PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “computer vision”

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 109 records · Page 6Linked to original sources
PubMed2001

Comparison of diagnosis of early retinal lesions of diabetic retinopathy between a computer system and human experts.

OBJECTIVE: To investigate whether a computer vision system is comparable with humans in detecting early retinal lesions of diabetic retinopathy using color fundus photographs. METHODS: A computer system has been developed using image processing and pattern recognition techniques to detect early lesions of diabetic retinopathy (hemorrhages and microaneurysms, hard exudates, and cotton-wool spots). Color fundus photographs obtained from American Indians in Oklahoma were used in developing and testing the system. A set of 369 color fundus slides were used to train the computer system using 3 diagnostic categories: lesions present, questionable, or absent (Y/Q/N). A different set of 428 slides were used to test and evaluate the system, and its diagnostic results were compared with those of 2 human experts-the grader at the University of Wisconsin Fundus Photograph Reading Center (Madison) and a general ophthalmologist. The experiments included comparisons using 3 (Y/Q/N) and 2 diagnostic categories (Y/N) (questionable cases excluded in the latter). RESULTS: In the training phase, the agreement rates, sensitivity, and specificity in detecting the 3 lesions between the retinal specialist and the computer system were all above 90%. The kappa statistics were high (0.75-0.97), indicating excellent agreement between the specialist and the computer system. In the testing phase, the results obtained between the computer system and human experts were consistent with those of the training phase, and they were comparable with those between the human experts. CONCLUSIONS: The performance of the computer vision system in diagnosing early retinal lesions was comparable with that of human experts. Therefore, this mobile, electronically easily accessible, and noninvasive computer system, could become a mass screening tool and a clinical aid in diagnosing early lesions of diabetic retinopathy.

Aged↗
PubMed1996

Image representations for visual learning.

Computer vision researchers are developing new approaches to object recognition and detection that are based almost directly on images and avoid the use of intermediate three-dimensional models. Many of these techniques depend on a representation of images that induce a linear vector space structure and in principle requires dense feature correspondence. This image representation allows the use of learning techniques for the analysis of images (for computer vision) as well as for the synthesis of images (for computer graphics).

Artificial Intelligence↗
PubMed1999

The role of convexity in perceptual completion: beyond good continuation.

Since the seminal work of the Gestalt psychologists, there has been great interest in understanding what factors determine the perceptual organization of images. While the Gestaltists demonstrated the significance of grouping cues such as similarity, proximity and good continuation, it has not been well understood whether their catalog of grouping cues is complete--in part due to the paucity of effective methodologies for examining the significance of various grouping cues. We describe a novel, objective method to study perceptual grouping of planar regions separated by an occluder. We demonstrate that the stronger the grouping between two such regions, the harder it will be to resolve their relative stereoscopic depth. We use this new method to call into question many existing theories of perceptual completion (Ullman, S. (1976). Biological Cybernetics, 25, 1-6; Shashua, A., & Ullman, S. (1988). 2nd International Conference on Computer Vision (pp. 321-327); Parent, P., & Zucker, S. (1989). IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 823-839; Kellman, P. J., & Shipley, T. F. (1991). Cognitive psychology, Liveright, New York; Heitger, R., & von der Heydt, R. (1993). A computational model of neural contour processing, figure-ground segregation and illusory contours. In Internal Conference Computer Vision (pp. 32-40); Mumford, D. (1994). Algebraic geometry and its applications, Springer, New York; Williams, L. R., & Jacobs, D. W. (1997). Neural Computation, 9, 837-858) that are based on Gestalt grouping cues by demonstrating that convexity plays a strong role in perceptual completion. In some cases convexity dominates the effects of the well known Gestalt cue of good continuation. While convexity has been known to play a role in figure/ground segmentation (Rubin, 1927; Kanizsa & Gerbino, 1976), this is the first demonstration of its importance in perceptual completion.

