Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Pattern Recognition, Automated”

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.

At least 577 records · Page 32Linked to original sources
PubMed2005

Vessel tree reconstruction in thoracic CT scans with application to nodule detection.

Vessel tree reconstruction in volumetric data is a necessary prerequisite in various medical imaging applications. Specifically, when considering the application of automated lung nodule detection in thoracic computed tomography (CT) scans, vessel trees can be used to resolve local ambiguities based on global considerations and so improve the performance of nodule detection algorithms. In this study, a novel approach to vessel tree reconstruction and its application to nodule detection in thoracic CT scans was developed by using correlation-based enhancement filters and a fuzzy shape representation of the data. The proposed correlation-based enhancement filters depend on first-order partial derivatives and so are less sensitive to noise compared with Hessian-based filters. Additionally, multiple sets of eigenvalues are used so that a distinction between nodules and vessel junctions becomes possible. The proposed fuzzy shape representation is based on regulated morphological operations that are less sensitive to noise. Consequently, the vessel tree reconstruction algorithm can accommodate vessel bifurcation and discontinuities. A quantitative performance evaluation of the enhancement filters and of the vessel tree reconstruction algorithm was performed. Moreover, the proposed vessel tree reconstruction algorithm reduced the number of false positives generated by an existing nodule detection algorithm by 38%.

Adult↗
PubMed2006

Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans.

Volumetric growth assessment of pulmonary lesions is crucial to both lung cancer screening and oncological therapy monitoring. While several methods for small pulmonary nodules have previously been presented, the segmentation of larger tumors that appear frequently in oncological patients and are more likely to be complexly interconnected with lung morphology has not yet received much attention. We present a fast, automated segmentation method that is based on morphological processing and is suitable for both small and large lesions. In addition, the proposed approach addresses clinical challenges to volume assessment such as variations in imaging protocol or inspiration state by introducing a method of segmentation-based partial volume analysis (SPVA) that follows on the segmentation procedure. Accuracy and reproducibility studies were performed to evaluate the new algorithms. In vivo interobserver and interscan studies on low-dose data from eight clinical metastasis patients revealed that clinically significant volume change can be detected reliably and with negligible computation time by the presented methods. In addition, phantom studies were conducted. Based on the segmentation performed with the proposed method, the performance of the SPVA volumetry method was compared with the conventional technique on a phantom that was scanned with different dosages and reconstructed with varying parameters. Both systematic and absolute errors were shown to be reduced substantially by the SPVA method. The method was especially successful in accounting for slice thickness and reconstruction kernel variations, where the median error was more than halved in comparison to the conventional approach.

Algorithms↗
PubMed2004

A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography.

Mass segmentation plays a crucial role in computer-aided diagnosis (CAD) systems for classification of suspicious regions as normal, benign, or malignant. In this article we present a robust and automated segmentation technique--based on dynamic programming--to segment mass lesions from surrounding tissue. In addition, we propose an efficient algorithm to guarantee resulting contours to be closed. The segmentation method based on dynamic programming was quantitatively compared with two other automated segmentation methods (region growing and the discrete contour model) on a dataset of 1210 masses. For each mass an overlap criterion was calculated to determine the similarity with manual segmentation. The mean overlap percentage for dynamic programming was 0.69, for the other two methods 0.60 and 0.59, respectively. The difference in overlap percentage was statistically significant. To study the influence of the segmentation method on the performance of a CAD system two additional experiments were carried out. The first experiment studied the detection performance of the CAD system for the different segmentation methods. Free-response receiver operating characteristics analysis showed that the detection performance was nearly identical for the three segmentation methods. In the second experiment the ability of the classifier to discriminate between malignant and benign lesions was studied. For region based evaluation the area Az under the receiver operating characteristics curve was 0.74 for dynamic programming, 0.72 for the discrete contour model, and 0.67 for region growing. The difference in Az values obtained by the dynamic programming method and region growing was statistically significant. The differences between other methods were not significant.

Aged↗
PubMed2003

Automated cardiac MR image segmentation: theory and measurement evaluation.

