Computerized analysis of abnormal asymmetry in digital chest radiographs: evaluation of potential utility. (1/3779)

The purpose of this study was to develop and test a computerized method for the fully automated analysis of abnormal asymmetry in digital posteroanterior (PA) chest radiographs. An automated lung segmentation method was used to identify the aerated lung regions in 600 chest radiographs. Minimal a priori lung morphology information was required for this gray-level thresholding-based segmentation. Consequently, segmentation was applicable to grossly abnormal cases. The relative areas of segmented right and left lung regions in each image were compared with the corresponding area distributions of normal images to determine the presence of abnormal asymmetry. Computerized diagnoses were compared with image ratings assigned by a radiologist. The ability of the automated method to distinguish normal from asymmetrically abnormal cases was evaluated by using receiver operating characteristic (ROC) analysis, which yielded an area under the ROC curve of 0.84. This automated method demonstrated promising performance in its ability to detect abnormal asymmetry in PA chest images. We believe this method could play a role in a picture archiving and communications (PACS) environment to immediately identify abnormal cases and to function as one component of a multifaceted computer-aided diagnostic scheme.  (+info)

Machine learning approaches for the prediction of signal peptides and other protein sorting signals. (2/3779)

Prediction of protein sorting signals from the sequence of amino acids has great importance in the field of proteomics today. Recently, the growth of protein databases, combined with machine learning approaches, such as neural networks and hidden Markov models, have made it possible to achieve a level of reliability where practical use in, for example automatic database annotation is feasible. In this review, we concentrate on the present status and future perspectives of SignalP, our neural network-based method for prediction of the most well-known sorting signal: the secretory signal peptide. We discuss the problems associated with the use of SignalP on genomic sequences, showing that signal peptide prediction will improve further if integrated with predictions of start codons and transmembrane helices. As a step towards this goal, a hidden Markov model version of SignalP has been developed, making it possible to discriminate between cleaved signal peptides and uncleaved signal anchors. Furthermore, we show how SignalP can be used to characterize putative signal peptides from an archaeon, Methanococcus jannaschii. Finally, we briefly review a few methods for predicting other protein sorting signals and discuss the future of protein sorting prediction in general.  (+info)

Mid-peripheral pattern electrical retinal responses in normals, glaucoma suspects, and glaucoma patients. (3/3779)

AIMS: Reliance on intraocular pressure, optic nerve cupping changes, nerve fibre layer integrity, and visual field changes may delay treatment of glaucoma since irreversible changes may have already occurred at the time of diagnosis. Abnormal pattern electrical retinal responses (PERR or PERG) have been demonstrated in patients with ocular hypertension (no visual field changes) and glaucoma when visual stimulation was presented to the central field. Since glaucomatous visual field changes tend to occur first in the mid-periphery, the use of PERR outside of the central field may offer an earlier indication of glaucomatous involvement. METHODS: Glaucoma suspects and glaucoma patients were derived from a university practice. Normal subjects were recruited from non-patient volunteers. Alternating bar gratings were presented in the supranasal, supratemporal, infratemporal, and infranasal visual field. Six spatial frequencies, from 0.25 to 6.0 cycles per degree, were used for normal volunteers; three spatial frequencies, from 0.38 to 1.5 cycles per degree, were presented to suspects and glaucoma patients. Time of onset of the first negative (N35) and first positive peak (P50) and the amplitude consisting of the absolute difference between the first negative peak and first positive peak (P50 amplitude) are reported. Age corrected values were determined for normals, suspects, and glaucoma patients for each spatial frequency and for each quadrant in the visual field. RESULTS: Mean P50 amplitudes from normal subjects showed spatial tuning in all quadrants with reduced low frequency attenuation. Normals demonstrated a small decline in amplitude with age. Glaucoma patients demonstrated an age corrected reduction in amplitude and early implicit times. Glaucoma suspects had values between those of normal and glaucoma subjects. P50 amplitudes were weakly correlated with increasing cup to disc diameter ratio. A glaucoma patient with asymmetric visual field loss demonstrated significant diminution of the PERR bilaterally. CONCLUSION: The PERR, using mid-peripheral stimulation, may be a sensitive tool for the early detection of glaucoma. Further refinements can speed clinical data acquisition and enhance signal to noise ratio.  (+info)

Syntactic analysis and languages of shape feature description in computer-aided diagnosis and recognition of cancerous and inflammatory lesions of organs in selected x-ray images. (4/3779)

We present new algorithms for the recognition of morphologic changes and shape feature analysis, which have been proposed to be used in a diagnosis of pathologic symptoms characteristic of cancerous and inflammatory lesions. These methods have been used so far for early detection and diagnosis of neoplastic changes in pancreas and chronic pancreatitis based on x-ray images acquired by endoscopic retrograde cholangiopancreatography (ERCP). Preliminary processing of x-ray images involves binarization, and, subsequently, pancreatic ducts shown in the pictures are subjected to the straightening transformation, which enables obtaining two-dimensional width graphs that show contours of objects with their morphologic changes. Recognition of such changes was performed using attributed context-free grammars. Correct description and diagnosis of some symptoms (e.g., large cavitary projections) required two-dimensional analysis of width graphs. In such cases, languages of shape feature description with special multidirectional sinquad distribution were additionally applied.  (+info)

