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 181 records · Page 10Linked to original sources
PubMed2006

A fully automated method for quantifying and localizing white matter hyperintensities on MR images.

White matter hyperintensities (WMH), commonly found on T2-weighted FLAIR brain MR images in the elderly, are associated with a number of neuropsychiatric disorders, including vascular dementia, Alzheimer's disease, and late-life depression. Previous MRI studies of WMHs have primarily relied on the subjective and global (i.e., full-brain) ratings of WMH grade. In the current study we implement and validate an automated method for quantifying and localizing WMHs. We adapt a fuzzy-connected algorithm to automate the segmentation of WMHs and use a demons-based image registration to automate the anatomic localization of the WMHs using the Johns Hopkins University White Matter Atlas. The method is validated using the brain MR images acquired from eleven elderly subjects with late-onset late-life depression (LLD) and eight elderly controls. This dataset was chosen because LLD subjects are known to have significant WMH burden. The volumes of WMH identified in our automated method are compared with the accepted gold standard (manual ratings). A significant correlation of the automated method and the manual ratings is found (P<0.0001), thus demonstrating similar WMH quantifications of both methods. As has been shown in other studies (e.g. [Taylor, W.D., MacFall, J.R., Steffens, D.C., Payne, M.E., Provenzale, J.M., Krishnan, K.R., 2003. Localization of age-associated white matter hyperintensities in late-life depression. Progress in Neuro-Psychopharmacology and Biological Psychiatry. 27 (3), 539-544.]), we found there was a significantly greater WMH burden in the LLD subjects versus the controls for both the manual and automated method. The effect size was greater for the automated method, suggesting that it is a more specific measure. Additionally, we describe the anatomic localization of the WMHs in LLD subjects as well as in the control subjects, and detect the regions of interest (ROIs) specific for the WMH burden of LLD patients. Given the emergence of large NeuroImage databases, techniques, such as that described here, will allow for a better understanding of the relationship between WMHs and neuropsychiatric disorders.

Aged↗
PubMed2006

Digital photogrammetry for quantitative wear analysis of retrieved TKA components.

The use of new materials in knee arthroplasty demands a way in which to accurately quantify wear in retrieved components. Methods such as damage scoring, coordinate measurement, and in vivo wear analysis have been used in the past. The limitations in these methods illustrate a need for a different methodology that can accurately quantify wear, which is relatively easy to perform and uses a minimal amount of expensive equipment. Off-the-shelf digital photogrammetry represents a potentially quick and easy alternative to what is readily available. Eighty tibial inserts were visually examined for front and backside wear and digitally photographed in the presence of two calibrated reference fields. All images were segmented (via manual and automated algorithms) using Adobe Photoshop and National Institute of Health ImageJ. Finally, wear was determined using ImageJ and Rhinoceros software. The absolute accuracy of the method and repeatability/reproducibility by different observers were measured in order to determine the uncertainty of wear measurements. To determine if variation in wear measurements was due to implant design, 35 implants of the three most prevalent designs were subjected to retrieval analysis. The overall accuracy of area measurements was 97.8%. The error in automated segmentation was found to be significantly lower than that of manual segmentation. The photogrammetry method was found to be reasonably accurate and repeatable in measuring 2-D areas and applicable to determining wear. There was no significant variation in uncertainty detected among different implant designs. Photogrammetry has a broad range of applicability since it is size- and design-independent. A minimal amount of off-the-shelf equipment is needed for the procedure and no proprietary knowledge of the implant is needed.

Biocompatible Materials↗
PubMed1995

Relative concentrations of proton MR visible neurochemicals in gray and white matter in human brain.

The relative distributions of N-acetylaspartate (NAA) + N-acetylaspartylglutamate (NAAG), creatine + phosphocreatine (Cr/PCr), and choline (Cho) in the gray and white matter of human brain were determined by utilizing proton magnetic resonance spectroscopic imaging (SI). The SI data was processed using an automated spectroscopic image processing algorithm, and image segmentation was performed using a supervised technique. Linear regression analysis indicated that the NAA + NAAG (2.01 ppm) and Cr/PCr (3.02 ppm) peaks are greater in gray matter compared with white matter. The large intersubject variation observed in the Cho (3.20 ppm) resonance prevented the assessment of its regional distribution with confidence.

Adult↗
PubMed2005

Advanced neuronavigation in skull base tumors and vascular lesions.