Cues↗
PubMed1994

Quantification of local symmetry: application to texture discrimination.

Symmetry is one of the most prominent cues in visual perception as well as in computer vision. We have recently presented a Generalized Symmetry Transform that receives as input an edge map, and outputs a symmetry map, where every point marks the intensity and orientation of the local generalized symmetry. In the context of computer vision, this map emphasizes points of high symmetry, which, in turn, are used to detect regions of interest for active vision systems. Many psychophysical experiments in texture discrimination use images that consist of various micro-patterns. Since the Generalized Symmetry Transform captures local spatial relations between image edges, it has been used here to predict human performance in discrimination tasks. Applying the transform to micro-patterns in some well-studied quantitative experiments of human texture discrimination, it is shown that symmetry, as characterized by the present computational scheme, can account for most of them.

Form Perception↗
PubMed1989

Fluorescence digital microscopy of interstitial macromolecular diffusion in burn injury.

Computer vision techniques implemented on an IBM PC/AT have been applied to the study of microvascular permeability and interstitial diffusion in dorsal skin flap chamber preparations of hamsters. Experimental data was obtained for the leakage of fluorescent labelled dextran (70,000 daltons) after a precisely controlled mild degree of localized thermal trauma and compared with control data acquired prior to burn injury. Computer vision analysis techniques were applied to convert the fluorescent images into two-dimensional concentration maps. Interstitial diffusion coefficient values were computed from measured extravascular concentration profiles around a vessel of interest, assuming cylindrical or rectangular geometry, and optimally fitting a diffusion model to the data. An increase in the apparent diffusivity after mild thermal trauma was observed. Novel techniques were applied to solve hardware problems related to data acquisition and analysis, and a new library of software was developed to handle specific image processing requirements.

Animals↗
PubMed2005

[Watershed-based segmentation of histiocytic images].

The task of segmenting histiocyte is a crucial step in the analysis of histiocytic images which is an important application of computer vision to histopathology. The algorithm presented in this article was composed of two steps: (1) the morph-based preprocessing; (2) the ameliorated watershed method. In the first step, the difference between histiocytes was magnified in order to increase the visibility from the view of the computer vision, and then the ameliorated terrace-flooding-simulated watershed method was used to achieve the segmentation of histiocytic images in the second step. To test the performance of the algorithm, different samples of visual quality were tested and the result figures proved successful.

Algorithms↗
PubMed1999

Efficient computational algorithms for docking and for generating and matching a library of functional epitopes I. Rigid and flexible hinge-bending docking algorithms.

In this, and the next review article (1), we present highly efficient, computer-vision and robotics based algorithms for docking and for the generation and matching of epitopes on molecular surfaces. We start with descriptions of molecular surfaces, and proceed to utilize these in both rigid-body and flexible matching routines. These algorithms originate in the computer vision and robotics disciplines. Frequently used approaches, both in searches for molecular similarity and for docking, i.e., molecular complementarity, strive to obtain highly accurate correspondence of respective molecular surfaces. However, owing to molecular surface variability in solution, to mutational events, and to the need to use modeled structures in addition to high resolution ones, utilization of epitopes might prove to be a judicious approach to follow. Furthermore, through the deployment of libraries of epitopes which represent recurring features, or motifs in a given family of receptors or of enzymes, in principle we a priori focus on the more critical groups of atoms, or amino acids, essential for the binding of the two molecules. Utilization of recurring motifs may prove more robust than single molecule matchings. In addition, via utilization of epitopes one can make use of information derived from evolutionary related molecules. All of the above combine to represent an approach which may be highly advantageous. Combinatorial approaches have proven their immense utility in the wet laboratory. The combination of efficient computational approaches and the utilization of such libraries may well be particularly profitable. Our highly efficient techniques are amenable to such a task. In this review we focus on rigid and flexible docking algorithms. In the second review (1) we address the generation of epitopes in families of molecules. These may be used by the docking algorithms to identify the more likely bound interfaces.

