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 379 records · Page 21Linked to original sources

PubMed2001

Remote verification in radiotherapy using digitally reconstructed radiography (DRR) and portal images: a pilot study.

PURPOSE: To use digitally reconstructed radiography (DRR) and digitally compressed portal images in distant consultation using a telecommunications network, the verification performance of DRR and digitally compressed portal images on the image console was investigated. METHODS AND MATERIALS: A human thoracic phantom was scanned with computed tomography (CT). Radiotherapy was planned at 5 different anatomic locations. A digitally reconstructed radiograph was made; verification films of the phantom were then taken with 6-MV X-rays. The treatment center was intentionally dislocated. Fifty sets of DRR and portal images were seen by 7 doctors on a conventional view-box (view-box method) to judge whether the treatment center was dislocated. These image sets were digitalized by a film scanner, compressed to 1/10 Joint Photographic Experts Group (JPEG) format, and compared on an image console by the same physicians (image-console method). The verification performance of the image console method was compared with that of the view-box method by means of receiver operating characteristic (ROC) analysis. Clinically, 159 portal-image-sets were verified with the image-console method and the appropriateness of the decision was later assessed by the view-box method. RESULTS: The accuracy of the treatment verification was estimated to be 88.8% by the conventional view-box method and 88.3% by the image-console method. There was no statistically significant difference in the verification performances of the conventional method (Az = 0.86+/-0.02) and the image console method (Az = 0.84+/-0.07). Frequent digital image-processing modification was positively related to the accuracy of verification. Clinically, there were 3 (1.8%) major corrections, 31 (19.5%) minor corrections, and 123 cases with no correction. No further correction was called for by the re-evaluation using the view-box method. CONCLUSION: The verification performance of DRR and digitally compressed portal images on the image console was as accurate as the conventional method. Distant consultation using DRR and portal images through telecommunication is usable in clinical practice.

Humans↗

PubMed2000

Electronic transmission of digital echocardiographic studies: effects of MPEG compression.

The acquisition, storage and retrieval of digital echocardiographic studies greatly facilitates image review and quantitation and permits the transmission of studies electronically. However, the considerable size of digital echocardiographic data files makes transmission over existing networks slow and impractical. Reduction in the size of these data files can be accomplished with digital image compression. We sought to evaluate the effects of MPEG-1 compression on the transfer time of digital echocardiographic studies over currently available network connections. Ninety consecutive routine clinical echocardiographic studies were randomly compressed at one of three compression ratios 60:1, 80:1, or 120:1 and sent to a receiving terminal using simulated transmission rates. Compression of digital echocardiographic studies at these ratios which, have been shown to maintain diagnostic image quality, reduced the size of digital echocardiographic studies to less than 1% of their original sizes which allowed transmission of echocardiographic studies over networks using 3ISDN or T1 lines with minimal waiting time.

Echocardiography↗

PubMed1988

Simulation of patient flow in a picture archival and communications system network.

As hospital radiology departments expand their use of digitally formatted imaging devices, these machines will be connected in local area networks called Picture Archival and Communications Systems (PACS). The purpose of this paper is to demonstrate the use of computer simulation to analyze the process of patients using a PACS. The flexibility of using simulation on a proposed PACS is shown, starting with the description of a basic model. Different machine networks are run and the results compared. Simulation modeling provides a valuable tool to hospital and department administrators in detecting possible problem areas which may occur with proposed PACS configurations under assumed patient loads.

Computer Communication Networks↗

PubMedDate not supplied

Taking digital imaging to the next level: challenges and opportunities.

New medical imaging technology, such as multi-detector computed tomography (CT) scanners and positron emission tomography (PET) scanners, are creating new possibilities for non-invasive diagnosis that are leading providers to invest heavily in these new technologies. The volume of data produced by such technology is so large that it cannot be "read" using traditional film-based methods, and once in digital form, it creates a massive data integration and archiving challenge. Despite the benefits of digital imaging and archiving, there are several key challenges that healthcare organizations should consider in planning, selecting, and implementing the information technology (IT) infrastructure to support digital imaging. Decisions about storage and image distribution are essentially questions of "where" and "how fast." When planning the digital archiving infrastructure, organizations should think about where they want to store and distribute their images. This is similar to decisions that organizations have to make in regard to physical film storage and distribution, except the portability of images is even greater in a digital environment. The principle of "network effects" seems like a simple concept, yet the effect is not always considered when implementing a technology plan. To fully realize the benefits of digital imaging, the radiology department must integrate the archiving solutions throughout the department and, ultimately, with applications across other departments and enterprises. Medical institutions can derive a number of benefits from implementing digital imaging and archiving solutions like PACS. Hospitals and imaging centers can use the transition from film-based imaging as a foundational opportunity to reduce costs, increase competitive advantage, attract talent, and improve service to patients. The key factors in achieving these goals include attention to the means of data storage, distribution and protection.

