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 37 records · Page 2Linked to original sources

PubMed2002

Confocal DNA cytometry: a contour-based segmentation algorithm for automated three-dimensional image segmentation.

BACKGROUND: Confocal laser scanning microscopy (CLSM) presents the opportunity to perform three-dimensional (3D) DNA content measurements on intact cells in thick histological sections. So far, these measurements have been performed manually, which is quite time-consuming. METHODS: In this study, an intuitive contour-based segmentation algorithm for automatic 3D CLSM image cytometry of nuclei in thick histological sections is presented. To evaluate the segmentation algorithm, we measured the DNA content and volume of human liver and breast cancer nuclei in 3D CLSM images. RESULTS: A high percentage of nuclei could be segmented fully automatically (e.g., human liver, 92%). Comparison with (time-consuming) interactive measurements on the same CLSM images showed that the results were well correlated (liver, r = 1.00; breast, r = 0.92). CONCLUSIONS: Automatic 3D CLSM image cytometry enables measurement of volume and DNA content of large numbers of nuclei in thick histological sections within an acceptable time. This makes large-scale studies feasible, whereby the advantages of CLSM can be exploited fully. The intuitive modular segmentation algorithm presented in this study detects and separates overlapping objects, also in two-dimensional (2D) space. Therefore, this algorithm may also be suitable for other applications.

Algorithms↗

PubMed2001

[Automated image analysis of lateral roentgen images of the spine using anatomic models].

PURPOSE: Development of a software for fully automated image analysis of lateral lumbar spine X-rays. MATERIAL AND METHOD: Using the concept of active shape models, we developed a software that produces a form model of the lumbar spine from lateral lumbar spine radiographs and runs an automated image segmentation. This model is able to detect lumbar vertebrae automatically after the filtering of digitized X-ray images. The model was trained with 20 lateral lumbar spine radiographs with no pathological findings before we evaluated the software with 30 further X-ray images which were sorted by image quality ranging from one (best) to three (worst). There were 10 images for each quality. RESULTS: Image recognition strongly depended on image quality. In group one 52 and in group two 51 out of 60 vertebral bodies including the sacrum were recognized, but in group three only 18 vertebral bodies were properly identified. CONCLUSION: Fully automated and reliable recognition of vertebral bodies from lateral spine radiographs using the concept of active shape models is possible. The precision of this technique is limited by the superposition of different structures. Further improvements are necessary. Therefore standardized image quality and enlargement of the training data set are required.

Humans↗

PubMed1991

Automated fluorescence image cytometry. DNA quantification and detection of chlamydial infections.

Digitized fluorescence microscopy in conjunction with automated image segmentation is a promising approach for screening clinical specimens quickly and reliably. This paper describes the hardware and software of a prototype image-based cytometer that can identify fluorescent objects, discriminate true objects from artifacts and divide overlapping pairs of objects. The use of this image cytometer is discussed for: (1) the measurement of the DNA ploidy distribution of isolated mature rat liver nuclei labeled with 4',6-diamidine-2-phenylindole; (2) the comparison of the DNA ploidy distributions of the same samples measured by image cytometry (ICM) and flow cytometry (FCM); and (3) the quantification of chlamydial infection by double labeling cells with antichlamydiae antibody and Hoechst 33258 for nuclear DNA analysis. Ploidy distributions measured by the automated image cytometer compared favorably to those obtained by FCM. All pairs of overlapping nuclei were automatically detected by an additional computer algorithm, and those pairs that were clearly more than one nucleus by visual inspection were correctly divided. The irregular morphology of the chlamydiae-infected cells meant that 26% of them were not correctly identified in the fluorescein-stained images (as judged by manual inspection), but all cells were nevertheless detected correctly from the images of the Hoechst-stained samples. Automated fluorescence ICM yielded results similar to those obtained with FCM and had the additional benefit of maintaining cell and tissue architecture while preserving the opportunity for subsequent manual inspection of the specimen.

Algorithms↗

PubMed2002

Genetic contributions to regional variability in human brain structure: methods and preliminary results.