Algorithms↗
PubMed1992

Potential usefulness of computerized nodule detection in screening programs for lung cancer.

RATIONALE AND OBJECTIVE: To alert radiologists to possible nodule locations and subsequently to reduce the number of false-negative diagnoses, the authors are developing a computer-aided diagnostic (CAD) scheme for the detection of lung nodules in digital chest images. METHODS: A computer-vision scheme was applied to photofluorographic films obtained in a mass survey for detection of asymptomatic lung cancer in Japan. Ninety-five patients with abnormal test results who had primary and metastatic lung cancers and 103 patients with normal test results were included. RESULTS: The sensitivity of the computer output was comparable with that of physicians in this mass survey (62%). The computer detected approximately 40% of all nodules missed in the mass survey, but missed 17 true-positive results identified in the mass survey. The CAD scheme produced an average of 15 false-positive findings per image. CONCLUSION: If the number of false-positive results can be significantly reduced, computer-vision schemes such as this may have a role in lung cancer screening programs.

False Positive Reactions↗
PubMed2002

Do third-party plans really pay for CVS care?

Until specific CPT and ICD-9 codes are created and approved for CVS, and until there is uniform agreement that CVS is a true medical anomaly (or not), each practitioner will have to decide on how to bill for the signs and symptoms of Computer Vision Syndrome. If the practitioner chooses to view CVS as a medical problem, then the same guidelines and rules for all other patients should be followed with appropriate documentation using CPT and ICD-9 coding. If the practitioner chooses to consider CVS solely as an optical problem, this is a "noncovered" service and the patient or any applicable optical plan will be responsible for payment. One final note: each practitioner who tests for CVS will also have to determine if there is a separate fee for CVS testing. If the practitioner considers CVS to be a medical problem, it may be applicable to include testing for Computer Vision Syndrome as an incidental test to the medical office visit. If the practitioner chooses to consider CVS to be purely an optical problem, it may be appropriate to add an appropriate charge to the noncovered examination. Whatever the decision is, there must be consistency from patient to patient.

Computers↗
PubMed2006

Standardization of edge magnitude in color images.

Edge detection is a useful task in low-level image processing. The efficiency of many image processing and computer vision tasks depends on the perfection of detecting meaningful edges. To get a meaningful edge, thresholding is almost inevitable in any edge detection algorithm. Many algorithms reported in the literature adopt ad hoc schemes for this purpose. These algorithms require the threshold values to be supplied and tuned by the user. There are many high-level tasks in computer vision which are to be performed without human intervention. Thus, there is a need to develop a scheme where a single set of threshold values would give acceptable results for many color images. In this paper, an attempt has been made to devise such an algorithm. Statistical variability of partial derivatives at each pixel is used to obtain standardized edge magnitude and is thresholded using two threshold values. The advantage of standardization is evident from the results obtained.

Algorithms↗
PubMed2003

Video reconstructions in dentistry.

OBJECTIVES: To present two practical techniques for three-dimensional (3D) modeling of the human jaw from a sequence of intra-oral images. DESIGN: A data acquisition system consists of: 3D digitizing arm, CCD camera and a laser projector in addition to a software module of two 3D modeling techniques; shape from shading (SFS) and space carving (SC). SETTING AND SAMPLE POPULATION: Several experiments have been conducted on a sample of students at the Computer Vision and Image Processing (CVIP) Laboratory at the University of Louisville, Louisville, KY. Other experiments were performed on solid models of human jaw. EXPERIMENTAL VARIABLE: The SFS technique, using perspective projection and camera calibration, extracts the 3D information from a sequence of two-dimensional images of the jaw. Data fusion of range data and 3D registration techniques develop the complete jaw model. The SC approach is implemented on a sequence of calibrated images. On the two reconstructions, we fit a mesh model to the data, in order to create a solid 3D model. OUTCOME MEASURE: The accuracy of the reconstructed 3D model of human jaw is calculated based on the measurements on real jaws. RESULTS: The SFS-based technique seems to provide more faithful information about the shape of the tooth tops. However, the SC algorithm successfully reconstructed 3D models of the human jaw with sub-millimeter accuracy, which is as accurate as (or even better than) the first technique without using any range measurements or laser projectors. The average error in distance calculation was found to be 0.74 mm, which is an acceptable resolution for many orthodontics and maxillofacial applications. CONCLUSION: Accurate 3D reconstruction of the human jaw enables many orthodontics and dental imaging research findings to be applied directly to a digital jaw model--not to a cast--using computer vision and medical imaging tools.