OBJECTIVE: The purpose of this study was to describe the usefulness of recent advances of neuronavigational technology in the management of skull base tumors and of vascular lesions, treated via a skull base approach. METHODS: In 16 patients (skull base meningioma n = 9, petrous apex epidermoid n = l, craniopharyngeoma n = 1, giant internal carotid artery aneurysm n = 1, basilar/vertebral artery aneurysm n = 2, brain stem cavernoma n = 2), "advanced" neuronavigation was used. In contrast to "conventional" neuronavigation, the information for the neurosurgeon was enhanced by the intraoperative screen display of 3-dimensional reconstructions of the lesion, vessels, nerves and fiber tracts at risk. The 3-dimensional reconstructions were obtained by preoperative manual or automated segmentation processes. In addition, different imaging modalities (computed tomography [CT] with magnetic resonance imaging [MRI], CT with CT angiography, T (l)- with diffusion-weighted MRI) were fused and shown on the screen. RESULTS: In the cases of tumors, "advanced" neuronavigation facilitated the approach (n = 4), contributed to tailor the approach (n = 2) and helped to identify hidden neurovascular structures (n = 9). In the cases of aneurysms, "advanced" neuronavigation allowed us to reduce the skull base approach to the needs of safe aneurysm clipping (n = 3). In both cases of brain stem cavernoma, "advanced" neuronavigation was deemed useful for definition of the best surgical approach in relation to the pyramidal tract and brain stem nuclei. CONCLUSION: The authors' experiences suggest that neuronavigation, which displays 3-dimensional reconstructions of lesion, vessels, nerves and fiber tracts during surgery and makes use of image fusion techniques, is an important tool in the neurosurgical management of skull base lesions.

Adolescent↗
PubMed2004

Echocardiography in left ventricular dysfunction.

Left ventricular (LV) function is an important predictor of cardiac morbidity and mortality. The role of echocardiography in the assessment of LV function is well established and has been expanded over the last few years with the development of new methodologies. Echocardiography can assess LV global and regional function, as well as systolic and diastolic function. It has the ability to measure volumes, including cardiac output, pressures, LV mass, dP/dt. It can also assess regional dysfunction using the wall motion score. However quantitation by standard echo can be limited, due to poor endocardial definition, time-consuming, and reproducibility, lack of accuracy, particularly considering it takes a lot of geometric assumptions. Therefore, new methodologies have been recently developed to increase echo accuracy. These include the introduction of second harmonics, which is becoming a standard in most equipments; the use of contrast echo to improve LV opacification and endocardial border definition; color kinesis, which allows automated segmental motion analysis; tissue Doppler imaging, which can help in the assessment of regional and diastolic function; and more recently the ability to assess strain and strain rate. This last technology has the ability to quantify local myocardial deformation and it has shown to be a potential strong marker of ischemia, as well as a predictor of LV myocardial recovery postrevascularization. In conclusion, echocardiography is widely used to assess LV function. The recent developments of new ultrasound-related technologies have further increased the interest and importance of echocardiography in the assessment of LV function.

Diastole↗
PubMed1995

Applications of neural networks in medicine.

Artificial Neural Networks (ANNs) are a relatively new approach to computing inspired by the design and operation of the human brain. This paper introduces ANNs and describes some of their applications in the area of medicine, including cancer prognosis, segmentation of magnetic resonance images, and automated analysis of electrocardiograms.

Breast Neoplasms↗
PubMed2000

Hybrid artificial neural network segmentation of precise and accurate inversion recovery (PAIR) images from normal human brain.

This paper presents a novel semi-automated segmentation and classification method based on raw signal intensities from a quantitative T1 relaxation technique with two novel approaches for the removal of partial volume effects. The segmentation used a Kohonen Self Organizing Map that eliminated inter- and intra-operator variability. A Multi-layered Backpropagation Neural Network was able to classify the test data with a predicted accuracy of 87.2% when compared to manual classification. A linear interpolation of the quantitative T1 information by region and on a pixel-by-pixel basis was used to redistribute voxels containing a partial volume of gray matter (GM) and white matter (WM) or a partial volume of GM and cerebrospinal fluid (CSF) into the principal components of GM, WM, and CSF. The method presented was validated against manual segmentation of the base images by three experienced observers. Comparing segmented outputs directly to the manual segmentation revealed a difference of less than 2% in GM and less than 6% in WM for pure tissue estimations for both the regional and pixel-by-pixel redistribution techniques. This technique produced accurate estimates of the amounts of GM and WM while providing a reliable means of redistributing partial volume effects.

Adolescent↗
PubMed1999

Automated T2 quantitation in neuropsychiatric lupus erythematosus: a marker of active disease.

