PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Digital network”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 613 records · Page 34Linked to original sources
PubMed2006

[Computer-based health care research in the competence network inflammatory bowel disease. Handling of bowel diseases in general practice].

BACKGROUND: Consultations due to most different bowel diseases and abdominal symptoms are common in primary care. However, little is known about the concrete situation in the general practitioner's office so far. In this study, practitioners involved in the actual treatment of patients with bowel diseases document their medical strategies by the use of an internet-based data entry system. Hence, with the support of an internet-based data collection tool, health care research has started to break new ground. METHODS: Following the programming of a digital data collection system and the installation of a nationwide research network of general practitioners interested in this matter, participating physicians communicated anonymised data on medical care of patients with various abdominal problems and intestinal/bowel diseases to the principal study investigators for 12 months, thereby using a computer-based data entry system (via internet). RESULTS: Within the 12 months of observation, 94 general practitioners documented 1,584 patient contacts by using the new data collection system. Accordingly, the most frequent reasons for consultation were abdominal pain (39%) and a change in stool habits (28%), each over a period of > 21 days. Women reported abdominal pain more often than men. Furthermore, the willingness to cooperate with specialists (hospitalization, referrals) was high among participating physicians, in reference to abdominal problems, thereby not demonstrating gender specificity. In the majority of cases, computer-assisted data entry took place outside regular consultation hours, and physicians frequently documented more than one patient within one session. CONCLUSION: High numbers of hospitalizations and specialist referrals, as shown in this study, points toward a high intensity of medical attendance necessary for patients with unspecific symptoms of the bowel or related abdominal problems. Computer-assisted data entry systems, however, represent a challenging yet still realizable way of data collection. This procedure should be brought forward for future projects in health care research.

Adult↗
PubMed1995

1995 Joseph E. Whitley, MD, Award. A World Wide Web gateway to the radiologic learning file.

RATIONALE AND OBJECTIVES: Computer networks in general, and the Internet specifically, are changing the way information is manipulated in the world at large and in radiology. The goal of this project was to develop a computer system in which images from the Radiologic Learning File, available previously only via a single-user laser disc, are made available over a generic, high-availability computer network to many potential users simultaneously. METHODS: Using a networked workstation in our laboratory and freely available distributed hypertext software, we established a World Wide Web (WWW) information server for radiology. Images from the Radiologic Learning File are requested through the WWW client software, digitized from a single laser disc containing the entire teaching file and then transmitted over the network to the client. The text accompanying each image is incorporated into the transmitted document. RESULTS: The Radiologic Learning File is now on-line, and requests to view the cases result in the delivery of the text and images. Image digitization via a frame grabber takes 1/30th of a second. Conversion of the image to a standard computer graphic format takes 45-60 sec. Text and image transmission speed on a local area network varies between 200 and 400 kilobytes (KB) per second depending on the network load. CONCLUSION: We have made images from a laser disc of the Radiologic Learning File available through an Internet-based hypertext server. The images previously available through a single-user system located in a remote section of our department are now ubiquitously available throughout our department via the department's computer network. We have thus converted a single-user, limited functionality system into a multiuser, widely available resource.

CD-ROM↗
PubMed2003

An introduction to bio-inspired artificial neural network architectures.

In this introduction to artificial neural networks we attempt to give an overview of the most important types of neural networks employed in engineering and explain shortly how they operate and also how they relate to biological neural networks. The focus will mainly be on bio-inspired artificial neural network architectures and specifically to neo-perceptions. The latter belong to the family of convolutional neural networks. Their topology is somewhat similar to the one of the human visual cortex and they are based on receptive fields that allow, in combination with sub-sampling layers, for an improved robustness with regard to local spatial distortions. We demonstrate the application of artificial neural networks to face analysis--a domain we human beings are particularly good at, yet which poses great difficulties for digital computers running deterministic software programs.