We present a new approach to magnetic resonance image segmentation with a Gradient-Vector-Flow-based snake applied to selective smoothing filtered images. The system also allows automated image segmentation in the presence of grey scale inhomogeneity, as in cardiac Magnetic Resonance imaging. Removal of such inhomogeneities is a difficult task, but we proved that using non-linear anisotropic diffusion filtering, myocardium edges are selectively preserved. The approach allowed medical data to be automatically segmented in order to track not only endocardium, which is usually a less difficult task, but also epicardium in anatomic and perfusion studies with Magnetic Resonance. The method developed proceeds in three distinct phases: (a) an anisotropic diffusion filtering tool is used to reduce grey scale inhomogeneity and to selectively preserve edges; (b) a Gradient-Vector-Flow-based snake is applied on filtered images to allow capturing a snake from a long range and to move into concave boundary regions; and (c) an automatic procedure based on a snake is used to fit both endocardium and epicardium borders in a multiphase, multislice examination. A good agreement (P<0.001) between manual and automatic data analysis, based on the mean difference+/-SD, was assessed in a pool of 907 cardiac function and perfusion images.

Algorithms↗
PubMed2006

[Quantification of pulmonary emphysema in multislice-CT using different software tools].

PURPOSE: The data records of thin-section MSCT of the lung with approx. 300 images are difficult to use in manual evaluation. A computer-assisted pre-diagnosis can help with reporting. Furthermore, post-processing techniques, for instance, for quantification of emphysema on the basis of three-dimensional anatomical information might be improved and the workflow might be further automated. MATERIALS AND METHODS: The results of 4 programs (Pulmo, Volume, YACTA and PulmoFUNC) for the quantitative analysis of emphysema (lung and emphysema volume, mean lung density and emphysema index) of 30 consecutive thin-section MSCT datasets with different emphysema severity levels were compared. The classification result of the YACTA program for different types of emphysema was also analyzed. RESULTS: Pulmo and Volume have a median operating time of 105 and 59 minutes respectively due to the necessity for extensive manual correction of the lung segmentation. The programs PulmoFUNC and YACTA, which are automated to a large extent, have a median runtime of 26 and 16 minutes, respectively. The evaluation with Pulmo and Volume using 2 different datasets resulted in implausible values. PulmoFUNC crashed with 2 other datasets in a reproducible manner. Only with YACTA could all graphic datasets be evaluated. The lung volume, emphysema volume, emphysema index and mean lung density determined by YACTA and PulmoFUNC are significantly larger than the corresponding values of Volume and Pulmo (differences: Volume: 119 cm(3)/65 cm(3)/1 %/17 HU, Pulmo: 60 cm(3)/96 cm(3)/1 %/37 HU). Classification of the emphysema type was in agreement with that of the radiologist in 26 panlobular cases, in 22 paraseptalen cases and in 15 centrilobular emphysema cases. CONCLUSION: The substantial expenditure of time obstructs the employment of quantitative emphysema analysis in the clinical routine. The results of YACTA and PulmoFUNC are affected by the dedicated exclusion of the tracheobronchial system. These fully automatic tools enable not only fast quantification without manual interaction, but also a reproducible measurement without user dependence.

Adolescent↗
PubMed2005

Figure-ground segmentation from occlusion.

Layered video representations are increasingly popular; see [2] for a recent review. Segmentation of moving objects is a key step for automating such representations. Current motion segmentation methods either fail to segment moving objects in low-textured regions or are computationally very expensive. This paper presents a computationally simple algorithm that segments moving objects, even in low-texture/low-contrast scenes. Our method infers the moving object templates directly from the image intensity values, rather than computing the motion field as an intermediate step. Our model takes into account the rigidity of the moving object and the occlusion of the background by the moving object. We formulate the segmentation problem as the minimization of a penalized likelihood cost function and present an algorithm to estimate all the unknown parameters: the motions, the template of the moving object, and the intensity levels of the object and of the background pixels. The cost function combines a maximum likelihood estimation term with a term that penalizes large templates. The minimization algorithm performs two alternate steps for which we derive closed-form solutions. Relaxation improves the convergence even when low texture makes it very challenging to segment the moving object from the background. Experiments demonstrate the good performance of our method.

Algorithms↗
PubMed2003

Automated generation of a four-dimensional model of the liver using warping and mutual information.

