Judging a digital imaging system.
Explore the source record for details and available documents.
Computer Peripherals↗
SEARCH · Search PubMed
Results for “Software Validation”
Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Bi-directional computing architecture for time series prediction.
A number of neural network models and training procedures for time series prediction have been proposed in the technical literature. These models studied for different time-variant data sets have typically used uni-directional computation flow or its modifications. In this study, on the contrary, the concept of bi-directional computational style is proposed and applied to prediction tasks. A bi-directional neural network model consists of two subnetworks performing two types of signal transformations bi-directionally. The networks also receive complementary signals from each other through mutual connections. The model not only deals with the conventional future prediction task, but also with the past prediction, an additional task from the viewpoint of the conventional approach. An improvement of the performance is achieved through making use of the future-past information integration. Since the coupling effects help the proposed model improve its performance, it is found that the prediction score is better than with the traditional uni-directional method. The bi-directional predicting architecture has been found to perform better than the conventional one when tested with standard benchmark sunspots data.
Data Interpretation, Statistical↗
Automated three-dimensional quantification of myocardial perfusion and brain SPECT.
To allow automated and objective reading of nuclear medicine tomography, we have developed a set of tools for clinical analysis of myocardial perfusion tomography (PERFIT) and Brain SPECT/PET (BRASS). We exploit algorithms for image registration and use three-dimensional (3D) "normal models" for individual patient comparisons to composite datasets on a "voxel-by-voxel basis" in order to automatically determine the statistically significant abnormalities. A multistage, 3D iterative inter-subject registration of patient images to normal templates is applied, including automated masking of the external activity before final fit. In separate projects, the software has been applied to the analysis of myocardial perfusion SPECT, as well as brain SPECT and PET data. Automatic reading was consistent with visual analysis; it can be applied to the whole spectrum of clinical images, and aid physicians in the daily interpretation of tomographic nuclear medicine images.
Algorithms↗
Workflow in nuclear medicine.
This paper discusses a workflow management system for nuclear medicine. It augments the more conventional PACS with automatic transfer of studies along the chain of activities making up an examination in nuclear medicine. A prototype system has been designed, built, and installed in a department of nuclear medicine, active in a network of hospitals.
Belgium↗
European Medical Device Directive: impact on nuclear medicine.
The European Council Directive 93/42/EEC concerning medical devices (14 June 1993) assigns new responsibilities and imposes technical requirements both to the manufacturer and user of medical devices. In this paper the general outlines of the directive are discussed with a particular emphasis on the risk classification of products, the compliance and evaluation process and the CE-marking regulations. Furthermore, some practical implications are highlighted for devices and tools relevant to the field of nuclear medicine such as radiation detectors, gamma- and PET-cameras and software.
Absorptiometry, Photon↗
Testing the precision of stereotactic planning systems.
The implementation of effective methods of testing the precision of computations, is essential for the development of medical systems, such as the stereotactic planning software for neurosurgery. During the development of our planning system we designed, in addition to the traditional phantom test, some tests based on digitally constructed images. These tests give quantitative and qualitative measurement of the precision and stability of the calculations, and are easy to implement and isolate the program error from the mechanical and image acquisition errors. The verification of our software shows good precision in coordinates calculation and a significant impact of pixel size and interscan spacing on the precision.
Brain↗
Verification of temporal scheduling constraints in clinical practice guidelines.
The computerization of clinical practice guidelines is a significant scientific challenge for the medical informatics community. One frequently reported factor hindering this objective is the existence of deficiencies within guideline knowledge. In this paper, we focus on the detection of flaws within temporal scheduling constraints. Temporal scheduling constraints are important elements of therapy management, and are frequently incorporated in clinical practice guidelines. We present a suitable verification method that is based on calculating the minimal network of temporal constraints on the execution of guideline activities. Our method serves three purposes: (1) it checks whether temporal scheduling constraints are consistent with scheduling constraints implied by control flow operators and the hierarchical structuring of a guideline; (2) it yields suggestions for an equivalent, yet more explicit representation of non-minimal constraints; (3) it can be used by the guideline interpreter to assemble feasible time intervals for the execution of each guideline activity. We evaluate our approach by applying it to a guideline specified in the Asbru language. For this purpose, we implemented a prototype verifier. Although we concentrate on the guideline representation language Asbru as the demonstration medium of our method within this paper, our approach can be reused to verify several alternative guideline representation formats.