Twin studies provide one approach for investigating and partitioning genetic and environmental contributions to phenotypic variability in human brain structure. Previous twin studies have found that cerebral volume, hemispheric volume, ventricular volume, and cortical gyral pattern variability were heritable. We investigated the contributions of genetic and environmental factors to both global (brain volume and lateral ventricular volume) and regional (parcellated gray matter) variability in brain structure. We examined MR images from 10 pairs of healthy monozygotic and 10 pairs of same-sex dizygotic twins. Regional gray matter volume was estimated by automated image segmentation, transformation to standard space, and parcellation using a digital atlas. Heritability was estimated by path analysis. Estimated heritability for brain volume variability was high (0.66; 95% confidence interval 0.17, 1.0) but the major effects on lateral ventricular volume variability were common and unique environmental factors. We constructed a map of regional brain heritability and found large genetic effects shared in common between several bilateral brain regions, particularly paralimbic structures and temporal-parietal neocortex. We tested three specific hypotheses with regard to the genetic control of brain variability: (i) that the strength of the genetic effect is related to gyral ontogenesis, (ii) that there is greater genetic control of left than of right hemisphere variability, and (iii) that random or fluctuating asymmetry in bilateral structures is not heritable. We found no evidence in support of the first two hypotheses, but our results were consistent with the third hypothesis. Finally, we used principal component (PC) analysis of the genetic correlation matrix, to identify systems of anatomically distributed gray matter regions which shared major genetic effects in common. Frontal and parietal neocortical areas loaded positively on the first PC; some paralimbic and limbic areas loaded negatively. Bilateral insula, some frontal regions, and temporal neocortical regions functionally specialized for audition and language loaded strongly on the second PC. We conclude that large samples are required for powerful investigation of genetic effects in imaging data from twins. However, these preliminary re. sults suggest that genetic effects on structure of the human brain are regionally variable and predominantly symmetric in paralimbic structures and lateral temporal cortex.

Algorithms↗

PubMed2006

Automated local bright feature image analysis of nuclear protein distribution identifies changes in tissue phenotype.

The organization of nuclear proteins is linked to cell and tissue phenotypes. When cells arrest proliferation, undergo apoptosis, or differentiate, distribution of nuclear proteins changes. Conversely, forced alteration of the distribution of nuclear proteins modifies cell phenotype. Immunostaining and fluorescence microscopy have been critical for such findings. However, there is increasing need for quantitative analysis of nuclear protein distribution to decipher epigenetic relationships between nuclear structure and cell phenotype and to unravel the mechanisms linking nuclear structure and function. We have developed imaging methods to quantify the distribution of fluorescently stained nuclear protein NuMA in different mammary phenotypes obtained using 3D cell culture. Automated image segmentation of DAPI-stained nuclei was generated to isolate thousands of nuclei from 3D confocal images. Prominent features of fluorescently stained NuMA were detected by using a previously undescribed local bright feature analysis technique, and their normalized spatial density was calculated as a function of the distance from the nuclear perimeter to its center. The results revealed marked changes in the distribution of the density of NuMA bright features when nonneoplastic cells underwent phenotypically normal acinar morphogenesis. Conversely, we did not detect any reorganization of NuMA during formation of tumor nodules by malignant cells. Importantly, the analysis also discriminated proliferating nonneoplastic from proliferating malignant cells, suggesting that these imaging methods are capable of identifying alterations linked not only to the proliferation status but also to the malignant character of cells. We believe that this quantitative analysis will have additional applications for classifying normal and pathological tissues.

Antigens, Nuclear↗

PubMed2000

Combining high-performance computing and networking for advanced 3-D cardiac imaging.

This paper deals with the integration of a powerful parallel computer-based image analysis and visualization system for cardiology into a hospital information system. Further services are remote access to the hospital Web server through an internet network. The visualization system includes dynamic three-dimensional representation of two types of medical images (e.g., magnetic resonance and nuclear medicine) as well as two images in the same modality (e.g., basal versus stress images). A series of software tools for quantitative image analysis developed for supporting diagnosis of cardiac disease are also available, including automated image segmentation and quantitative time evaluation of left ventricular volumes and related indices during cardiac cycle, myocardial mass, and myocardial perfusion indices. The system has been tested both at a specialized cardiologic center and for remote consultation in diagnosis of cardiac disease by using anatomical and perfusion magnetic resonance images.