Animals↗
PubMed1999

Feature selection for computerized mass detection in digitized mammograms by using a genetic algorithm.

RATIONALE AND OBJECTIVES: To investigate optimization of feature selection for computerized mass detection in digitized mammograms, and to compare the effectiveness of a genetic algorithm (GA) in such optimization with that of an "exhaustive" search of all feature permutations. MATERIALS AND METHODS: A Bayesian belief network (BBN) was used to classify positive and negative regions for masses depicted in digitized mammograms; 20 features were computed for each of 592 positive and 3,790 negative regions in two databases. Conditional probabilities for the BBN were computed by using a "training" database of 288 positive and 2,204 negative regions. Performance was measured by the area under the receiver operating characteristic curve (A) by using the remainder database (304 positive and 1,586 negative regions). The optimal set was first found by using an "exhaustive" (complete permutation) searching method. A GA-based search for the optimal set then was applied, and the results of the two approaches were compared. RESULTS: As the number of features in the classifier increased, the A value increased until it reached a maximum performance for 11 features of 0.876 +/- 0.008. The A value then decreased monotonically as the number of features increased from 11 to 20. Using 100 random chromosomes (seeds) in the first generation, the GA identified the same optimal set of features but reduced the total computation time by a factor of 65. CONCLUSION: A GA-based search might be an efficient and effective approach to selecting an optimal feature set.

Algorithms↗
PubMedDate not supplied

Influence of the teleradiology technology (N-ISDN and ATM) on the inter-hospital management of neurosurgical patients.

We set out to assess the influence of a teleradiology network on the relations between a general hospital and a 100 km distant university hospital in the context of neurosurgical emergencies, and compared a commercially available technology, N-ISDN (Narrowband Integrated Service/Digital Network), to an emerging technology, ATM (Asynchronous Transfer Mode). The evaluation was conducted using records of advice request calls and patient transfers. Three phases were considered: without teleradiology, with transfer of digitized images over N-ISDN at 64 kbps, and with an experimental ATM network at 10.5 Mbps with DICOM image transfers and videoconferencing. Additionally, staff meetings over ATM videoconferencing were set up. To assess the ATM service, we used log files and questionnaires, 108 advice requests were studied over a 18 month period. The average transmission time for one examination was 38 s with full DICOM image resolution over ATM, versus 150 s with 10:1 JPEG (Joint Photographic Expert Group) compression over N-ISDN. Up to 50% unnecessary patient transfers were avoided. Advice requests increased fourfold, and non-urgent advice requests increased from 0 to 21%. Despite the experimental configuration of the ATM network, the service gave satisfaction to all the physicians. Videoconferencing was unanimously regarded as a prominent tool to improve the quality of interaction. It was particularly useful for non-urgent cases and distant staff meetings. Teleradiology can improve the relations between hospitals through an increase of urgent and non-urgent advice requests. Asynchronous transfer mode is an efficient way for fast transfer of radiological examinations in DICOM format and for discussing them through high-quality videoconferencing.

Brain Neoplasms↗
PubMed2004

A portable digital microphotography unit for rapid documentation of periungual nailfold capillary changes in autoimmune connective tissue diseases.