Algorithms↗
PubMed1998

Advances in three-dimensional diagnostic radiology.

The maturity of current 3D rendering software in combination with recent developments in computer vision techniques enable an exciting range of applications for the visualisation, measurement and interactive manipulation of volumetric data, relevant both for diagnostic imaging and for anatomy. This paper reviews recent work in this area from the Image Sciences Institute at Utrecht University. The processes that yield a useful visual presentation are sequential. After acquisition and before any visualisation, an essential step is to prepare the data properly: this field is known as 'image processing' or 'computer vision' in analogy with the processing in human vision. Examples will be discussed of modern image enhancement and denoising techniques, and the complex process of automatically finding the objects or regions of interest, i.e. segmentation. One of the newer and promising methodologies for image analysis is based on a mathematical analysis of the human (cortical) visual processing: multiscale image analysis. After preprocessing the 3D rendering can be acquired by simulating the 'ray casting' in the computer. New possibilities are presented, such as the integrated visualisation in one image of (accurately registered) datasets of the same patient acquired in different modality scanners. Other examples include colour coding of functional data such as SPECT brain perfusion or functional magnetic resonance (MR) data and even metric data such as skull thickness on the rendered 3D anatomy from MR or computed tomography (CT). Optimal use and perception of 3D visualisation in radiology requires fast display and truly interactive manipulation facilities. Modern and increasingly cheaper workstations ( < $10000) allow this to be a reality. It is now possible to manipulate 3D images of 256 at 15 frames per second interactively, placing virtual reality within reach. The possibilities of modern workstations become increasingly more sophisticated and versatile. Examples presented include the automatic detection of the optimal viewing angle of the neck of aneurysms and the simulation of the design and placement procedure of intra-abdominal aortic stents. Such developments, together with the availability of high-resolution datasets of modern scanners and data such as from the NIH Visible Human project, have a dramatic impact on interactive 3D anatomical atlases.

Humans↗
PubMed2001

Marker-less systems for tracking working postures--results from two experiments.

Two experiments are performed to examine the usability of different marker-less approaches in image analysis and computer vision for automatic registration of OWAS (Ovako working posture analysing system) postures from video film. In experiment 1, a parametric method based on image analysis routines is developed both for separating the subject from its background and for relating the shapes of the extracted subject to OWAS postures. All 12 analysed images were correctly classified by the method. In experiment 2 a computer neural network is taught to relate postures of a subject to OWAS postures. When the network was trained with 53 images the rest of the set of 138 images was correctly classified. The experiments described in this paper show promising results regarding the use of image analysis and computer vision for tracking and assessing working postures. However, further research is needed including tests of different human models, neural networks, and template matching for making the OWAS method more useful in identifying and evaluating potentially harmful working postures.

Humans↗
PubMed1997

Using neural networks to automatically detect brain tumours in MR images.