Active neuropsychiatric systemic lupus erythematosus (NPSLE) is characterized by brain edema as measured by manual quantitative magnetic resonance (MR) relaxometry. An automated image processing method was developed to segment gray matter (GM), while minimizing the effects of confounding factors, specifically cerebral atrophy and volume averaging artifacts. Twenty patients with SLE (10 major, 10 minor), matched for atrophy, were studied. We compared T2 calculated for GM segmented by manual and automated methods. Both methods demonstrated a marked increase in GM T2 in patients with major NPSLE (P < 0.001), confirming the presence of cerebral edema. The results from each method were highly correlated, (r = 0.64, P = 0.002). The automated method effectively identifies GM, minimizes volume averaging artifacts, and produces results similar to the manual method. This method markedly decreases analysis time and will make quantitative relaxometry a valuable contribution to the clinical management of NPSLE.

Adult↗
PubMed2006

Automated quantification of quantum-dot-labelled epidermal growth factor receptor internalization via multiscale image segmentation.

The ability to monitor epidermal growth factor receptor (EGFr) internalization specifically, and cellular protein concentrations and activation states in general, has been recently improved by the use of appropriately functionalized quantum dots (QDs), as a result of the long-lasting fluorescence, brightness and multicolour of these nanoparticles. However, important quantitative information about locational proteomics is based on the analysis of the properties of many cells and cell cultures on a per-cell basis, rather than tracking individual events within one cell. Moreover, relative positional information is often gained from traditional staining protocols of distinct cellular compartments that are prone to noise, fading and low contrast. We apply a novel multiscale image segmentation based on region growing to classify automatically objects in fixed cell preparations and to define regional zones in all cells prior to QD concentration measures. This allows rapid quantitative description of EGFr internalization as it changes with incubation time. The capabilities realizable by simultaneous application of confocal imaging and functionalized QDs in conjunction with advanced image analysis are a prerequisite for automated and multiplexed cytomics assays.

Biotin↗
PubMed1998

Segmentation and interpretation of MR brain images: an improved active shape model.

This paper reports a novel method for fully automated segmentation that is based on description of shape and its variation using point distribution models (PDM's). An improvement of the active shape procedure introduced by Cootes and Taylor to find new examples of previously learned shapes using PDM's is presented. The new method for segmentation and interpretation of deep neuroanatomic structures such as thalamus, putamen, ventricular system, etc. incorporates a priori knowledge about shapes of the neuroanatomic structures to provide their robust segmentation and labeling in magnetic resonance (MR) brain images. The method was trained in eight MR brain images and tested in 19 brain images by comparison to observer-defined independent standards. Neuroanatomic structures in all testing images were successfully identified. Computer-identified and observer-defined neuroanatomic structures agreed well. The average labeling error was 7%+/-3%. Border positioning errors were quite small, with the average border positioning error of 0.8+/-0.1 pixels in 256 x 256 MR images. The presented method was specifically developed for segmentation of neuroanatomic structures in MR brain images. However, it is generally applicable to virtually any task involving deformable shape analysis.

Algorithms↗
PubMed1996

Echocardiographic quantification of regional left ventricular wall motion with color kinesis.

BACKGROUND: Color kinesis is a new technology for the echocardiographic assessment of left ventricular wall motion based on acoustic quantification. This technique automatically detects endocardial motion in real time by using integrated backscatter data to identify pixel transitions from blood to tissue during systole on a frame-by-frame basis. In this study, we evaluated the feasibility and accuracy of quantitative segmental analysis of color kinesis images to provide objective evaluation of regional systolic endocardial motion. METHODS AND RESULTS: Two-dimensional echocardiograms were obtained in the short-axis and apical four-chamber views in 20 normal subjects and 40 patients with regional wall motion abnormalities. End-systolic color overlays superimposed on the gray scale images were obtained with color kinesis to color encode left ventricular endocardial motion throughout systole on a frame-by-frame basis. These color-encoded images were divided into segments by use of custom software. In each segment, pixels of different colors were counted and displayed as stacked histograms reflecting the magnitude and timing of regional endocardial excursion. In normal subjects, histograms were found to be highly consistent and reproducible. The patterns of contraction obtained in normal subjects were used as a reference for the objective automated interpretation of regional wall motion abnormalities, defined as deviations from this pattern. The variability in the echocardiographic interpretation of wall motion between two experienced readers was similar to the diagnostic variability between the consensus of the two readers and the automated interpretation. CONCLUSIONS: Color kinesis is a promising new tool that may be used clinically to improve the qualitative and quantitative evaluation of spatial and temporal aspects of global and regional wall motion. In this initial study, segmental analysis of color kinesis images provided accurate, automated, and quantitative diagnosis of regional wall motion abnormalities.

Adult↗
PubMed2004

Multidetector CT angiography of arterial inflow and runoff in the lower extremities: a challenge in data acquisition and evaluation.