OBJECTIVE: While employing a DermLite dermoscopy unit to assess pigment pattern networks in melanocytic skin lesions, it was observed that this compact, portable dermoscopy unit can also be used to quickly detect nailfold capillary changes when entertaining a diagnosis of autoimmune connective tissue diseases (CTD) such as dermatomyositis (DM), scleroderma/systemic sclerosis (SSc), or systemic lupus erythematosus. Aware that the suppliers of the DermLite dermoscopy unit also market a portable digital microphotography unit based on the DermLite optical principles for efficiently documenting cutaneous pigment network patterns, we investigated whether this unit (DermLite Foto flash unit attached to a Nikon Coolpix digital camera) might be used to photographically document nailfold capillary changes in patients with autoimmune CTD. METHODS: A DermLite Foto flash unit attached to a Nikon Coolpix digital camera was used in a controlled observational study to obtain digital photographs of nailfold capillaries in a small sequential sample of patients with autoimmune CTD attending a rheumatic skin disease subspecialty clinic in an academic department of dermatology. RESULTS: The digital microphotography system proved to be highly useful in documenting the nailfold vascular changes observed in a small sample of patients with DM. We observed that the nailfold capillary changes seen in patients with clinically amyopathic DM were qualitatively and quantitatively similar to those seen in patients with classical DM. CONCLUSION: Digital microphotography systems designed for examining pigmented skin lesions can be used easily to document nailfold capillary changes often observed in DM and SSc. Nailfold capillary changes documented in this manner appear to be indistinguishable in clinically amyopathic DM and classical DM.

Autoimmune Diseases↗
PubMed1989

A multimedia medical communication link between a radiology department and an emergency department.

The most critical aspect of a radiologist's work is communicating his findings to the attending physician responsible for the patient's care. This is also the part of the process that is least well organized and the most subject to failure. At the University of Ottawa Medical Communications Research Centre we are investigating technical means to improving communications between radiologists and attending physicians. We first introduce the radiology communication service problem and show why it is essentially a multimedia communication problem. We then briefly describe a multimedia communication system designed and implemented by our research team. The multimedia system consists of several work stations linked by the Hospital's local area network (LAN). Each physician work station comprises a Compaq 386/20-Mhz microcomputer with 16 Mbytes of RAM, a 500-Mbyte image disk, and an image memory that drives a 1,000-line monochrome monitor. The images are digitized using a Konica laser-based film digitizer (2430 by 2000 10-bit pixels for a standard chest radiograph). The multimedia file server manager station is built around a PC-AT compatible with a Northern Telecom Meridian SL-1ST digital PBX and a Meridian Mail digital voice messaging system. This last device is used to store voice data and is linked via the PBX to the workstations' digital telephones. A Sytek 6,000 LAN links all work stations to the file server. All data, image, and graphic information is transmitted via this network, while the twisted pair connections linking the digital PBX to the telephone sets are used for transmitting voice data.(ABSTRACT TRUNCATED AT 250 WORDS)

Computer Communication Networks↗
PubMed1997

Classification of handwritten digits using a RAM neural net architecture.

Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.

Classification↗
PubMed2004

[Digital echocardiography laboratory].

The implementation of a digital echocardiography laboratory exists today using the DICOM (Digital Imaging Communication in Medicine) standard to acquire, store and transfer echocardiographic digital images. The components of a laboratory include: 1) digital echocardiography machines with DICOM output, 2) a switched high-speed local area network, 3) a DICOM server with abundant local storage, and 4) a software to manage image and measurement information. The aim of this article was to describe the critical components of a digital echocardiography laboratory, discuss strategies for implementation, and describe some of the pitfalls that we encountered in our own implementation of the digital third level echocardiography laboratory.

Ambulatory Care Facilities↗
PubMed2002

Automated diagnosis of pigmented skin lesions.

Since advanced melanoma remains practically incurable, early detection is an important step toward a reduction in mortality. High expectations are entertained for a technique known as dermoscopy or epiluminescence light microscopy; however, evaluation of pigmented skin lesions by this method is often extremely complex and subjective. To obviate the problem of qualitative interpretation, methods based on mathematical analysis of pigmented skin lesions, such as digital dermoscopy analysis, have been developed. In the present study, we used a digital dermoscopy analyzer (DBDermo-Mips system) to evaluate a series of 588 excised, clinically atypical, flat pigmented skin lesions (371 benign, 217 malignant). The analyzer evaluated 48 parameters grouped into 4 categories (geometries, colors, textures and islands of color), which were used to train an artificial neural network. To evaluate the diagnostic performance of the neural network and to check it during the training process, we used the error area over the receiver operating characteristic curve. The discriminating power of the digital dermoscopy analyzer plus artificial neural network was compared with histologic diagnosis. A feature selection procedure indicated that as few as 13 of the variables were sufficient to discriminate the 2 groups of lesions, and this also ensured high generalization power. The artificial neural network designed with these variables enabled a diagnostic accuracy of about 94%. In conclusion, the good diagnostic performance and high speed in reading and analyzing lesions (real time) of our method constitute an important step in the direction of automated diagnosis of pigmented skin lesions.