Cardiac Output↗

PubMedDate not supplied

Topographic study of sudanophilic lesions in cholesterol-fed minipigs by image analysis.

A new morphometric technique using image analysis has been developed to express the topographic distribution of atherosclerotic lesions in unambiguous statistical terms. Computer-stored images of opened Sudan IV-stained aortas and iliac and coronary arteries from hypercholesterolemic minipigs (n = 39) were used in this study. The image processing methods included transformation of the data to standard templates, automated image segmentation, and creation of probability-of-occurrence maps. These maps have shown that sudanophilic lesions are localized with a characteristic topography along the aortas and iliac and coronary arteries. Areas of high probability are associated with the entrance regions of vessels and the lateral leading edges of the major flow dividers. Regions immediately distal to large branches were found to be areas of low probability. Despite the association of areas of sudanophilia with entrance regions and branch points, a major portion of sudanophilic lesions was not associated with any orifice region (e.g., ductus scar, dorsolateral surface of abdominal aorta, and ventral surface of terminal aorta). The present study provides the necessary information for the development of a rational sampling strategy for the experimental study of the distribution of localizing factors (e.g., hemodynamic, biochemical, cellular, mass transport, histological) and their relationships to putative atherogenic mechanisms.

Animals↗

PubMed2005

1H-MRS alterations in the cerebellum of patients with familial hemiplegic migraine type 1.

BACKGROUND: About 20% of patients with familial hemiplegic migraine (FHM) develop progressive cerebellar signs. Genetic studies have established an association with mutations in the CACNA1A gene. However, the mechanisms underlying cerebellar involvement are largely unknown. OBJECTIVE: To use proton MR spectroscopy (1H-MRS) to investigate metabolic alterations in the cerebellum as well as cortical regions known to be involved in the propagation of migraine aura. METHODS: Fifteen CACNA1A mutation carriers from three FHM families and 17 healthy control subjects were studied. Eleven patients had clinical signs of cerebellar involvement. LCModel fits were used to estimate absolute concentrations of N-acetyl aspartate (NAA), myo-inositol (mI), glutamate (Glu), choline-containing compounds, total creatine, and lactate in the superior cerebellar vermis (SCV), parietal cortex, and occipital cortex. To control for atrophy effects, automated image segmentation was performed using SPM99. The brain parenchyma fraction (BPF) was determined for all three regions. RESULTS: Compared with controls, the brain parenchyma fraction (BPF), NAA, and Glu were significantly reduced and mI was significantly elevated in the SCV of patients with FHM. In contrast, no metabolite alterations were found in supratentorial regions. BPF and NAA in the SCV significantly correlated with cerebellar scores, in particular, gait ataxia. CONCLUSIONS: The findings suggest that there is a regionally distinct neuronal impairment in the superior cerebellar vermis that exceeds macroscopic tissue loss. Correlations with clinical scores emphasize the functional relevance of localized atrophy (brain parenchyma fraction) and N-acetyl aspartate levels. These measures may be useful to monitor disease progression. The observed reduction in glutamate may in part reflect impaired glutamatergic neurotransmission.

Adolescent↗

PubMedDate not supplied

The physical, biologic, and clinical basis of radiosurgery.