PURPOSE: To show the feasibility of acquiring homogenous 3-dimensional datasets with high temporal and spatial resolution from computed tomographic angiographic (CTA) scans of the lower extremities and to assess automated vessel-tracking techniques for vascular evaluation. METHODS: Eighteen men (mean age 67.0 years, range 43-83) with aneurysmal or occlusive vascular diseases underwent contrast-enhanced CTA of the lower limb arteries utilizing a 16-row CT imager. Curved multiplanar reformations were generated by manual selection of vessel centerlines in the infrarenal aorta and the arterial vasculature in the pelvis, thigh, and calf based on volume-rendering techniques. For each vessel, opacification and depiction were quantitatively evaluated. The manually segmented images were compared to datasets processed with automated vessel-tracking strategies by 5 radiologists, who evaluated diagnostic reliability and image quality. A Differential Receiver Operating Characteristic (DROC) analysis was performed. RESULTS: An increase in the temporal and spatial resolution led to acquisition of high quality CTA datasets. Significant homogeneity of the vascular contrast-to-noise ratios was achieved in the pelvic (coefficient of variance 1.5% to 10.1%), thigh (0.1% to 9.4%), and calf (3.3% to 19.2%) vessels. The assessment of vascular delineation revealed full-width-at-half-maximum contrast values of 96.4%, 95.5%, and 111.3% in the pelvis, thigh, and calf, respectively. Observers were not able to distinguish between manual and automated vascular segmentation, as represented by a 0.56 value for the area under the DROC curve. CONCLUSIONS: High-resolution CTA lower extremity datasets were acquired successfully, presenting vascular signal intensities of high homogeneity suitable for automated vessel-tracking techniques. Automated 3D visualization tools produced reliable, reproducible, and time-efficient centerline extractions that were comparable to manually defined centerlines.

Adult↗
PubMed1996

Tumour volume determination from MR images by morphological segmentation.

Accurate tumour volume measurement from MR images requires some form of objective image segmentation, and therefore a certain degree of automation. Manual methods of separating data according to the various tissue types which they are thought to represent are inherently prone to operator subjectivity and can be very time consuming. A segmentation procedure based on morphological edge detection and region growing has been implemented and tested on a phantom of known adjustable volume. Comparisons have been made with a traditional data thresholding procedure for the determination of tumour volumes on a set of patients with intracerebral glioma. The two methods are shown to give similar results, with the morphological segmentation procedure having the advantages of being automated and faster.

Brain Neoplasms↗
PubMed1988

Medical images and automated interpretation.

The application of automated interpretation to medical images is discussed and the main methods of medical imaging are briefly described. The factors behind the process of human clinical interpretation are also considered. Because human interpretation can be aided by processing of the raw image, the standard methods of image processing are mentioned. Automated interpretation of images in other fields is relevant, and segmentation of images is an important initial part of the process. There are already some applications of automated interpretation of medical images. Some are more complete than others. This will undoubtedly be an important developing field of work which will draw on experience from other areas, and be spurred on by the increasing complexity of medical imaging methods and shortage of expertise for human interpretation.

Artificial Intelligence↗
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↗
PubMed1998

Automated lung segmentation in digital lateral chest radiographs.

We are developing a fully automated computerized scheme for segmenting the lung fields in digital lateral chest radiographs. Existing computer-aided diagnostic (CAD) schemes and automated lung segmentation methods have focused exclusively on the posteroanterior view, despite the diagnostic importance of the lateral view. Information from the lateral radiograph is routinely incorporated by radiologists in their decision-making process, and thus computer analysis of lateral images may potentially add another dimension to current CAD schemes. Automated analysis of the lung fields in lateral images will necessarily require accurate segmentation. Our scheme employs an initial procedure to eliminate external and subcutaneous pixels. Global gray-level histogram analysis then allows for the identification of a range of gray-level thresholds. An iterative gray-level thresholding scheme is implemented using this range of thresholds to construct a series of binary images in which contiguous regions are identified and geometrically analyzed. Regions determined to be outside the lungs are prevented from contributing to binary images at later iterations. Adaptive local gray-level thresholding is applied along the initial contour that results from the global thresholding procedure to extend the contour closer to the true lung borders. This local thresholding method uses regions of interest of various dimensions, depending on the enclosed anatomy. Smoothing and polynomial curve fitting complete the segmentation. A database of 100 normal and 100 abnormal lateral images was analyzed. Quantitative comparison of computer-segmented lung regions with lung regions manually delineated by two radiologists indicated that 83% and 84% of normal and abnormal images, respectively, displayed segmentation contours within three standard deviations of the mean inter-radiologist contour degree-of-overlap value.

Automation↗