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 163 records · Page 9Linked to original sources

PubMed2005

Atlas-based hippocampus segmentation in Alzheimer's disease and mild cognitive impairment.

This study assesses the performance of public-domain automated methodologies for MRI-based segmentation of the hippocampus in elderly subjects with Alzheimer's disease (AD) and mild cognitive impairment (MCI). Structural MR images of 54 age- and gender-matched healthy elderly individuals, subjects with probable AD, and subjects with MCI were collected at the University of Pittsburgh Alzheimer's Disease Research Center. Hippocampi in subject images were automatically segmented by using AIR, SPM, FLIRT, and the fully deformable method of Chen to align the images to the Harvard atlas, MNI atlas, and randomly selected, manually labeled subject images ("cohort atlases"). Mixed-effects statistical models analyzed the effects of side of the brain, disease state, registration method, choice of atlas, and manual tracing protocol on the spatial overlap between automated segmentations and expert manual segmentations. Registration methods that produced higher degrees of geometric deformation produced automated segmentations with higher agreement with manual segmentations. Side of the brain, presence of AD, choice of reference image, and manual tracing protocol were also significant factors contributing to automated segmentation performance. Fully automated techniques can be competitive with human raters on this difficult segmentation task, but a rigorous statistical analysis shows that a variety of methodological factors must be carefully considered to insure that automated methods perform well in practice. The use of fully deformable registration methods, cohort atlases, and user-defined manual tracings are recommended for highest performance in fully automated hippocampus segmentation.

Aged↗

PubMed2002

Automated histogram-based brain segmentation in T1-weighted three-dimensional magnetic resonance head images.

Current semiautomated magnetic resonance (MR)-based brain segmentation and volume measurement methods are complex and not sufficiently accurate for certain applications. We have developed a simpler, more accurate automated algorithm for whole-brain segmentation and volume measurement in T(1)-weighted, three-dimensional MR images. This histogram-based brain segmentation (HBRS) algorithm is based on histograms and simple morphological operations. The algorithm's three steps are foreground/background thresholding, disconnection of brain from skull, and removal of residue fragments (sinus, cerebrospinal fluid, dura, and marrow). Brain volume was measured by counting the number of brain voxels. Accuracy was determined by applying HBRS to both simulated and real MR data. Comparing the brain volume rendered by HBRS with the volume on which the simulation is based, the average error was 1.38%. By applying HBRS to 20 normal MR data sets downloaded from the Internet Brain Segmentation Repository and comparing them with expert segmented data, the average Jaccard similarity was 0.963 and the kappa index was 0.981. The reproducibility of brain volume measurements was assessed by comparing data from two sessions (four total data sets) with human volunteers. Intrasession variability of brain volumes for sessions 1 and 2 was 0.55 +/- 0.56 and 0.74 +/- 0.56%, respectively; the mean difference between the two sessions was 0.60 +/- 0.46%. These results show that the HBRS algorithm is a simple, fast, and accurate method to determine brain volume with high reproducibility. This algorithm may be applied to various research and clinical investigations in which brain segmentation and volume measurement involving MRI data are needed.

Adult↗

PubMed2002

Fast robust automated brain extraction.

An automated method for segmenting magnetic resonance head images into brain and non-brain has been developed. It is very robust and accurate and has been tested on thousands of data sets from a wide variety of scanners and taken with a wide variety of MR sequences. The method, Brain Extraction Tool (BET), uses a deformable model that evolves to fit the brain's surface by the application of a set of locally adaptive model forces. The method is very fast and requires no preregistration or other pre-processing before being applied. We describe the new method and give examples of results and the results of extensive quantitative testing against "gold-standard" hand segmentations, and two other popular automated methods.

Algorithms↗

PubMed2006

A knowledge-guided active model method of cortical structure segmentation on pediatric MR images.

PURPOSE: To develop an automated method for quantification of cortical structures on pediatric MR images. MATERIALS AND METHODS: A knowledge-guided active model (KAM) approach was proposed with a novel object function similar to the Gibbs free energy function. Triangular mesh models were transformed to images of a given subject by maximizing entropy, and then actively slithered to boundaries of structures by minimizing enthalpy. Volumetric results and image similarities of 10 different cortical structures segmented by KAM were compared with those traced manually. Furthermore, the segmentation performances of KAM and SPM2, (statistical parametric mapping, a MATLAB software package) were compared. RESULTS: The averaged volumetric agreements between KAM- and manually-defined structures (both 0.95 for structures in healthy children and children with medulloblastoma) were higher than the volumetric agreement for SPM2 (0.90 and 0.80, respectively). The similarity measurements (kappa) between KAM- and manually-defined structures (0.95 and 0.93, respectively) were higher than those for SPM2 (both 0.86). CONCLUSION: We have developed a novel automatic algorithm, KAM, for segmentation of cortical structures on MR images of pediatric patients. Our preliminary results indicated that when segmenting cortical structures, KAM was in better agreement with manually-delineated structures than SPM2. KAM can potentially be used to segment cortical structures for conformal radiation therapy planning and for quantitative evaluation of changes in disease or abnormality.

Algorithms↗

PubMed1991

Influence of optical density on the automated segmentation of rat kidney lysosomes.