Since Leksell's description of the concept of radiosurgery in 1951, probably more than 20,000 patients worldwide have been treated with this technique. Initially designed as a tool for functional neurostereotaxis, it has found widespread applicability for conditions as diverse as vascular malformations, benign tumors such as acoustic neuroma, meningioma, pituitary adenoma, and also malignant tumors such as brain metastases and malignant glioma. From rudimentary knowledge of the ability to produce focal necrotic lesions, the biologic understanding of the process of single-fraction, small-volume, high-dose brain radiation has evolved into a multicompartmental model, with reasonable appreciation of the dose, volume, and time factors involved. With the explosion of technology on several fronts in the 1980s and 1990s, a multitude of devices for radiosurgery, ranging from cyclotron-generated particle beams to multisource cobalt-60 units to an immense variety of modified linear accelerators has become available. A parallel explosion of technology in the fields of imaging and computing will ensure that this is just the beginning; already, technologies for automated image segmentation and target identification, long the physician's monopoly, are around the corner; image fusion now allows simultaneous visualization of target and normal tissue anatomy, physiology, and other exciting possibilities such as chemical composition and vascular characteristics. Advances in physics and robotics have led to development of prototypical machines that will blur the distinction between radiosurgery and conformal radiotherapy. Already, several "first generation" devices to free stereotaxis from its fixation to frames are available. Substantial enthusiasm among clinicians has ensured that, unlike many fleetingly and momentarily exciting technologies of the last 2 decades, radiosurgery has made and will continue to make a strong commitment for clinical efficacy, safety, and cost-effectiveness through the process of thorough multiinstitutional clinical trials, as opposed to seeking validation from anecdotal experiences. In this regard, the Radiation Therapy Oncology Group (RTOG) and the Gamma Knife User's Group (GKUG) are to be commended; if the plethora of radiosurgery-related publications is evidence of scientific interest, the field will likely continue to expand. In the future, issues pertaining to appropriate regulatory review, patient selection, quality assurance, and training will need to be addressed. Major clinical and biological studies still need to be undertaken.

Adenoma↗

PubMed2001

Automated CT marker segmentation for image registration in radionuclide therapy.

In this paper a novel, automated CT marker segmentation technique for image registration is described. The technique, which is based on analysing each CT slice contour individually, treats the cross sections of the external markers as protrusions of the slice contour. Knowledge-based criteria, using the shape and dimensions of the markers, are defined to enable marker identification and segmentation. Following segmentation, the three-dimensional (3D) markers' centroids are localized using an intensity-weighted algorithm. Finally, image registration is performed using a least-squares fit algorithm. The technique was applied to both simulated and patient studies. The patients were undergoing 131I-mIBG radionuclide therapy with each study comprising several 99mTc single photon emission computed tomography (SPECT) scans and one CT marker scan. The mean residual 3D registration errors (+/- 1 SD) computed for the simulated and patient studies were 1.8 +/- 0.3 mm and 4.3 +/- 0.5 mm respectively.

Algorithms↗

PubMedDate not supplied

Whole-brain atrophy in multiple sclerosis measured by automated versus semiautomated MR imaging segmentation.

BACKGROUND AND PURPOSE: Semiautomated and automated methods are used to measure whole-brain atrophy in multiple sclerosis (MS), but their comparative reliability, sensitivity, and validity are unknown. METHODS: Brain parenchymal fraction (BPF) was measured in patients with MS (n = 52) and healthy control subjects (n = 17) by four methods: semiautomated or automated segmentation and 2D or 3D pulse sequences. Linear measures of atrophy, whole-brain lesion volumes, and clinical data were used to explore validity. RESULTS: The 2D automated method yielded unreliable segmentation and was discarded. The three other BPF methods produced data that were highly intercorrelated and indistinguishable by analysis of variance. In the MS group, semiautomated (2D: 0.84 +/- 0.04, P <.001; 3D: 0.84 +/- 0.05, P =.04) and automated 3D (0.83 +/- 0.05, P =.002) BPFs were lower than controls (semiautomated 2D: 0.88 +/- 0.02; 3D: 0.88 +/- 0.03; automated 3D: 0.88 +/- 0.03). In the MS group, the semiautomated (r = -.79 to -.82) and automated 3D (r = -.81) BPFs inversely correlated with third ventricular width and showed similarly robust correlations with the bicaudate ratio (all r = -.74). The semiautomated and automated BPFs showed similar, moderate correlations with T1 hypointense and FLAIR hyperintense lesion volume, physical disability (Expanded Disability Status Scale) score, and disease duration and similar differences between secondary progressive and relapsing-remitting patients. The intraobserver, interobserver, and test-retest reliability was somewhat higher for the automated than for the semiautomated methods. CONCLUSION: These automated and semiautomated measures of whole-brain atrophy provided similar and nearly interchangeable data regarding MS. They discriminated MS from healthy individuals and showed similar relationships to established disease variables.