The use of mutual information (MI) based alignment to map changes in liver shape and position from exhale to inhale was investigated. Inhale and exhale CT scans were obtained with intravenous contrast for six patients. MI based alignment using thin-plate spine (TPS) warping was performed between each inhale and exhale image set. An expert radiation oncologist identified corresponding vessel bifurcations on the exhale and inhale CT image and the transformation for identified points was determined. This transformation was then used to determine the accuracy of the MI based alignment. The reproducibility of the vessel bifurcation identification was measured through repeat blinded vessel bifurcation identification. Reproducibility [standard deviation (SD)] in the L/R, A/P, and I/S directions was 0.11, 0.09, and 0.14 cm, respectively. The average absolute difference between the transformation obtained using MI based alignment and the vessel bifurcation in the L/R, A/P, and I/S directions was 0.13 cm (SD=0.10 cm), 0.15 cm (SD=0.12 cm), and 0.15 cm (SD-0.14 cm), respectively. These values are comparable to the reproducibility of bifurcation identification, indicating that MI based alignment using TPS warping is accurate to within measurement error and is a reliable tool to aid in describing deformation that the liver undergoes from the exhale to inhale state.

Algorithms↗
PubMed2005

Automated design of robust discriminant analysis classifier for foot pressure lesions using kinematic data.

In the recent years, the use of motion tracking systems for acquisition of functional biomechanical gait data, has received increasing interest due to the richness and accuracy of the measured kinematic information. However, costs frequently restrict the number of subjects employed, and this makes the dimensionality of the collected data far higher than the available samples. This paper applies discriminant analysis algorithms to the classification of patients with different types of foot lesions, in order to establish an association between foot motion and lesion formation. With primary attention to small sample size situations, we compare different types of Bayesian classifiers and evaluate their performance with various dimensionality reduction techniques for feature extraction, as well as search methods for selection of raw kinematic variables. Finally, we propose a novel integrated method which fine-tunes the classifier parameters and selects the most relevant kinematic variables simultaneously. Performance comparisons are using robust resampling techniques such as Bootstrap 632+ and k-fold cross-validation. Results from experimentations with lesion subjects suffering from pathological plantar hyperkeratosis, show that the proposed method can lead to approximately 96% correct classification rates with less than 10% of the original features.

Adult↗
PubMed2004

An improved strategy for automated electron microscopic tomography.

A prediction-based scheme is proposed and implemented for automated electron microscopic tomography. By assuming that the sample follows a simple geometric rotation and that the optical system can be characterized in terms of an offset between the optical and mechanical axes, it is found that the image movement in the x, y, and z directions due to stage tilt can be dynamically predicted with desired accuracy (15 nm in x-y position and 100 nm in focus). Thus, the microscope optical system (beam/image shift and focus) can be automatically adjusted to compensate for the predicted image movement prior to taking the projected image at each tilt angle. As a consequence, it is not necessary to either record additional images for tracking and focusing during the course of data collections or to spend valuable setup time in a lengthy pre-calibration of stage motions. Furthermore, this scheme is also found to tolerate a significant degree of non-eucentricity and to be quite robust in the collection of regular and cryo low-dose images on thin or thick samples even at magnifications greater than 62000x and angular step as large as 10 degrees. For interested users the software can be freely downloaded for non-profit use at http://www.msg.ucsf.edu/tomography.

Animals↗
PubMed2005

Automatic selection of parameters for vessel/neurite segmentation algorithms.

An automated method is presented for selecting optimal parameter settings for vessel/neurite segmentation algorithms using the minimum description length principle and a recursive random search algorithm. It trades off a probabilistic measure of image-content coverage against its conciseness. It enables nonexpert users to select parameter settings objectively, without knowledge of underlying algorithms, broadening the applicability of the segmentation algorithm, and delivering higher morphometric accuracy. It enables adaptation of parameters across batches of images. It simplifies the user interface to just one optional parameter and reduces the cost of technical support. Finally, the method is modular, extensible, and amenable to parallel computation. The method is applied to 223 images of human retinas and cultured neurons, from four different sources, using a single segmentation algorithm with eight parameters. Improvements in segmentation quality compared to default settings using 1000 iterations ranged from 4.7%-21%. Paired t-tests showed that improvements are statistically significant (p < 0.0005). Most of the improvement occurred in the first 44 iterations. Improvements in description lengths and agreement with the ground truth were strongly correlated (p = 0.78).

Algorithms↗
PubMed2003

Automated Abdominal Aortic Aneurysm segmentation using MATLAB.