Content-based image retrieval in picture archiving and communications systems. (5/3779)

We propose the concept of content-based image retrieval (CBIR) and demonstrate its potential use in picture archival and communication system (PACS). We address the importance of image retrieval in PACS and highlight the drawbacks existing in traditional textual-based retrieval. We use a digital mammogram database as our testing data to illustrate the idea of CBIR, where retrieval is carried out based on object shape, size, and brightness histogram. With a user-supplied query image, the system can find images with similar characteristics from the archive, and return them along with the corresponding ancillary data, which may provide a valuable reference for radiologists in a new case study. Furthermore, CBIR can perform like a consultant in emergencies when radiologists are not available. We also show that content-based retrieval is a more natural approach to man-machine communication.  (+info)

Information systems integration in radiology. (6/3779)

Advances in information systems and technology in conjunction with outside forces requiring improved reporting are driving sweeping changes in the practice of radiology. In most academic radiology departments, there can be at least five separate information systems in daily use, a clinical picture archiving and communication system (PACS), a hospital information system (HIS), a radiology information system (RIS), a voice-recognition dictation system, and an electronic teaching/research file system. A PACS will have incomplete, incorrect, and inconsistent data if manual data entry is used. Correct routing of studies for diagnostic reporting and clinical review requires accurate information about the study type and the referring physician or service, often not easily entered manually. An HIS is a hospital-wide information system used to access patient information, reports from various services, and billing information. The RIS is typically a system specifically designed to place radiology orders, to receive interpretations, and to prepare bills for patients. Voice-recognition systems automatically transcribe the radiologist's dictation, eliminating transcription delays. Another system that is needed in a teaching hospital holds images and data for research and education. Integration of diverse systems must be performed to provide the functionality required by an electronic radiology department and the services it supports. Health Level 7 (HL7) and Digital Imaging and Communications in Medicine (DICOM) have enabled sharing of data among systems and can be used as the building blocks for truly integrated systems, but the user community and manufacturers need to specify the types of functionality needed to build clinically useful systems. Although technology development has produced the tools for interoperability for clinical and research/educational use, more work needs to be done to define the types of interaction that needs to be performed to realize the potential of these systems.  (+info)

Improved performance in protein secondary structure prediction by inhomogeneous score combination. (7/3779)

MOTIVATION: In many fields of pattern recognition, combination has proved efficient to increase the generalization performance of individual prediction methods. Numerous systems have been developed for protein secondary structure prediction, based on different principles. Finding better ensemble methods for this task may thus become crucial. Furthermore, efforts need to be made to help the biologist in the post-processing of the outputs. RESULTS: An ensemble method has been designed to post-process the outputs of discriminant models, in order to obtain an improvement in prediction accuracy while generating class posterior probability estimates. Experimental results establish that it can increase the recognition rate of protein secondary structure prediction methods that provide inhomogeneous scores, even though their individual prediction successes are largely different. This combination thus constitutes a help for the biologist, who can use it confidently on top of any set of prediction methods. Moreover, the resulting estimates can be used in various ways, for instance to determine which areas in the sequence are predicted with a given level of reliability. AVAILABILITY: The prediction is freely available over the Internet on the Network Protein Sequence Analysis ([email protected]) WWW server at ml. The source code of the combiner can be obtained on request for academic use.  (+info)

The Kautsky curve is a built-in barcode. (8/3779)

We identify objects from their visually observable morphological features. Automatic methods for identifying living objects are often needed in new technology, and these methods try to utilize shapes. When it comes to identifying plant species automatically, machine vision is difficult to implement because the shapes of different plants overlap and vary greatly because of different viewing angles in field conditions. In the present study we show that chlorophyll a fluorescence, emitted by plant leaves, carries information that can be used for the identification of plant species. Transient changes in fluorescence intensity when a light is turned on were parameterized and then subjected to a variety of pattern recognition procedures. A Self-Organizing Map constructed from the fluorescence signals was found to group the signals according to the phylogenetic origins of the plants. We then used three different methods of pattern recognition, of which the Bayesian Minimum Distance classifier is a parametric technique, whereas the Multilayer Perceptron neural network and k-Nearest Neighbor techniques are nonparametric. Of these techniques, the neural network turned out to be the most powerful one for identifying individual species or groups of species from their fluorescence transients. The excellent recognition accuracy, generally over 95%, allows us to speculate that the method can be further developed into an application in precision agriculture as a means of automatically identifying plant species in the field.  (+info)