SEARCH · PubMed Health

Results for “Pattern Recognition, Automated”

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 181 records · Page 10Linked to original sources

PubMedDate not supplied

Multilevel adaptive process control of acquisition and post-processing of computed radiographic images in picture archiving and communication system environment.

Computed radiography (CR) has become a widely used imaging modality replacing the conventional screen/film procedure in diagnostic radiology. After a latent image is captured in a CR imaging plate, there are seven key processes required before a CR image can be reliably archived and displayed in a picture archiving and communication system (PACS) environment. Human error, computational bottlenecks, software bugs, and CR system errors often crash the CR acquisition and post-processing computers which results in a delay of transmitting CR images for proper viewing at the workstation. In this paper, we present a control theory and a fault tolerance algorithm, as well as their implementation in the PACS environment to circumvent such problems. The software implementation of the control theory and the algorithm is based on the event-driven, multilevel adaptive processing structure. The automated software has been used to provide real-time monitoring and control of CR image acquisition and post-processing in the intensive care unit module of the PACS operation at the University of California, San Francisco. Results demonstrate that the multilevel adaptive process control structure improves CR post-processing time, increases the reliability of the CR images delivery, minimizes user intervention, and speeds up the previously time-consuming quality assurance procedure.

Algorithms↗

PubMed2002

Automatic segmentation of echocardiographic sequences by active appearance motion models.

A novel extension of active appearance models (AAMs) for automated border detection in echocardiographic image sequences is reported. The active appearance motion model (AAMM) technique allows fully automated robust and time-continuous delineation of left ventricular (LV) endocardial contours over the full heart cycle with good results. Nonlinear intensity normalization was developed and employed to accommodate ultrasound-specific intensity distributions. The method was trained and tested on 16-frame phase-normalized transthoracic four-chamber sequences of 129 unselected infarct patients, split randomly into a training set (n = 65) and a test set (n = 64). Borders were compared to expert drawn endocardial contours. On the test set, fully automated AAMM performed well in 97% of the cases (average distance between manual and automatic landmark points was 3.3 mm, comparable to human interobserver variabilities). The ultrasound-specific intensity normalization proved to be of great value for good results in echocardiograms. The AAMM was significantly more accurate than an equivalent set of two-dimensional AAMs.

Algorithms↗

PubMed2003

Optimized region finding and edge detection of knee cartilage surfaces from magnetic resonance images.

Expert hand-drawing of magnetic resonance image (MRI) features can be tedious and time consuming. MRI of the knee were acquired from eight subjects to develop an automated segmentation approach. The regions of interest (ROI) were femur, tibia, and patella cartilage. The Karhunen-Loeve transformation was used to construct prototypical ROI with accentuated features and reduced noise level. Adaptive template matching was then used to translate the prototypical ROI locations for detection and optimal overlap of ROI in test images. Cartilage boundaries at the optimal overlap area were computed based on standard gradient methods.

Cartilage, Articular↗

PubMed1997

Fully automatic identification of AC and PC landmarks on brain MRI using scene analysis.

We describe a method for identification of brain structures from MRI data sets. The bulk of the paper concerns an automatic system for finding the anterior and posterior commissures [(AC) and (PC)] in the midsagittal plane. These landmarks are key for the definition of the Talairach space, commonly used in stereotactic neurosurgery, in the definition of common coordinate systems for the pooling of functional positron emission tomography (PET) images and for neuroanatomy studies. The process works according to a step-by-step procedure: it first analyzes the skull limits. A grey-level histogram is then calculated and allows an automated selection of thresholds. Then, the interhemispheric plane is detected. Following an advanced scene analysis in the midsagittal plane for anatomical structures, the AC and the PC are identified. Experimentally, with a set of 200 patients, the process never failed. Its performances and limits are comparable to that of neuroanatomy experts. Those results are due to a high degree of robustness at each step of the program.

Algorithms↗

PubMed1999

Automated morphometric analysis in peripheral neuropathies.