Costs and Cost Analysis↗

PubMed1993

Automatic lung nodule detection using profile matching and back-propagation neural network techniques.

The potential advantages of using digital techniques instead of film-based radiography have been discussed extensively for the past 10 years. A major future application of digital techniques is computer-assisted diagnosis: the use of computer techniques to assist the radiologist in the diagnostic process. One aspect of this assistance is computer-assisted detection. The detection of small lung nodule has been recognized as a clinically difficult task for many years. Most of the literature has indicated that the rate for finding lung nodules (size range from 3 mm to 15 mm) is only approximately 65%, in those cases in which the undetected nodules could be found retrospectively. In recent published research, image processing techniques, such as thresholding and morphological analysis, have been used to enhance true-positive detection. However, these methods still produce many false-positive detections. We have been investigating the use of neural networks to distinguish true-positives nodule detections among those areas of interest that are generated from a signal enhanced image. The initial results show that the trained neural networks program can increase true-positive detections and moderately reduce the number of false-positive detections. The program reported here can perform three modes of lung nodule detection: thresholding, profile matching analysis, and neural network. This program is fully automatic and has been implemented in a DEC 5000/200 (Digital Equipment Corp, Maynard, MA) workstation. The total processing time for all three methods is less than 35 seconds. In this report, key image processing techniques and neural network for the lung nodule detection are described and the results of this initial study are reported.

Algorithms↗

PubMed1995

[Trial of a small image network system in a radiology department of an university hospital].

This paper describes the construction of an image network system in Shinshu University Hospital, and some of its current issues and advantages. Our discussion is based on our experience with a PACS system. SAIPACS, which was installed in 1990 for use in clinical conferencing and pre- and post-graduate education, and with a new CT and MRI network, which was subsequently introduced in 1993. The SAIPACS interconnects eight digital imaging modalities, including CT, MRI, XTV-DR (including digital tomosynthesis), FCR, nuclear medicine (RI), DSA, US, and a film digitizer (FD), with a workstation. Transmission time from the magnetic disk of each imaging modality to the SAIPACS image disk is not rapid enough. Therefore, we need to select images for transfer that are pertinent to our specific purpose, to complete image transmission within a practically acceptable period of time. The new CT/MRI network is composed of two CT units, two MRI systems, an image processing unit and a Universal Gateway. It provides faster image transmission than the SAIPACS system, because there is no need to reform image data to send them in a reversible compressed form. A versatile network system connected to the SAIPACS and CT/MRI network enables digital image data to be processed and edited and images to be transferred back to SAIPACS for clinical or educational use.

Computer Communication Networks↗

PubMed2003

Distributed sensor networks: a cellular nonlinear network perspective.

Large-scale networks of integrated wireless sensors become increasingly tractable. Advances in hardware technology and engineering design have led to dramatic reductions in size, power consumption, and cost for digital circuitry, and wireless communications. Networking, self-organization, and distributed operation are crucial ingredients to harness the sensing, computing, and computational capabilities of the nodes into a complete system. This article shows that those networks can be considered as cellular nonlinear networks (CNNs), and that their analysis and design may greatly benefit from the rich theoretical results available for CNNs.

Microcomputers↗

PubMed2003

Communicable disease case entry using PDAs and public wireless networks.

Concerns about detecting and responding to attacks with biowarfare agents have resulted in the development of deployable case reporting systems, e.g. RSVP. We implement a proof of concept web-based information system to be used securely from personal digital assistants over public wireless networks, by public health field workers for routine and emergent case reporting. The system collects data for a local health jurisdiction, provides content- and event-based notification, and forwards case reports to the Colorado State communicable disease reporting system (CEDRS). We believe this demonstrates a useful integration of portable and web-based technologies with public health practice.

Colorado↗

PubMed1988

[Venous drainage of Littler's neurovascular pedicle flap].

