PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Automated image segmentation”

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 325 records · Page 18Linked to original sources
PubMed1998

Automatic segmentation of gadolinium-enhanced multiple sclerosis lesions.

Automatic detection and quantitation of contrast-enhanced lesions on MRI is expected to be useful in characterizing the disease state in multiple sclerosis (MS). The enhancing structures such as cerebral vasculature and regions with no blood-brain barrier complicate automated analysis of lesion enhancement. A pulse sequence that incorporates both stationary and marching saturation bands and gradient dephasing is described for suppressing the enhancements within the cerebral vasculature. A postprocessing technique based on automatic image segmentation is implemented for eliminating enhancing structures such as choroid plexus. All MS lesions larger than 5 mm3 have been successfully identified. The automated analysis produced no false-positives or false-negative lesions above this volume in 13 patients with MS who were evaluated using the acquisition and evaluation techniques described.

Algorithms↗
PubMed2004

Computerized characterization of breast masses on three-dimensional ultrasound volumes.

We are developing computer vision techniques for the characterization of breast masses as malignant or benign on radiologic examinations. In this study, we investigated the computerized characterization of breast masses on three-dimensional (3-D) ultrasound (US) volumetric images. We developed 2-D and 3-D active contour models for automated segmentation of the mass volumes. The effect of the initialization method of the active contour on the robustness of the iterative segmentation method was studied by varying the contour used for its initialization. For a given segmentation, texture and morphological features were automatically extracted from the segmented masses and their margins. Stepwise discriminant analysis with the leave-one-out method was used to select effective features for the classification task and to combine these features into a malignancy score. The classification accuracy was evaluated using the area Az under the receiver operating characteristic (ROC) curve, as well as the partial area index Az(0.9), defined as the relative area under the ROC curve above a sensitivity threshold of 0.9. For the purpose of comparison with the computer classifier, four experienced breast radiologists provided malignancy ratings for the 3-D US masses. Our dataset consisted of 3-D US volumes of 102 biopsied masses (46 benign, 56 malignant). The classifiers based on 2-D and 3-D segmentation methods achieved test Az values of 0.87+/-0.03 and 0.92+/-0.03, respectively. The difference in the Az values of the two computer classifiers did not achieve statistical significance. The Az values of the four radiologists ranged between 0.84 and 0.92. The difference between the computer's Az value and that of any of the four radiologists did not achieve statistical significance either. However, the computer's Az(0.9) value was significantly higher than that of three of the four radiologists. Our results indicate that an automated and effective computer classifier can be designed for differentiating malignant and benign breast masses on 3-D US volumes. The accuracy of the classifier designed in this study was similar to that of experienced breast radiologists.

Algorithms↗
PubMed1997

Absence of co-localized glutamic acid decarboxylase and neuropeptides in noradrenergic axons of the rat spinal cord.

Patterns of co-localization of immunoreactivity for dopamine beta-hydroxylase (the synthetic enzyme for noradrenaline) and glutamic acid decarboxylase (the synthetic enzyme for GABA) or each one of six neuropeptides (neuropeptide Y, substance P, met-enkephalin, galanin, dynorphin A and somatostatin) were investigated with dual-colour confocal laser scanning microscopy in axons of cervical, thoracic and lumbar spinal segments of six adult rats. Four regions of the grey matter were studied (laminae I-II, V, IX and X) and, in thoracic segments, the intermediolateral cell column was also examined. The extent of co-localization was estimated by direct assessment of merged pairs of optical sections and by automated image analysis. Significant co-localization was found for neuropeptide Y in axons of the intermediolateral cell column of thoracic segments and in lamina X of cervical and thoracic segments. None of the other peptides or glutamic acid decarboxylase were found to coexist at significant levels with dopamine beta-hydroxylase and hence it is likely that this group of neuropeptides and GABA are not co-transmitters of bulbospinal noradrenergic axons in the rat.

Animals↗
PubMedDate not supplied

Weekly alcohol consumption, brain atrophy, and white matter hyperintensities in a community-based sample aged 60 to 64 years.