We describe a three-step algorithm for the morphometric analysis of color images of nerve specimens, currently used in the diagnosis of peripheral neuropathies. The algorithm first segments the images by applying a clustering method in the color space. It then identifies and eliminates irrelevant regions and, in the final step, calculates the diagnostic parameters required for clinical analysis. The results obtained on 25 images are reported and compared with corresponding measurements made by neurologists.

Algorithms↗

PubMed1997

A user-centred design approach for introducing computer-based process information systems.

There has been an increasing tendency to use computer-based process information systems as the main interface through which operators interact with complex industrial systems. Although the new technology has produced greater hardware reliability and maintainability, the corresponding potential benefits for operability have not always been achieved. Automation has introduced new forms of design and operating errors. One of the major reasons for this problem has been the lack of human factors advice and user participation early in the design process. This paper discusses a user-centred design approach to increase operability and user acceptance of new technologies and working practices. Application of this approach in the context of a chemical plant indicates its promise, but also highlights the difficulties involved in gaining user participation and management commitment.

Chemical Industry↗

PubMedDate not supplied

Acquiring background knowledge for machine learning using function decomposition: a case study in rheumatology.

Domain or background knowledge is often needed in order to solve difficult problems of learning medical diagnostic rules. Earlier experiments have demonstrated the utility of background knowledge when learning rules for early diagnosis of rheumatic diseases. A particular form of background knowledge comprising typical co-occurrences of several groups of attributes was provided by a medical expert. This paper explores the possibility of automating the process of acquiring background knowledge of this kind and studies the utility of such methods in the problem domain of rheumatic diseases. A method based on function decomposition is proposed that identifies typical co-occurrences for a given set of attributes. The method is evaluated by comparing the typical co-occurrences it identifies as well as their contribution to the performance of machine learning algorithms, to the ones provided by a medical expert.

Algorithms↗

PubMed1996

Autonomous design of artificial neural networks by Neurex.

Artificial neural networks (ANN) have been demonstrated to be increasingly more useful for complex problems difficult to solve with conventional methods. With their learning abilities, they avoid having to develop a mathematical model or acquiring the appropriate knowledge to solve a task. The difficulty now lies in the ANN design process. A lot of choices must be made to design an ANN, and there are no available design rules to make these choices directly for a particular problem. Therefore, the design for an ANN demands a certain number of iterations, mainly guided by the expertise and the intuition of the developer. To automate the ANN design process, we have developed Neurex, composed of an expert system and an ANN simulator. Neurex autonomously guides the iterative ANN design process. Its structure tries to reproduce the design steps done by a human expert in conceiving an ANN. As a whole, the Neurex structure serves as a framework to implement this expertise for different learning paradigms. This article presents the system's general characteristics and its use in designing ANN using the standard backpropagation learning law.

Computer Simulation↗

PubMed1990

The Athena semi-automated karyotyping system.

In this article we describe Athena, a system that provides for semi-automated karyotyping of metaphase spreads. The system is based upon the Macintosh II computer. It uses software that is written entirely in C and consists of approximately 200 Kbytes of executable code. Athena provides automated segmentation of metaphase images into individual chromosomes, automated measurements on each banded chromosome, and automated classification into the standard Paris-convention karyotype. Furthermore, the system provides the ability to construct one or more chromosome data bases to represent the types of metaphase spreads and staining techniques that may be used in a given laboratory. Because we believe that it is impossible to construct a system that can achieve perfect segmentation, perfect separation of touching and overlapping chromosomes, perfect localization of the centromeres, and perfect classification, the system offers the possibility for interaction at each of the above stages using the well-accepted Macintosh user interface.

Centromere↗

PubMed2002

GP3: GenePix post-processing program for automated analysis of raw microarray data.

UNLABELLED: Here we describe an automated and customizable program to correct, filter and normalize raw microarray data captured using GenePix, a commonly used microarray image analysis application. Files can be processed individually or in batch mode for increased throughput. User defined inputs specify the stringency of data filtering and the method and conditions of normalization. The output includes gene summaries for replicate spots and descriptive statistics for each experiment. The source code (Perl) can also be adapted to handle raw data output from other image analysis applications. AVAILABILITY: http://bch.msu.edu/~zacharet/microarray/GP3.html

Algorithms↗

PubMed2003

Efficient center-line extraction for quantification of vessels in confocal microscopy images.