Adult↗

PubMedDate not supplied

FAZYTAN: a system for fast automated cell segmentation, cell image analysis and feature extraction based on TV-image pickup and parallel processing.

Cell location, segmentation and feature extraction of cell images are principal tasks of a high-resolution system for automated cytology. To perform these tasks with high speed, image processing algorithms and the architecture of a processor have to be optimized mutually. This has led to the development of a fast system for the evaluation of cytologic samples based on an optimized TV microscope, a host minicomputer with different peripheral array processors and digital image storages. The processors are optimized in speed for two-dimensional local operations to investigate neighborhood relations and morphology in cell images. Two-dimensional transformations of TV images (288 x 512 x 8 bit) can be carried out within 20 to 200 msec. The processors are able to realize linear filter functions (correlation, convolution) as well as nonlinear functions (median filtering). A set of measurements like area, circumference and connectivity can be derived parallely from one image in 20 msec. The system performs efficient and fast detection and segmentation of cells scanned in one TV frame within one second as well as the extraction of a large number of morphologic features within a few seconds. Based on these procedures, high-resolution analysis of several thousand cells of a sample within one minute will be possible.

Autoanalysis↗

PubMed1992

Automated image detection and segmentation in blood smears.

A simple technique which automatically detects and then segments nucleated cells in Wright's giemsa-stained blood smears is presented. Our method differs from others in 1) the simplicity of our algorithms; 2) inclusion of touching (as well as nontouching) cells; and 3) use of these algorithms to segment as well as to detect nucleated cells employing conventionally prepared smears. Our method involves: 1) acquisition of spectral images; 2) preprocessing the acquired images; 3) detection of single and touching cells in the scene; 4) segmentation of the cells into nuclear and cytoplasmic regions; and 5) postprocessing of the segmented regions. The first two steps of this algorithm are employed to obtain high-quality images, to remove random noise, and to correct aberration and shading effects. Spectral information of the image is used in step 3 to segment the nucleated cells from the rest of the scene. Using the initial cell masks, nucleated cells which are just touching are detected and separated. Simple features are then extracted and conditions applied such that single nucleated cells are finally selected. In step 4, the intensity variations of the cells are then used to segment the nucleus from the cytoplasm. The success rate in segmenting the nucleated cells is between 81 and 93%. The major errors in segmentation of the nucleus and the cytoplasm in the recognized nucleated cells are 3.5% and 2.2%, respectively.

Algorithms↗

PubMed1997

Different approaches to synovial membrane volume determination by magnetic resonance imaging: manual versus automated segmentation.

Automated fast (5-20 min) synovial membrane volume determination by MRI, based on pre-set post-gadolinium-DTPA enhancement thresholds, was evaluated as a substitute for a time-consuming (45-120 min), previously validated, manual segmentation method. Twenty-nine knees [rheumatoid arthritis (RA) 13, osteoarthritis (OA) 16] and 17 RA wrists were examined. At enhancement thresholds between 30 and 60%, the automated volumes (Syn(x%)) were highly significantly correlated to manual volumes (SynMan) (knees: rho = 0.78-0.91, P < 10(-5) to < 10(-9); wrists: rho = 0.87-0.95, P < 10(-4) to < 10(-6)). The absolute values of the automated estimates were extremely dependent on the threshold chosen. At the optimal threshold of 45%, the median numerical difference from SynMan was 7 ml (17%) in knees and 2 ml (25%) in wrists. At this threshold, the difference was not related to diagnosis, clinical inflammation or synovial membrane volume, e.g. no systematic errors were found. The inter-MRI variation, evaluated in three knees and three wrists, was higher than by manual segmentation, particularly due to sensitivity to malalignment artefacts. Examination of test objects proved the high accuracy of the general methodology for volume determinations (maximal error 6.3%). Preceded by the determination of reproducibility and the optimal threshold at the available MR unit, automated 'threshold' segmentation appears to be acceptable when changes rather than absolute values of synovial membrane volumes are most important, e.g. in clinical trials.