Humans↗
Large volume leukapheresis with AMICUS cell separator in peripheral blood stem cell autologous transplant.
Explore the source record for details and available documents.
Adult↗
The reliability of "Analyze" software in measuring orbital volume utilizing CT-derived data.
INTRODUCTION: Craniomaxillofacial surgeons require to estimate the orbital volume in a variety of clinical situations. This paper evaluates a new method based on software analysis of computerized tomography (CT) scan data. MATERIAL AND METHODS: Five dried skulls with prosthetic globes and periorbita were non-helically scanned in an Elscint 2400 CT scanner. Images obtained were processed using the "Analyze" software package and results compared to the volume of the intraorbital prosthesis as determined by a volume displacement gravimetric method. RESULTS: Estimates of volume produced by the software varied from the gold standard by 0.06-50.44%, with a mean error of 8.8%. CONCLUSION: Despite the use of a variety of scan protocols it was not possible to obtain results with "Analyze" software which were sufficiently accurate for clinical use.
Eye, Artificial↗
Advanced research systems' ATLANTES Care Management System.
Explore the source record for details and available documents.
Case Management↗
An Internet-based evaluation system for a surgical residency program.
BACKGROUND: Efficient and meaningful evaluation of performance is critical to the professional development of trainees in surgical residency programs. Current paper-based evaluation instruments have numerous limitations. We developed an Internet-based evaluation system to more rapidly and efficiently assess the experience of residents, faculty, and rotations. STUDY DESIGN: An on-line evaluation system was designed and implemented in October 1999. Custom evaluations were created for residents, faculty, and rotations. Evaluations were completed via the Internet site from remote locations with standard computers and standard Web browser software. Completed evaluations were automatically available on-line for review and data analysis. Data were analyzed by chi-square analysis with a probability value of less than 0.05 considered statistically significant. RESULTS: Compliance in completion of evaluations improved from 50% to 80% in the initial 6 months of implementation (p < 0.01) with the Web-based system. There was no significant difference between faculty and resident compliance. In evaluation of "ease of use," a total of 612 responses were received over this period with a total average score of 3.5 (5 point scale, 5 = strongly agree). Residents' opinions (average score, 3.69) were slightly more positive than those of faculty (average score, 3.31). Confidentiality was improved over paper-based systems by a detailed security network. CONCLUSIONS: This Internet-based evaluation system is a potentially powerful instrument for evaluating our surgical residency program and making changes to improve the educational experience in a timely and efficient manner.
Attitude of Health Personnel↗
MR volumetric analysis of the human basal ganglia: normative data.
RATIONALE AND OBJECTIVES: The authors undertook this study to identify a precise, semiautomated, reproducible magnetic resonance (MR) imaging technique for measuring the basal ganglia, to establish normative volumetric data, and to verify the presence of previously reported asymmetries. MATERIALS AND METHODS: Twenty-eight healthy adults underwent cranial MR examination. The volumes of the various components of the basal ganglia were measured by means of a combination of thresholding and manual tracing techniques performed with specialized software. The validity of these measurements was assessed by fashioning, imaging, and measuring a practical basal ganglia phantom. Measurement accuracy was also established by means of inter- and intrarater reliability indexes. Normalized volumes were statistically analyzed with analysis of variance and paired t tests. RESULTS: The absolute values of the various components of the basal ganglia varied widely even though the volumes were normalized to differences in intracranial volume. The right caudate nucleus volume was significantly (P < .000001) larger than the left in both men and women and in both right-handed and non-right-handed subjects. This asymmetry led to an increase in the overall volume of the basal ganglia on the right. CONCLUSION: The authors have defined a precise, reproducible technique for measuring various components of the basal ganglia and have established normative data. The basal ganglia, similar to other brain structures, exhibit hemispheric lateralization.
Adult↗
Joint Photographic Experts Group compression of intraoral radiographs for image transmission on the World Wide Web.