After staining for acid phosphatase, video-images were acquired from 0.5-micron sections of rat kidney. Lysosomes in proximal tubules were automatically segmented, using a VICOM digital image processor and measured for area, number and optical density (OD). The purpose of this study is to objectively evaluate the performance of the automated segmentation algorithm at different staining intensities (a) by measuring area after staining with different incubation times, reduced substrate concentration or by adding an inhibitor and (b) by 'simulating' a decrease in OD (reducing grey-values at each point of a digitized image). The results of the experiments showed that: (1) the algorithm will underestimate the size of lysosomes (a) when the OD in close to the local background and (b) when an area is larger than or close to the area of the lowpass square filter; (2) accuracy of the segmentation can be improved by comparing the results of feature extraction after segmentation of the same image at different relative OD levels; (3) lysosomes with very low OD, compared to background are delineated with a large error or not delineated at all and this cannot be corrected. Incorrectly delineated lysosomes can be identified and excluded from further calculations, or their measured area replaced by an estimate of the true area.

Acid Phosphatase↗

PubMed1997

Groping for quantitative digital 3-D image analysis: an approach to quantitative fluorescence in situ hybridization in thick tissue sections of prostate carcinoma.

In molecular pathology numerical chromosome aberrations have been found to be decisive for the prognosis of malignancy in tumours. The existence of such aberrations can be detected by interphase fluorescence in situ hybridization (FISH). The gain or loss of certain base sequences in the desoxyribonucleic acid (DNA) can be estimated by counting the number of FISH signals per cell nucleus. The quantitative evaluation of such events is a necessary condition for a prospective use in diagnostic pathology. To avoid occlusions of signals, the cell nucleus has to be analyzed in three dimensions. Confocal laser scanning microscopy is the means to obtain series of optical thin sections from fluorescence stained or marked material to fulfill the conditions mentioned above. A graphical user interface (GUI) to a software package for display, inspection, count and (semi-)automatic analysis of 3-D images for pathologists is outlined including the underlying methods of 3-D image interaction and segmentation developed. The preparative methods are briefly described. Main emphasis is given to the methodical questions of computer-aided analysis of large 3-D image data sets for pathologists. Several automated analysis steps can be performed for segmentation and succeeding quantification. However tumour material is in contrast to isolated or cultured cells even for visual inspection, a difficult material. For the present a fully automated digital image analysis of 3-D data is not in sight. A semi-automatic segmentation method is thus presented here.

Humans↗

PubMed2001

Mathematical morphologic segmentation dedicated to quantitative immunohistochemistry.

OBJECTIVE: To develop automatic segmentation sequences for fully automated quantitative immunohistochemistry of cancer cell nuclei by image analysis. STUDY DESIGN: The study focused on the automated delineation of cancer cell lobules and nuclei, taking breast carcinoma as an example. A hierarchic segmentation was developed, employing mainly the chaining of mathematical morphology operators. The proposed sequence was tested on 22 images of various situations, collected from 18 different cases of breast carcinoma. A quality control procedure was applied, comparing the automated method with manual outlining of cancer cell foci and with manual pricking of cancer cell nuclei. RESULTS: Good concordance was found between automated and manual segmentation procedures (90% for cancer cell clumps, 97% for cancer cell nuclei on average), but the rate of false positive nuclei (small regions labeled as nuclei by the segmentation procedure) could be relatively high (11% on average, with a maximum of 35%) and can result in underestimation of the immunostaining ratio. CONCLUSION: This study examined a preliminary approach to automated immunoquantification, limited to automated segmentation without any color characterization. The automated hierarchic segmentation presented here leads to good discrimination of cancer cell nuclei at the chosen magnification.

Breast Neoplasms↗

PubMed2006

3-D brain segmentation towards the integration of DTI and MRI modalities.

This study introduces a 3-D segmentation method together with a graphical user interface (GUI) as means to effectively automate the process of segmentation with the ultimate objective of integrating and visualizing diffusion tensor imaging (DTI) with magnetic resonance imaging (MRI) in a fully automated 3-D brain imaging system. A secondary objective is to reduce significantly the segmentation time required to extract key landmarks of the brain in contrast to the manual process currently used at many hospital settings. The results provided will prove this important assertion. The inter-correlation coefficient revealed 96.1% accuracy in segmenting all of the processed data, which consequently led to effective registration of the DTI and MRI modalities since they involve the same landmarks. The average speed of segmentation was just 35 seconds, a reduction of over 20 times of what is required for manual segmentation. In order to create a highly integrated interface, the segmentation results serve as input to a registration algorithm we are currently investigating and whose preliminary results support the significance of relying on an effective segmentation process. T1-weighted 3D Gradient Echo MR and DT images from 16 patients at Miami Children's Hospital were used for evaluation purposes.

Algorithms↗

PubMed1999

Neurocognitive deficits in medulloblastoma survivors and white matter loss.

Although previous studies have documented a significant risk of intellectual loss after treatment for childhood medulloblastoma (MED), the pathophysiology underlying this process is poorly understood. The purpose of this study was to test the hypotheses that (1) patients treated for MED in childhood have reduced volumes of normal white matter (NWM) related to their treatment with craniospinal irradiation with or without chemotherapy, and (2) deficits in NWM among patients surviving MED can at least partially explain deficits in their intellectual performance. Eighteen pediatric patients previously treated for MED were matched on the basis of age at the time of evaluation to 18 patients previously treated for low-grade posterior fossa tumors with surgery alone (mean difference, 3.7 months). Evaluations were conducted with age-appropriate neurocognitive testing and quantitative magnetic resonance imaging by using a novel automated segmentation and classification algorithm constructed from a hybrid neural network. Patients treated for MED had significantly less NWM (p < 0.01) and significantly lower Full-Scale IQ values than those treated for low-grade tumors (mean, 82.1 vs 92.9). In addition, NWM had a positive and statistically significant association with Full-Scale IQ among the patients treated for MED. We conclude that irradiation- or chemotherapy-induced destruction of NWM can at least partially explain intellectual and academic achievement deficits among MED survivors.

Adolescent↗

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↗