The antegrade transosseous injection of the digital veins, followed by dissection enables the authors to analyse the role of various networks in drainage of the pulp. The satellite veins of the digital artery in the finger are probably not involved. The venous return of the pulp is constituted by an anatomical continuity between the superficial palmar network and the common digital veins. A narrow anastomotic channel is demonstrated in the commissure between these two systems.

Coloring Agents↗

PubMed2000

Classification of rat behavior with an image-processing method and a neural network.

Video recordings of 11 rats were digitized at five frames per second, and parameters describing the shape and the position of the rat were calculated. The behavior displayed by the rats was observed by an experienced observer. Separate neural networks were trained and validated, using the data for each individual rat. The neural networks correctly classified an average of 76.53% of the frames in the validation set and 98.18% of the frames in the training set. A single neural network was trained with 6 rats and validated with 5 rats. The neural network correctly classified 63.74% of the frames in the validation set and 82.85% of the frames in the training set.

Animals↗

PubMed2000

Transition to an all-digital echocardiography laboratory: a large, multi-site private cardiology practice experience.

Acquisition, interpretation, and storage of digital echocardiographic images has many advantages over the standard videotape-based method. Archival, transmission, and comparative interpretation are all optimized with digital echocardiography. A study performed at one site can be immediately available for viewing and analysis at another site by means of standard data transfer technology. Echocardiograms can be interpreted in the context of prior studies, which are readily available for side-by-side comparison. The transition to an all-digital laboratory involves the commitment of persons at multiple levels in the cardiology practice, including administrators, information technology specialists, sonographers, and physicians. Quality of patient care, use of physicians' and sonographers' time, and long-term financial benefit are all areas where improvement may be realized with the use of digital echocardiography. We present our experience in the development of an all-digital echocardiography laboratory, and we conclude that digital echo-cardiography is practical and can be implemented readily in a clinical setting. We performed several correlative analyses during this transition to validate the consistency and accuracy of digital interpretation compared with those of analog methods. The transition process from analog (videotape) to digital, including full wide area network exchange, took approximately 8 months. As technology advances, issues surrounding storage, comparison, and acquisition formats will continue to develop. We hope that our experience will help others make the transition to the digital environment and benefit from the ease of image access, the ability to comparatively interpret echocardiograms, and the superior image quality afforded by this advancement.

Attitude of Health Personnel↗

PubMed1990

The reconstruction of individual spike trains from extracellular multineuron recordings using a neural network emulation program.

A method for the reconstruction of the individual spike trains from extracellular multineuron recordings is described. A neural network emulation program is trained to recognize a sample set of digitized spikes. The digitized spikes are fed into the neural network, and the network output is used to classify spikes in terms of the training set. The system runs on any PC and its speed makes is especially well suited for the analysis of large amounts of data.

Action Potentials↗

PubMed1994

Differentiation of beats of ventricular and sinus origin using a self-training neural network.

Despite advances in the computerized detection of arrhythmias, arrhythmia recognition by morphological waveform analysis still poses a difficult problem. Artificial neural networks, computer algorithms that are self-trained by an analog of biological synaptic modification to perform pattern recognition, hold great promise for the differentiation of various cardiac rhythms. The goal of this study was to differentiate beats of sinus and ventricular origin on a global basis and on a patient-specific basis by the use of artificial neural network analysis. Neural networks were trained to recognize digitized intracardiac electrograms (9 patients) and surface electrocardiograms (11 patients) obtained during sinus rhythm and ventricular tachycardia. After training, sinus rhythm or ventricular tachycardia beats were input into the neural network, and classified as to their origin. By the use of modified receiver operating characteristic curve plots, it was possible to differentiate with high sensitivity and specificity between beats of sinus origin and ventricular origin in all patients. The addition of high amounts of noise to the beats did not markedly degrade the performance of the surface ECG neural networks, and still allowed high sensitivity in differentiating beats of sinus origin from beats of ventricular origin, especially when noise was added to the training set. Neural networks provided sensitive and specific detection of cardiac electrical activity during sinus rhythm and ventricular tachycardia, and may play an important role in allowing development of improved arrhythmia recognition and management systems.

Aged↗

PubMed2000

An experimental teleradiology transmission system using a high-speed ATM backbone network.

