choosing a diagnosis based on the clinical data gathered. The first step, screening for abnormal areas, is of particular interest for anyone wishing to understand and automate the diagnostic process. As part of ongoing research into lesion detection and measurement, we examined the reproducibility and reliability of dermatologists who were asked to screen sets of cutaneous digital images and high-resolution photographs for the presence of skin lesions. RESULTS: The intraobserver and interobserver variation in this task was considerable. The average reproducibilities and reliabilities were approximately 85%. The photographs did not produce significantly better overall screening results than the moderately low-resolution digital images. CONCLUSIONS: Even highly trained dermatologists appear to differ significantly in their initial interpretations of skin images, both from observer to observer and within observers from session to session. These differences were reflected in all measures of diagnostic sensitivity, reproducibility, and reliability assessed. The magnitude of this variation is relatively insensitive to the means used to measure it, and is not simply due to different individual standards for diagnosis. It is highly unlikely that this variation is attributable to the images themselves, since the overall results were nearly identical for moderately low-resolution digital formats and very high-resolution photographs. These findings have important implications for determining where errors may take place in dermatologic screening and for automating the process of detecting changes in skin lesions over time.

Asunto(s)

RESUMEN

The digital imaging revolution that swept other medical specialties in the late 1970s and early 1980s is beginning to find new and important roles in dermatology. This technology has a wide range of educational, clinical, and research applications. Dermatologists should understand certain basic concepts about images and imaging techniques to take advantage of progress in this field and eventually apply it to their own research and/or clinical practice.

Asunto(s)

RESUMEN

This paper presents a new approach to the detection of cutaneous features such as pigmented moles, pores and hair in digital images. We show that by considering the digitized image to be a 3-D terrain with brightness being height, common skin features appear as 'pits' in the terrain. Pits contain a great deal of information about local features in a form that can be easily extracted and analyzed. Pigmented lesions of clinical interest typically have pit characteristics which can be used to separate them from other features. We show empirically that, by creating a statistical database, on the average over 99% of pits can be classified correctly after only a few training images are established for a subject. When attempting to detect pigmented lesions, mean sensitivity ranges from 78% to 98%, depending on imaging conditions and the classification algorithm used. Using image compression, the speed of this screening technique is shown to be increased by a factor of 4 without loss of sensitivity.

Asunto(s)

RESUMEN

Fourteen cases of primary lupus-associated protein-losing enteropathy have now been reported in the English-language literature. These cases were reviewed to find any consistent pattern of presentation. Lupus-associated protein-losing enteropathy typically occurs in young women, and is characterized by the onset of profound edema and hypoalbuminemia. In many cases it is the first obvious manifestations of systemic lupus erythematosus. Diarrhea is present about 50% of the time, but steatorrhea is absent. Diagnosis of protein-losing enteropathy can be successfully made by radioisotopic studies or 24-hour stool alpha 1-antitrypsin clearance. A normal lymphocyte count, elevated serum cholesterol, and absence of lymphangiectasia on intestinal biopsy help distinguish lupus-associated protein-losing enteropathy from protein-losing enteropathies due to direct or indirect lymphatic obstruction. Normal endoscopy and mucosal biopsy can rule out protein loss due to mucosal disruption. Prognosis appears to be excellent with corticosteroids, although other immunosuppressive therapies have been successfully used. A typical and illustrative case is presented as a focal point for review and discussion.

Asunto(s)

RESUMEN

Intralesional interferon alfa-2b has been proven effective in the treatment of basal cell carcinomas. Because nine injections over a 3-week period have been necessary to produce clinically significant cure rates, a sustained-release protamine zinc chelate interferon formulation has been developed. In this study, 65 basal cell carcinomas were treated in one of two dosing schedules with intralesional sustained release interferon alfa-2b (10 million IU per injection). Thirty-three patients received a single injection and 32 patients received one injection per week for 3 weeks. At study week 16, 80% of evaluable tumors treated with three injections and 52% treated with one injection were cured histologically. Two patients discontinued injections because of side effects. A sustained-release protamine zinc preparation of interferon alfa-2b shows promise as a practical, effective, and cosmetically elegant treatment for basal cell carcinoma.

Asunto(s)

RESUMEN

Digital imaging could potentially provide a rapid, objective, and quantitative means of detecting changes in important skin conditions, especially the dysplasic nevus syndrome. Image analysis techniques can be applied to digital images to automate the search for changes in moles or other features. Consistent determination of lesion boundaries, perimeter, and area in digital images is a vital first step in this process. In this paper, we show how bilaterally symmetric Laplacian-of-a-Gaussian filters can be used to recover the borders of selected lesions while remaining robust with respect to factors such as the camera point spread function and additive noise. Tests on real and synthetic images demonstrate that lesion borders, area, and perimeter can be obtained with a high degree of reliability. Boundaries are routinely found to within +/- 0.2 pixels, and area and perimeter measurements vary by less than 10% when imaging spot targets and actual cutaneous lesions under a realistic range of experimental conditions.

Asunto(s)