OBJECTIVE: The objective of this study was to determine the association between weekly alcohol consumption and brain atrophy in adults aged 60 to 64 years. METHODS: Brain magnetic resonance imaging scans from 385 adults recruited through a community survey were analyzed. Automated segmentation and manual tracing methods were used to obtain brain subvolumes and automated methods were used to obtain quantification and localization of white matter hyperintensities. Visual measures of cortical atrophy were obtained as were data on health and lifestyle factors. Alcohol consumption was assessed with the Alcohol Use Disorders Identification Test. RESULTS: In men, weekly alcohol consumption had a positive linear association with ventricular volume and gray matter and a negative linear association with white matter. In women, weekly alcohol consumption had a nonlinear relationship with cerebrospinal fluid and white matter. Alcohol consumption was not associated with white matter hyperintensities, corpus callosum size, hippocampal or amygdala volumes in analyses adjusting for confounding variables. CONCLUSION: An association between alcohol consumption and brain atrophy is evident at the population level. In women, detrimental effects of alcohol on the brain appear to occur at lower levels of consumption. It remains possible that low levels of alcohol consumption have neuroprotective benefits but is clear that high levels of consumption are detrimental.

Alcohol Drinking↗
PubMed1993

CT and SPECT image registration and fusion for spatial localization of metastatic processes using radiolabeled monoclonals.

The fusion of computed tomography (CT) and single-photon emission computerized tomography (SPECT) antibody images can enhance the information provided by either single modality by providing precise anatomical-functional correlation. Functional abnormalities seen on low resolution SPECT antibody images can be precisely located with specific anatomic structures seen in high resolution CT images. External fiducials located on each image modality aid in the automated registration, alignment and matching of CT and SPECT antibody images. The potential benefits of multimodal fusion include (A) the discrimination of more subtle activity peaks using anatomic organ segmentation, (B) temporal discrimination of recurrent disease, (C) assessment of residual activity post-surgery and (D) automated localization of significant focal activity. In addition, the correlation of function with anatomy may be used to establish the physiologic status of ambiguously identified objects in the anatomic image.

Aged↗
PubMed2000

Dobutamine magnetic resonance imaging as a predictor of myocardial functional recovery after revascularisation.

OBJECTIVE: To assess the use of dobutamine magnetic resonance imaging (MRI) as a preoperative predictor of myocardial functional recovery after revascularisation, comparing wall motion and radial wall thickening analyses by observer and semi-automated edge detection. PATIENTS: 25 men with multivessel coronary disease and resting wall motion abnormalities were studied with preoperative rest and stress MRI. MAIN OUTCOME MEASURES: Observer analysis for radial wall thickening was compared with a normal range, while wall motion analysis used a standard four point scale. Semi-automated analysis was performed using an edge detection algorithm. Segments displaying either improved or worsened thickening or motion with dobutamine were considered viable. Postoperative rest images were performed 3-6 months after coronary artery bypass grafting (CABG) for comparison. RESULTS: For observer analysis the values for sensitivity and specificity were 50% and 72% for wall motion, with respective values of 50% and 68% for thickening. With semi-automated edge detection the figures for motion were 60% and 73%, with corresponding values of 79% and 58% for thickening. Combining thickening and motion for the semi-automated method to describe any change in segmental function yielded a sensitivity of 71% and specificity of 70%. CONCLUSIONS: Dobutamine MRI is a reasonably good predictor of myocardial functional recovery after CABG. The use of semi-automated edge detection analysis improved results.

Aged↗
PubMed2006

Automated extraction of fine features of kinetochore microtubules and plus-ends from electron tomography volume.