We evaluated the performance of an experimental teleradiology system based on a high-speed ATM backbone network. Image acquisition, transmission and the disk-to-display processing times were measured. Computerized tomography (CT) scans printed on 14 inch x 17 inch (36 cm x 43 cm) films were digitized and transferred over the network. The average time for the entire process was 1 min 30 s. Three radiologists interpreted 20 cases. For CT image interpretation, the reading time for one case ranged from 2 to 12 min (mean 6 min 46 s) on a monitor, and from 1 to 3 min (mean 1 min 31 s) with the original film. The ATM backbone network operating at 156 Mbit/s provided sufficient speed for remote consultation. However, further improvements in the operability of the system, especially the image viewing station, are necessary before it will be satisfactory for clinical use.

Computer Systems↗

PubMed1999

Artificial neural network-aided image analysis system for cell counting.

BACKGROUND: In histological preparations containing debris and synthetic materials, it is difficult to automate cell counting using standard image analysis tools, i.e., systems that rely on boundary contours, histogram thresholding, etc. In an attempt to mimic manual cell recognition, an automated cell counter was constructed using a combination of artificial intelligence and standard image analysis methods. METHODS: Artificial neural network (ANN) methods were applied on digitized microscopy fields without pre-ANN feature extraction. A three-layer feed-forward network with extensive weight sharing in the first hidden layer was employed and trained on 1,830 examples using the error back-propagation algorithm on a Power Macintosh 7300/180 desktop computer. The optimal number of hidden neurons was determined and the trained system was validated by comparison with blinded human counts. System performance at 50x and lO0x magnification was evaluated. RESULTS: The correlation index at 100x magnification neared person-to-person variability, while 50x magnification was not useful. The system was approximately six times faster than an experienced human. CONCLUSIONS: ANN-based automated cell counting in noisy histological preparations is feasible. Consistent histology and computer power are crucial for system performance. The system provides several benefits, such as speed of analysis and consistency, and frees up personnel for other tasks.

Cell Count↗

PubMed2005

Error concealment for shape in MPEG-4 object-based video coding.

In asynchronus transfer mode networks, cell loss or channel errors can cause data to be dropped in the channel. When digital images/videos are transmitted over these networks, one must be able to reconstruct the missing data so that the impact of the errors is minimized. In this paper, we present an error-concealment technique for shape in MPEG-4 object-based video coding. This method, which is based on using global motion estimation and compensation techniques for boundary recovery, consists of three steps: (1) boundary extraction from shape; (2) boundary patching using global motion compensation; and (3) boundary filling to reconstruct the shape of the damaged video object planes. Global motion parameters are inserted as part of the USER_DATA field in the compressed stream and are utilized in reconstructing the damaged boundaries of compressed video object planes.

Algorithms↗

PubMed1994

Classification of action potentials in multi-unit intrafascicular recordings using neural network pattern-recognition techniques.

Neural network pattern-recognition techniques were applied to the problem of identifying the sources of action potentials in multi-unit neural recordings made from intrafascicular electrodes implanted in cats. The network was a three-layer connectionist machine that used digitized action potentials as input. On average, the network was able to reliably separate 6 or 7 units per recording. As the number of units present in the recording increased beyond this limit, the number separable by the network remained roughly constant. The results demonstrate the utility of neural networks for classifying neural activity in multi-unit recordings.

Action Potentials↗

PubMed2005

Precision constrained stochastic resonance in a feedforward neural network.

Stochastic resonance (SR) is a phenomenon in which the response of a nonlinear system to a subthreshold information-bearing signal is optimized by the presence of noise. By considering a nonlinear system (network of leaky integrate-and-fire (LIF) neurons) that captures the functional dynamics of neuronal firing, we demonstrate that sensory neurons could, in principle harness SR to optimize the detection and transmission of weak stimuli. We have previously characterized this effect by use of signal-to-noise ratio (SNR). Here in addition to SNR, we apply an entropy-based measure (Fisher information) and compare the two measures of quantifying SR. We also discuss the performance of these two SR measures in a full precision floating point model simulated in Java and in a precision limited integer model simulated on a field programmable gate array (FPGA). We report in this study that stochastic resonance which is mainly associated with floating point implementations is possible in both a single LIF neuron and a network of LIF neurons implemented on lower resolution integer based digital hardware. We also report that such a network can improve the SNR and Fisher information of the output over a single LIF neuron.

Action Potentials↗