In this paper we present a novel method for the three-dimensional (3-D) centerline extraction of elongated objects such as vessels. This method combines the basic ideas in distance transform-based, thinning, and path planning methods to extract thin and connected centerlines. This efficient approach needs no user interaction or any prior knowledge of the object shape. We used the path planning approach, which has exclusively been used in the virtual endoscopy or robotics, to obtain the medial curve of the objects. To make our approach fully automated, a distance transform mapping is used to identify the end points of the object branches. The initial paths are also constructed on the surface of the object, traversing the same distance map. Then a thinning algorithm centralizes the paths. The proposed approach is especially efficient for centerline extraction of the complex branching structures. The method has been applied on the confocal microscopy images of rat brains and the results confirm its efficiency in extracting the medial curve of vessels, essential for the computation of quantitative parameters.

Algorithms↗

PubMed2003

An objective method to measure cell survival by computer-assisted image processing of numeric images of Petri dishes.

This work establishes an objective method to measure cell clonogenic survival by computer-assisted image processing using images of cell cultures fixed and stained in Petri dishes. The procedure, developed by Samba Technologies, consists of acquiring Petri dish pictures with a desktop scanner and analysing them by computer, using algorithms based on the 'top hat' filter. The results from the automated count for the cell line SQ20B are compared with those found by two observers, before and after normalization of the counting. After normalization, the shape of the survival curves of the 'manual' counting of the Petri dishes shows a good correlation between both observers. The software enables the small visible differences in count between observers to be eliminated. The comparison between the absolute number of colonies shows an increased difference between the two manual scorings that can be as great as 67 colonies, whereas the difference between the two automated counts is never greater than 8 colonies. These results demonstrate that the 'manual' count is inter- and intraobserver variable, whereas the automatic count performs reproducible cell colony counts, thereby minimizing user-generated bias. The large amount of data produced also gives information about cell and colony characteristics. Thus, this computer-assisted method has considerably improved the reliability of our statistical results.

Algorithms↗

PubMed1979

An image analysis system for cervical cytology automation using nuclear DNA content.

An experimental computer/image analysis system has been used to investigate cytology automation techniques based on nuclear DNA measurement and morphological artefact rejector tests. The system automatically measures and normalizes the integrated optical density of cell nuclei in specially prepared cervical cytology specimens, and selects any objects with abnormally high values for further analysis. These are then analyzed by morphological and densitometric tests designed to eliminate false positive signals caused by non-nuclear artefacts. The coordinates of the remaining abnormal nuclei are recorded so that they can subsequently be relocated and examined by a cytotechnician. Preliminary results are given showing the measurement accuracy of the system and the performance of the artefact rejection tests.

Cell Nucleus↗

PubMed2003

Automated lung nodule classification following automated nodule detection on CT: a serial approach.

We have evaluated the performance of an automated classifier applied to the task of differentiating malignant and benign lung nodules in low-dose helical computed tomography (CT) scans acquired as part of a lung cancer screening program. The nodules classified in this manner were initially identified by our automated lung nodule detection method, so that the output of automated lung nodule detection was used as input to automated lung nodule classification. This study begins to narrow the distinction between the "detection task" and the "classification task." Automated lung nodule detection is based on two- and three-dimensional analyses of the CT image data. Gray-level-thresholding techniques are used to identify initial lung nodule candidates, for which morphological and gray-level features are computed. A rule-based approach is applied to reduce the number of nodule candidates that correspond to non-nodules, and the features of remaining candidates are merged through linear discriminant analysis to obtain final detection results. Automated lung nodule classification merges the features of the lung nodule candidates identified by the detection algorithm that correspond to actual nodules through another linear discriminant classifier to distinguish between malignant and benign nodules. The automated classification method was applied to the computerized detection results obtained from a database of 393 low-dose thoracic CT scans containing 470 confirmed lung nodules (69 malignant and 401 benign nodules). Receiver operating characteristic (ROC) analysis was used to evaluate the ability of the classifier to differentiate between nodule candidates that correspond to malignant nodules and nodule candidates that correspond to benign lesions. The area under the ROC curve for this classification task attained a value of 0.79 during a leave-one-out evaluation.