Abdominal Aortic Aneurysms (AAA) are the 10th leading cause of death in older men. It is estimated that about 5% of men over 50 have AAA but the prevalence and risk of death due to rupture increase with age to estimated 10% prevalence and almost 1% of male deaths over the age of 65. AAA is defined as a focal dilation of the artery at least 50% larger than the normal diameter. If the defect is not surgically repaired prior to rupture, the mortality is about 80%. The role of clotted blood (thrombus) lining the walls of the AAA has been speculated to play a role in aneurysm expansion. Although aneurysm diameter is easily measured from a CT scan, accurately measuring the relative amount of clotted blood (thrombus load) cannot be readily done with a ruler. This paper presents a process to segment the relative thrombus area and aneurysmal area from CT images using computer algorithms. We have developed an image processing based technique, using MATLAB, to aid in the detection of a threatening AAA condition. This technique uses segmentation-based techniques to extract the desired data. The process of segmentation involves several steps to obtain desirable results. This algorithm uses primarily thresholding techniques, erosion, and dilation filters to segment the wall and determine the bounds of the aorta; then segmentation is done to enhance and isolate areas of interest.

Algorithms↗
PubMed2006

Improved discrimination of breast lesions using selective sampling of segmented MR images.

OBJECTIVE: The aim of this work is to examine if the specificity of differentiation between malignant and benign tumours can be improved by retrospectively examining lesion-extracted distributions. A semi-automated method for selecting a region-of-interest (ROI) is described. A new histogram segmentation approach for sampling pharmacokinetic breast maps of transfer uptake is defined in order to assign classification variables for the lesion. METHOD: Fifty exchange rate parameter maps were extracted from 49 subjects and retrospectively analysed. Distributions obtained from semi-automatically delineated ROIs were subdivided into ten overlapping segments. Parameters were extracted from each segment which effectively presents a new pixel intensity sampling strategy. Mann-Whitney non-parametric tests and ROC curves were generated. RESULTS: Correlation exists between mean parameter values drawn from semi-automatically or manually drawn ROIs. However, the former yield higher specificity values as applied to this subset of enhancing benign lesions. Segmenting the exchange rate parameter histogram allows the identification of which part of the distribution correlates most with tumour type. Significant improvement in specificity is obtained when using half the pixels within the ROI. CONCLUSION: Improved specificity values are obtained by a new method of selecting the differentiation parameters which relies on intensity rather than spatial segmentation. Only half the pixels available within the ROI contributed to the measured classification parameters.

Adult↗
PubMed2006

A fully automated method for lung nodule detection from postero-anterior chest radiographs.

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.

Algorithms↗
PubMed2003

Landmark detection in the chest and registration of lung surfaces with an application to nodule registration.

We developed an automated system for registering computed tomography (CT) images of the chest temporally. Our system detects anatomical landmarks, in particular, the trachea, sternum and spine, using an attenuation-based template matching approach. It computes the optimal rigid-body transformation that aligns the corresponding landmarks in two CT scans of the same patient. This transformation then provides an initial registration of the lung surfaces segmented from the two scans. The initial surface alignment is refined step by step in an iterative closest-point (ICP) process. To establish the correspondence of lung surface points, Elias' nearest neighbor algorithm was adopted. Our method improves the processing time of the original ICP algorithm from O(kn log n) to O(kn), where k is the number of iterations and n the number of surface points. The surface transformation is applied to align nodules in the initial CT scan with nodules in the follow-up scan. For 56 out of 58 nodules in the initial CT scans of 10 patients, nodule correspondences in the follow-up scans are established correctly. Our methods can therefore potentially facilitate the radiologist's evaluation of pulmonary nodules on chest CT for interval growth.

Algorithms↗
PubMed2006

Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification.

We present a method for automated segmentation of the vasculature in retinal images. The method produces segmentations by classifying each image pixel as vessel or nonvessel, based on the pixel's feature vector. Feature vectors are composed of the pixel's intensity and two-dimensional Gabor wavelet transform responses taken at multiple scales. The Gabor wavelet is capable of tuning to specific frequencies, thus allowing noise filtering and vessel enhancement in a single step. We use a Bayesian classifier with class-conditional probability density functions (likelihoods) described as Gaussian mixtures, yielding a fast classification, while being able to model complex decision surfaces. The probability distributions are estimated based on a training set of labeled pixels obtained from manual segmentations. The method's performance is evaluated on publicly available DRIVE (Staal et al., 2004) and STARE (Hoover et al., 2000) databases of manually labeled images. On the DRIVE database, it achieves an area under the receiver operating characteristic curve of 0.9614, being slightly superior than that presented by state-of-the-art approaches. We are making our implementation available as open source MATLAB scripts for researchers interested in implementation details, evaluation, or development of methods.