Adult↗

PubMed1983

Influence of staining on fast automated cell segmentation, feature extraction and cell image analysis.

FAZYTAN, a system for fast automated cell segmentation, cell image analysis and extraction of nuclear features, was used to analyze cervical cell images variously stained by the conventional Papanicolaou stain, the new Papanicolaou stain and hematoxylin and thionin only; the last two dyes are used as the nuclear stains in the two versions of the Papanicolaou stain. Other dyes were also tried in cell classification experiments. All cell images in the variously stained samples could be described by the same nuclear features as had been adapted for the discrimination of conventional-Papanicolaou-stained cells. Variances were lower for thionin-stained cells as compared with hematoxylin-stained cells. By application of spectrophotometry, it was confirmed that the spectra of the cytoplasmic counterstains are superimposed on those of the nuclear stains. It appears that a variety of dyes are suitable as cytologic stains for cell classification by the FAZYTAN system, provided that they achieve sufficiently strong nuclear-cytoplasmic contrast by precisely delineating the chromatin texture.

Cell Nucleus↗

PubMed2003

A hybrid 3D watershed algorithm incorporating gradient cues and object models for automatic segmentation of nuclei in confocal image stacks.

BACKGROUND: Automated segmentation of fluorescently-labeled cell nuclei in 3D confocal microscope images is essential to many studies involving morphological and functional analysis. A common source of segmentation error is tight clustering of nuclei. There is a compelling need to minimize these errors for constructing highly automated scoring systems. METHODS: A combination of two approaches is presented. First, an improved distance transform combining intensity gradients and geometric distance is used for the watershed step. Second, an explicit mathematical model for the anatomic characteristics of cell nuclei such as size and shape measures is incorporated. This model is constructed automatically from the data. Deliberate initial over-segmentation of the image data is performed, followed by statistical model-based merging. A confidence score is computed for each detected nucleus, measuring how well the nucleus fits the model. This is used in combination with the intensity gradient to control the merge decisions. RESULTS: Experimental validation on a set of rodent brain cell images showed 97% concordance with the human observer and significant improvement over prior methods. CONCLUSIONS: Combining a gradient-weighted distance transform with a richer morphometric model significantly improves the accuracy of automated segmentation and FISH analysis.

Algorithms↗

PubMed2005

The bi-elliptical deformable contour and its application to automated tongue segmentation in Chinese medicine.

Automated tongue image segmentation, in Chinese medicine, is difficult due to two special factors: 1) there are many pathological details on the surface of the tongue, which have a large influence on edge extraction; 2) the shapes of the tongue bodies captured from various persons (with different diseases) are quite different, so they are impossible to describe properly using a predefined deformable template. To address these problems, in this paper, we propose an original technique that is based on a combination of a bi-elliptical deformable template (BEDT) and an active contour model, namely the bi-elliptical deformable contour (BEDC). The BEDT captures gross shape features by using the steepest decent method on its energy function in the parameter space. The BEDC is derived from the BEDT by substituting template forces for classical internal forces, and can deform to fit local details. Our algorithm features fully automatic interpretation of tongue images and a consistent combination of global and local controls via the template force. We apply the BEDC to a large set of clinical tongue images and present experimental results.

Algorithms↗

PubMed2004

Automated performance evaluation of range image segmentation algorithms.

Previous performance evaluation of range image segmentation algorithms has depended on manual tuning of algorithm parameters, and has lacked a basis for a test of the significance of differences between algorithms. We present an automated framework for evaluating the performance of range image segmentation algorithms. Automated tuning of algorithm parameters in this framework results in performance as good as that previously obtained with careful manual tuning by the algorithm developers. Use of multiple training and test sets of images provides the basis for a test of the significance of performance differences between algorithms. The framework implementation includes range images, ground truth overlays, program source code, and shell scripts. This framework should a) make it possible to objectively and reliably compare the performance of range image segmentation algorithms; b) allow informed experimental feedback for the design of improved segmentation algorithms. The framework is demonstrated using range images, but in principle it could be used to evaluate region segmentation algorithms for any type of image.

Journal Article↗