Automation↗
PubMed1994

In vivo liver differentiation by ultrasound using an artificial neural network.

A pattern recognition algorithm and instrumentation for in vivo ultrasound human liver differentiation are presented. An available 16-MHz microprocessor-based data acquisition and analysis system with 6-bit resolution is used to capture, digitize, and store the backscattered ultrasound signal. The algorithm is based on a multilayer perception neural network using the backpropagation training procedure. The network is implemented to differentiate between normal and abnormal liver. Data earlier obtained from 18 volunteers with normal liver history and from 12 volunteers with liver abnormalities are used to test the algorithm. The power spectra of the backscattered signal from depths of 5, 6.5, and 8 cm in the liver are calculated. The acoustic attenuation coefficient is calculated by the log spectral difference technique over the frequency range from 1.5 to 4.5 MHz. The change of speed of sound with frequency (dispersion) is estimated over the 3-MHz bandwidth. The attenuation and velocity dispersion are used as differentiation features. The results show that of the 22 tested cases, the system differentiated correctly 19 and 20 cases when using the attenuation and the velocity dispersion, respectively. The average magnitude of dispersion of liver is estimated to be 1.67 +/- 0.1 m/s/MHz and about 2.3 +/- 0.18 m/s/MHz in the normal and abnormal cases, respectively. The overall performance of the system for liver differentiation is 91% for normal cases, and 86% for abnormal cases. The data files are also differentiated using the nearest neighbor statistical classifier. The results show that of the 30 tested cases, 23 files are differentiated correctly using the attenuation coefficient.

Humans↗
PubMed1991

Retinal microcirculation in patients with diabetes mellitus: dynamic and morphological analysis of perifoveal capillary network.

The new scanning laser technique allows one to quantify the retinal microcirculation. A digital image analysing system was used to study capillary blood flow velocities and morphological parameters of perifoveal intercapillary areas and foveal avascular zones in normal and diabetic subjects. Diabetic patients showed a significant reduction in capillary blood cell velocities in comparison with normal subjects. Perifoveal intercapillary areas and foveal avascular zones were significantly increased in all stages of diabetic retinopathy, and both parameters increased with progressing diabetic retinopathy. Significant changes in the perifoveal intercapillary areas were observed between normal subjects and patients with no retinopathy.

Adult↗
PubMed1996

Application of neural networks to quantitative nondestructive evaluation.

This paper concentrates on the quantitative analysis of reflection and transmission characteristics of structural waves in notched beams using neural networks. At one end of a rod a piezoelectric transducer excites a flexural guided wave, which propagates through the structure and is reflected from the notch as well as from the ends of the rod. At another point, a laser interferometer measures the resulting displacement versus time, which is recorded and serves as the digital fingerprint of the experiment. Our aim is to obtain quantitative information about the notch characteristics, i.e. its location and depth, on the basis of these digital recordings. This requires an inverse problem to be solved using neural networks. For the training of the network, synthetically produced wave patterns are used. The results of the corresponding wave experiment simulations compare well with experimental data. For fixed location, the calculated wave patterns could be quantitatively analysed to yield the depth of the notch if it is greater than a twentieth of the diameter. Another network could be trained for the localization with an accuracy of 2 cm for 93% of the training patterns. On the basis of these results a strategy is formulated on how neural networks could be trained to evaluate quantitatively both of the notch characteristics.

Algorithms↗