Adult↗

PubMedDate not supplied

A small angle light scattering device for planar connective tissue microstructural analysis.

The planar fibrous connective tissues of the body are composed of a dense extracellular network of collagen and elastin fibers embedded in a ground matrix, and thus can be thought of as biocomposites. Thus, the quantification of fiber architecture is an important step in developing an understanding of the mechanics of planar tissues in health and disease. We have used small angle light scattering (SALS) to map the gross fiber orientation of several soft membrane connective tissues. However, the device and analysis methods used in these studies required extensive manual intervention and were unsuitable for large-scale fiber architectural mapping studies. We have developed an improved SALS device that allows for rapid data acquisition, automated high spatial resolution specimen positioning, and new analysis methods suitable for large-scale mapping studies. Extensive validation experiments revealed that the SALS device can accurately measure fiber orientation for up to a tissue thickness of at least 500 microns to an angular resolution of approximately 1 degree and a spatial resolution of +/-254 microns. To demonstrate the new device's capabilities, structural measurements from porcine aortic valve leaflets are presented. Results indicate that the new SALS device provides an accurate method for rapid quantification of the gross fiber structure of planar connective tissues.

Animals↗

PubMed2003

Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels.

We describe an automated method to locate the optic nerve in images of the ocular fundus. Our method uses a novel algorithm we call fuzzy convergence to determine the origination of the blood vessel network. We evaluate our method using 31 images of healthy retinas and 50 images of diseased retinas, containing such diverse symptoms as tortuous vessels, choroidal neovascularization, and hemorrhages that completely obscure the actual nerve. On this difficult data set, our method achieved 89% correct detection. We also compare our method against three simpler methods, demonstrating the performance improvement. All our images and data are freely available for other researchers to use in evaluating related methods.

Algorithms↗

PubMed1997

Computerized analysis of daily life motor activity for ambulatory monitoring.

The primary goal of an ambulatory monitoring of motor activities (AMMA) system is to document the occurrence of random and spontaneous motor activities (e.g., sitting, lying, standing, walking, running, etc.) of the ambulatory subject in natural environmental circumstances. Much progress has been made in recording fidelity, reduction in energy requirement, fixation of the accelerometers, equipment size and weight, memory capacity and data acquisition. At present, our laboratory is interested in developing an automated off-line AMMA-signal analysis system. The system has to take care of activity (wave) detection, recognition of onsets and endpoints of the various activities (waves), and computation of a set of relevant clinical parameters (e.g., total walking time, number of times rising from a chair, etc.) from long-term recorded data. Two methods are currently being used for computerizing the off-line analysis system: using an artificial neural network and using a set of selected features extracted from the input data. The present paper is aimed at the latter method. The method was successfully applied to long-term recorded data sets of eight male amputees and three other subjects. The primary results indicate that the method is a potentially useful too to computerize the off-line analysis system.

Activities of Daily Living↗

PubMed2002

An automatic block and spot indexing with k-nearest neighbors graph for microarray image analysis.

MOTIVATION: In this paper, we propose a fully automatic block and spot indexing algorithm for microarray image analysis. A microarray is a device which enables a parallel experiment of ten to hundreds of thousands of test genes in order to measure gene expression. Due to this huge size of experimental data, automated image analysis is gaining importance in microarray image processing systems. Currently, most of the automated microarray image processing systems require manual block indexing and, in some cases, spot indexing. If the microarray image is large and contains a lot of noise, it is very troublesome work. In this paper, we show it is possible to locate the addresses of blocks and spots by applying the Nearest Neighbors Graph Model. Also, we propose an analytic model for the feasibility of block addressing. Our analytic model is validated by a large body of experimental results. RESULTS: We demonstrate the features of automatic block detection, automatic spot addressing, and correction of the distortion and skewedness of each microarray image.

Algorithms↗