Kinetochore microtubules (KMTs) and the associated plus-ends have been areas of intense investigation in both cell biology and molecular medicine. Though electron tomography opens up new possibilities in understanding their function by imaging their high-resolution structures, the interpretation of the acquired data remains an obstacle because of the complex and cluttered cellular environment. As a result, practical segmentation of the electron tomography data has been dominated by manual operation, which is time consuming and subjective. In this paper, we propose a model-based automated approach to extracting KMTs and the associated plus-ends with a coarse-to-fine scale scheme consisting of volume preprocessing, microtubule segmentation and plus-end tracing. In volume preprocessing, we first apply an anisotropic invariant wavelet transform and a tube-enhancing filter to enhance the microtubules at coarse level for localization. This is followed with a surface-enhancing filter to accentuate the fine microtubule boundary features. The microtubule body is then segmented using a modified active shape model method. Starting from the segmented microtubule body, the plus-ends are extracted with a probabilistic tracing method improved with rectangular window based feature detection and the integration of multiple cues. Experimental results demonstrate that our automated method produces results comparable to manual segmentation but using only a fraction of the manual segmentation time.

Algorithms↗
PubMed2002

An integrated system for feature evaluation of 3D images of a tissue specimen.

In this article we have proposed an integrated system for measurement of important features from 3D tissue images. We propose a segmentation technique, where we combine several methods to achieve a good degree of automation. Important histological and cytological three-dimensional features and strategies to measure them are described.

Algorithms↗
PubMed2002

A fully automated method for tissue segmentation and CSF-correction of proton MRSI metabolites corroborates abnormal hippocampal NAA in schizophrenia.

In this report, we describe the implementation and application of a fully automated segmentation routine using SPM99 algorithms and MATLAB for clinical Magnetic Resonance Spectroscopic Imaging (MRSI) studies. By segmenting high-resolution 3-D image data and coregistering the results to the spatial localizer slices of a spectroscopy examination, the program offers the possibility to easily calculate segmentation maps for a large variety of MRSI experiments. The segmented data are corrected for the individual point-spread function, slice and VOI profiles for measurement sequences with selective pulses as well as for the chemical shifts of different metabolites. The new method was applied to investigate discrete hippocampal metabolite abnormalities in a small sample of schizophrenic patients in comparison to healthy controls (15 patients, 15 controls). Only after correction was the N-acetyl-aspartate (NAA) signal significantly lower in patients compared to controls. No differences were found for the corrected signals from the creatine/phosphocreatine (Cr) or choline-containing compounds (Ch). These results are in good agreement with neuropathological and previous MR spectroscopy studies of the hippocampus in schizophrenic patients.

Adult↗
PubMed2006

MChip: a tool for influenza surveillance.

The design and characterization of a low-density microarray for subtyping influenza A is presented. The microarray consisted of 15 distinct oligonucleotides designed to target only the matrix gene segment of influenza A. An artificial neural network was utilized to automate microarray image interpretation. The neural network was trained to recognize fluorescence image patterns for 68 known influenza viruses and subsequently used to identify 53 unknowns in a blind study that included 39 human patient samples and 14 negative control samples. The assay exhibited a clinical sensitivity of 95% and clinical specificity of 92%.

Automation↗
PubMed2000

Ultra-rare-event detection performance of a custom scanning cytometer on a model preparation of fetal nRBCs.

BACKGROUND: The performance of a fully automated scanning cytometer incorporating previously reported high-precision autofocus and accurate image segmentation was evaluated for the detection of "ultra-rare" cells using a model of fetal nucleated red blood cells (fnRBCs) in the maternal circulation. These distinctive scanning cytometry techniques were expected to markedly improve sensitivity and specificity. METHODS: Normal adult blood and fetal red blood cells were stained with fluorescein isothiocyanate-conjugated anti-fetal hemoglobin and 4,6-diamidino-2-phenylindole, a nuclear dye. Adult cells were spiked with fetal cells to create ratios of about 1 fnRBC in 10(7) nucleated cells and deposited in monolayers on slides using centrifugal cytology. Rare-event performance parameters were reviewed, formalized, and applied to test the new instrument using this cell model. RESULTS: Fifteen slides were analyzed to establish performance by comparison with manual detection, and four sets of four slides each were then scanned to explore the limit of detection. Results were an average sensitivity of 91%, an average specificity error of 12.3 false-positives per million cells, and repeatability of 100% at a cell analysis rate of 862 Hz. With addition of a quick interactive step subsequent to scanning, the false-positive rate dropped to a total of only one artifact over the 15 experiments. The instrument succeeded at locating 1 fnRBC in 20 million adult cells, the lowest limit of detection tested. CONCLUSION: This consistently high performance, coupled with the capability of scanning arbitrarily large numbers of cells, validates the considerable potential of precise high-speed autofocus and accurate real-time image segmentation for ultra-rare event detection.