Algorithms↗
PubMed2005

Automated identification of axonal growth cones in time-lapse image sequences.

The isolation and purification of axon guidance molecules has enabled in vitro studies of the effects of axon guidance molecule gradients on numerous neuronal cell types. In a typical experiment, cultured neurons are exposed to a chemotactic gradient and their growth is recorded by manual identification of the axon tip position from two or more micrographs. Detailed and statistically valid quantification of axon growth requires evaluation of a large number of neurons at closely spaced time points (e.g. using a time-lapse microscopy setup). However, manual tracing becomes increasingly impractical for recording axon growth as the number of time points and/or neurons increases. We present a software tool that automatically identifies and records the axon tip position in each phase-contrast image of a time-lapse series with minimal user involvement. The software outputs several quantitative measures of axon growth, and allows users to develop custom measurements. For, example analysis of growth velocity for a dissociated E13 mouse cortical neuron revealed frequent extension and retraction events with an average growth velocity of 0.05 +/- 0.14 microm/min. Comparison of software-identified axon tip positions with manually identified axon tip positions shows that the software's performance is indistinguishable from that of skilled human users.

Animals↗
PubMed2006

A computer-aided method to expedite the evaluation of prognosis for childhood acute lymphoblastic leukemia.

This study presented a fully-automated computer-aided method (scheme) to detect metaphase chromosomes depicted on microscopic digital images, count the total number of chromosomes in each metaphase cell, compute the DNA index, and correlate the results to the prognosis of childhood acute lymphoblastic leukemia (ALL). The computer scheme first uses image filtering, threshold, and labeling algorithms to segment and count the number of the suspicious "chromosome," and then computes a feature vector for each "detected chromosome." Based on these features, a knowledge-based classifier is used to eliminate those "non-chromosome" objects (i.e., inter-phase cells, stain debris, and other kinds of background noises). Due to the possible overlap of the chromosomes, a classification criterion was used to identify the overlapped chromosomes and adjust the initially counted number of the total chromosomes in each image. In this preliminary study with 60 testing images (depicting metaphase chromosome cells) acquired from three pediatric patients, the computer scheme generated results matched with the diagnostic results provided by the clinical cytogeneticists. The results demonstrated the feasibility or potential of using a computerized method to replace the tedious and the reader-dependent diagnostic methods commonly used in genetic laboratories to date.

Algorithms↗
PubMed2003

Quantitative computerized analysis of diffuse lung disease in high-resolution computed tomography.

An automated computerized scheme has been developed for the detection and characterization of diffuse lung diseases on high-resolution computed tomography (HRCT) images. Our database consisted of 315 HRCT images selected from 105 patients, which included normal and abnormal slices related to six different patterns, i.e., ground-glass opacities, reticular and linear opacities, nodular opacities, honeycombing, emphysematous change, and consolidation. The areas that included specific diffuse patterns in 315 HRCT images were marked by three radiologists independently on the CRT monitor in the same manner as they commonly describe in their radiologic reports. The areas with a specific pattern, which three radiologists marked independently and consistently as the same patterns, were used as "gold standard" for specific abnormal opacities in this study. The lungs were first segmented from the background in each slice by use of a morphological filter and a thresholding technique, and then divided into many contiguous regions of interest (ROIs) with a 32x32 matrix. Six physical measures which were determined in each ROI included the mean and the standard deviation of the CT value, air density components, nodular components, line components, and multilocular components. Artificial neural networks (ANNs) were employed for distinguishing between seven different patterns which included normals and six patterns associated with diffuse lung disease. The sensitivity of this computerized method for a detection of the six abnormal patterns in each ROI was 99.2% (122/123) for ground-glass opacities, 100% (15/15) for reticular and linear opacities, 88.0% (132/150) for nodular opacities, 100% (98/98) for honeycombing, 95.8% (369/385) for emphysematous change, and 100% (43/43) for consolidation. The specificity in detecting a normal ROI was 88.1% (940/1067). This computerized method may be useful in assisting radiologists in their assessment of diffuse lung disease in HRCT images.

Algorithms↗