Computer vision has been applied to many medical imaging problems with the aim of providing clinical tools to aid medical professionals. We present work being carried out to develop one such system to automatically detect a specific type of brain tumour from head MR images. The tumour under consideration is an acoustic neuroma, which is a benign tumour occurring in the acoustic canals. The hybrid system developed integrates neural networks with more conventional techniques used for computer vision tasks. A database of MR images from 50 patients has been assembled and the acoustic neuromas present in the images have been labelled by hand. Using this data, neural networks (MLPs) have been developed to classify the images at the pixel level to achieve a targeted segmentation. The data used to train and test the MLPs developed, consists of the grey levels of a square of pixels, the pixel to be classified being the centre pixel, together with its global position in the image. The initial pixel level segmentation is refined by a series of conventional techniques. It is combined with an edge-region based segmentation and a morphological operation is applied to the result. This processing produces clusters of adjacent regions, which are considered to be candidate tumour regions. For each possible combination of these regions, features are measured and presented to neural networks which have been trained to identify structures corresponding to acoustic neuromas. Using this approach, all the acoustic neuromas are identified together with three false positive errors.

Automation↗
PubMed1995

Classification of microcalcifications in radiographs of pathologic specimens for the diagnosis of breast cancer.

RATIONALE AND OBJECTIVES: Early detection of breast cancer depends on accurate classification of microcalcifications. We have developed a computer vision system that has the potential to classify microcalcifications objectively and consistently to aid radiologists in diagnosing breast cancer. METHODS: A convolution neural network (CNN) was used to classify benign and malignant microcalcifications in radiographs of pathologic specimens. Digital images were acquired by digitizing radiographs at a high resolution of 21 microns x 21 microns. RESULTS: Eighty regions of interest selected from digitized radiographs of pathologic specimens were used for training and testing of the neural network system. The CNN achieved an Az value (area under the receiver operating characteristic curve) of 0.90 in classifying clusters of microcalcifications associated with benign and malignant processes. CONCLUSION: Classification of microcalcifications in pathologic specimens for diagnosis of breast cancer was achieved at a high level in our computer vision system, which consists of high-resolution digitization of mammograms and a CNN.

Breast Neoplasms↗
PubMed2000

Tracking differential interference contrast diffraction line images with nanometre sensitivity.

This paper presents a computer vision framework for detecting and tracking diffraction images of linear structures in differential interference contrast (DIC) microscopy. The tracker can resolve image displacements of 1/10 of a pixel despite the weak and orientation-dependent contrast in DIC, as well as the variable blur in such image data caused by vertical specimen movement. In our high numerical aperture, high magnification microscope set-up, this resolution corresponds to 5 nm in object space. In video DIC similar resolution has been reported hitherto only for rotationally symmetric targets such as bead images. The tracker was developed for measuring deflections of clamped microtubules with a freely moving second end. By analysing the thermal fluctuations of such microtubules it was possible to derive their elasticity. The paper describes a filtering scheme for the detection and localization of DIC diffraction line images which represent loci of microtubules. For tracking the movements of the extracted lines we adopted the sum of squared (brightness) differences algorithm from computer vision. The analysis of the fluctuation measurements demonstrates the high sensitivity of this tracking technique in quantifying positional and orientational changes. We derived that the theoretical limit in tracking displacements of such diffraction line images is 1.25 nm, four times below the experimentally verified sensitivity. This indicates that the proposed tracker is still suboptimal. Nevertheless, the tracking precision was sufficient to reveal subtle deviations in the distribution of microtubule deflection from free diffusion. They were induced by pivotal points and multiple positions of relaxation. Also, the results suggest that there were defects in the polymer structure which caused very small but significant bends in the microtubule axis.

Algorithms↗
PubMed2004

Analysis on multiresolution mosaic images.

Image mosaicing is the act of combining two or more images and is used in many applications in computer vision, image processing, and computer graphics. It aims to combine images such that no obstructive boundaries exist around overlapped regions and to create a mosaic image that exhibits as little distortion as possible from the original images. In the proposed technique, the to-be-combined images are first projected into wavelet subspaces. The images projected into the same wavelet space are then blended. Our blending function is derived from an energy minimization model which balances the smoothness around the overlapped region and the fidelity of the blended image to the original images. Experiment results and subjective comparison with other methods are given.

Algorithms↗