Adult↗
PubMed1998

Anatomic region-based dynamic range compression for chest radiographs using warping transformation of correlated distribution.

The purpose of this paper is to investigate the effectiveness of our novel dynamic range compression (DRC) for chest radiographs. The purpose of DRC is to compress the gray scale range of the image when using narrow dynamic range viewing systems such as monitors. First, an automated segmentation method was used to detect the lung region. The combined region of mediastinum, heart, and subdiaphragm was defined based on the lung region. The correlated distributions, between a pixel value and its neighboring averaged pixel value, for the lung region and the combined region were calculated. According to the appearance of overlapping of two distributions, the warping function was decided. After pixel values were warped, the pixel value range of the lung region was compressed while preserving the detail information, because the warping function compressed the range of the averaged pixel values while preserving the pixel value range for the pixels which had had the same averaged pixel value. The performance was evaluated with our criterion function which was the contrast divided by the moment, where the contrast and the moment represent the sum of the differences between the pixel values and the averaged values of eight pixels surrounding that pixel, and the sum of the differences between the pixel values and the averaged value of all pixels in the region-of-interest, respectively. For 71 screening chest images from Johns Hopkins University Hospital (Baltimore, MD), this method improved our criterion function at 11.7% on average. The warping transformation algorithm based on the correlated distribution was effective in compressing the dynamic range while simultaneously preserving the detail information.

Humans↗
PubMed1998

Left-ventricle boundary detection from nuclear medicine images.

We present here a new algorithm for segmentation of nuclear medicine images to detect the left-ventricle (LV) boundary. In this article, other image segmentation techniques, such as edge detection and region growing, are also compared and evaluated. In the edge detection approach, we explored the relationship between the LV boundary characteristics in nuclear medicine images and their radial orientations: we observed that no single brightness function (eg, maximum of first or second derivative) is sufficient to identify the boundary in every direction. In the region growing approach, several criteria, including intensity change, gradient magnitude change, gradient direction change, and running mean differences, were tested. We found that none of these criteria alone was sufficient to successfully detect the LV boundary. Then we proposed a simple but successful region growing method--Contour-Modified Region Growing (CMRG). CMRG is an easy-to-use, robust, and rapid image segmentation procedure. Based on our experiments, this method seems to perform quite well in comparison to other automated methods that we have tested because of its ability to handle the problems of both low signal-to-noise ratios (SNR) as well as low image contrast without any assumptions about the shape of the left ventricle.

Heart Ventricles↗
PubMed2001

Computerized image analysis: estimation of breast density on mammograms.

An automated image analysis tool is being developed for the estimation of mammographic breast density. This tool may be useful for risk estimation or for monitoring breast density change in prevention or intervention programs. In this preliminary study, a data set of 4-view mammograms from 65 patients was used to evaluate our approach. Breast density analysis was performed on the digitized mammograms in three stages. First, the breast region was segmented from the surrounding background by an automated breast boundary-tracking algorithm. Second, an adaptive dynamic range compression technique was applied to the breast image to reduce the range of the gray level distribution in the low frequency background and to enhance the differences in the characteristic features of the gray level histogram for breasts of different densities. Third, rule-based classification was used to classify the breast images into four classes according to the characteristic features of their gray level histogram. For each image, a gray level threshold was automatically determined to segment the dense tissue from the breast region. The area of segmented dense tissue as a percentage of the breast area was then estimated. To evaluate the performance of the algorithm, the computer segmentation results were compared to manual segmentation with interactive thresholding by five radiologists. A "true" percent dense area for each mammogram was obtained by averaging the manually segmented areas of the radiologists. We found that the histograms of 6% (8 CC and 8 MLO views) of the breast regions were misclassified by the computer, resulting in poor segmentation of the dense region. For the images with correct classification, the correlation between the computer-estimated percent dense area and the "truth" was 0.94 and 0.91, respectively, for CC and MLO views, with a mean bias of less than 2%. The mean biases of the five radiologists' visual estimates for the same images ranged from 0.1% to 11%. The results demonstrate the feasibility of estimating mammographic breast density using computer vision techniques and its potential to improve the accuracy and reproducibility of breast density estimation in comparison with the subjective visual assessment by radiologists.