OBJECTIVE: The purpose of this study was to evaluate the subjective quality of Joint Photographic Experts Group (JPEG) compressed images of intraoral radiographs with file sizes of 30 kilobytes or less, which can be transmitted quickly on the World Wide Web. STUDY DESIGN: Conventional intraoral radiographs were digitized at sampling rates of 100, 200, 300, 400, and 600 dots per inch through use of a flatbed scanner and saved in JPEG format in 11 compression degrees. Fifty-five combinations of sampling rate and compression degree were evaluated by means of a visual analog scale. Sampling rate and compression degree combinations whose quality was inferior to that of an average image were excluded. The quality of the remaining combinations was subsequently evaluated through assessment of 8 anatomical features in each image. RESULTS: Forty of the 55 combinations provided a file size less than 30 kilobytes. Thirty combinations obtained VAS scores of 0 or higher on the standardized VAS. As a result, 16 combinations of sampling and compression conditions were selected for the second part of the study. Only one combination of sampling rate and compression degree was found to provide sufficient image quality for all 8 anatomical features. CONCLUSIONS: Under the file size limit of the study design, the full-sized compressed image of an intraoral radiograph did not always provide sufficient quality. This problem will be reduced by improvements in telecommunications infrastructure, which will permit faster transfer of files of larger size.
Algorithms↗
[Study of theoretical cases of intensity-modulated beams with step-and-shoot technique].
To initiate Intensity-Modulated Radiation Therapy (IMRT) in our department, theoretical cases were used as a training, to define methods of measurements and to verify the software by comparing results of calculation and measurement on a PMMA phantom. Irradiation was performed with 6 and 25 MV X-rays from a linear accelerator. For measurements, films and ionization chambers have been chosen. The comparison between calculations and measurements shows some discrepancies at the level of junctions and also in areas of low doses especially when many segments were used. These theoretical cases provide a first step on the way towards treatments with intensity modulation.
Bias↗
Application of combined genetic algorithms with cascade correlation to diagnosis of delayed gastric emptying from electrogastrograms.
The current standard method (radioscintigraphy) for the diagnosis of delayed gastric emptying (GE) of a solid meal involves radiation exposure and considerable expense. Based on combining genetic algorithms with the cascade correlation learning architecture, a neural network approach is proposed for the diagnosis of delayed GE from electrogastrograms (EGGs). EGGs were measured by placing surface electrodes on the abdominal skin over the stomach in 152 patients with suspected gastric motility disorders for 30 min in the fasting state and for 2 h after a standard test meal. The GE rate of the stomach was simultaneously monitored after the meal using radioscintigraphy. Five spectral parameters of EGG data in each patient were used as the inputs to a classifier. The classifier was designed by using genetic algorithms in conjunction with the cascade correlation learning architecture. The main advantage of this technique over the back-propagation (BP) for supervised learning is that it can automatically develop the architecture of neural networks to give a suitable network size for a specific problem. The resulted neural network with three hidden units exhibits 83% correct classification for the EGG data, and has comparable performance with the BP network. This study demonstrates the potential of the neural network approach based on combined genetic algorithms with cascade correlation for diagnosis of gastric emptying from the EGG.
Algorithms↗
Model extraction from magnetic resonance volume data using the deformable pyramid.
A general framework for automatic model extraction from magnetic resonance (MR) images is described. The framework is based on a two-stage algorithm. In the first stage, a geometrical and topological multiresolution prior model is constructed. It is based on a pyramid of graphs. In the second stage, a matching algorithm is described. This algorithm is used to deform the prior pyramid in a constrained manner. The topological and the main geometrical properties of the model are preserved, and at the same time, the model adapts itself to the input data. We show that it performs a fast and robust model extraction from image data containing unstructured information and noise. The efficiency of the deformable pyramid is illustrated on a synthetic image. Several examples of the method applied to MR volumes are also represented.
Algorithms↗
Critical assessment of healthcare informatics standards.
Explore the source record for details and available documents.
Evaluation Studies as Topic↗
Automated outbreak detection: a quantitative retrospective analysis.
An automated early warning system has been developed and used for detecting clusters of human infection with enteric pathogens. The method used requires no specific disease modelling, and has the potential for extension to other epidemiological applications. A compound smoothing technique is used to determine baseline 'normal' incidence of disease from past data, and a warning threshold for current data is produced by combining a statistically determined increment from the baseline with a fixed minimum threshold. A retrospective study of salmonella infections over 3 years has been conducted. Over this period, the automated system achieved > 90% sensitivity, with a positive predictive value consistently > 50%, demonstrating the effectiveness of the combination of statistical and heuristic methods for cluster detection. We suggest that quantitative measurements are of considerable utility in evaluating the performance of such systems.
Australia↗