Biophysical Phenomena↗
PubMed1998

Ovarian ultrasound image analysis: follicle segmentation.

Ovarian ultrasound is an effective tool in infertility treatment. Repeated measurements of the size and shape of follicles over several days are the primary means of evaluation by physicians. Currently, follicle wall segmentation is achieved by manual tracing which is time consuming and susceptible to inter-operator variation. An automated method for follicle wall segmentation is reported that uses a four-step process based on watershed segmentation and knowledge-based graph search algorithm which utilizes priori information about follicle structure for inner and outer wall detection. The automated technique was tested on 36 ultrasonographic images of women's ovaries. Validation against manually traced borders has shown good correlation of manually defined and computer-determined area measurements (R2 = 0.85 - 0.96). The border positioning errors were small: 0.63+/-0.36 mm for inner border and 0.67+/-0.41 mm for outer border detection. The use of watershed segmentation and graph search methods facilitates fast, accurate inner and outer border detection with minimal user-interaction.

Algorithms↗
PubMed2004

Direct neural network application for automated cell recognition.

BACKGROUND: Automated cell recognition from histologic images is a very complex task. Traditionally, the image is segmented by some methods chosen to suit the image type, the objects are measured, and then a classifier is used to determine cell type from the object's measurements. Different classifiers have been used with reasonable success, including neural networks working with data from morphometric analysis. METHODS: Image data of cells were input directly into neural networks to determine the feasibility of direct classification by using pixel intensity information. Several types of neural network and their ability to work with cells in a complex patterned background were assessed for a variety of images and cell types and for the accuracy of classification. RESULTS: Inflammatory cells from animal biomaterial implants in rabbit paravertebral muscle were imaged in histologic sections. Simple, three-layer, fully connected, back-propagation neural networks and four-layer networks with two layers of a shared-weights neural network were most successful at classifying the cells from the images, with 97% and 98% correct recognition rates, respectively. CONCLUSIONS: The high accuracy recognition rate shows the potential for direct classification of visual image pixel data by neural networks.

Animals↗
PubMed1997

Verification of radiosurgery target point alignment with an electronic portal imaging device (EPID).

A procedure has been developed using an electronic portal imaging device (EPID) to verify that the center of a patient's lesion is aligned with the center of a treatment cone prior to treatment in a linac-based stereotactic radiosurgery procedure. The coordinates of the lesion center are set on the Brown-Roberts-Wells phantom base using a target simulator. A 3 mm tungsten ball, mounted on the target simulator, is used as the reference point for the planned isocenter. The target simulator is then attached to an adapter mounted on the linac couch, and an EPID image of the simulated target is acquired. The center of the circular-shaped radiation field is calculated from the centroid of the segmented EPID image, and the center of the tungsten ball is identified by an automated computer search algorithm. A summation filter is used to find the position of the lowest radiation intensity coincident with the center of the ball. The alignment error is defined as the difference between the center of the radiation field and the center of the ball. The accuracy of this method was tested and found to be within 0.2 mm. The advantage of the EPID-based procedure is that it can give quantitative offset values quickly for immediate readjustment. We have found that the method is also a convenient tool for testing room laser alignment and the accuracy of the treatment cones.

Algorithms↗