Automated analysis of nerve-cell images using active contour models

The number of nerve fibers (axons) in a nerve, the axon size, and shape can all be important neuroanatomical features in understanding different aspects of nerves in the brain. However, the number of axons in a nerve is typically in the order of tens of thousands and a study of a particular aspect of the nerve often involves many nerves. Potentially meaningful studies are often prohibited by the huge number involved when manual measurements have to be employed. A method that automates the analysis of axons from electron-micrographic images is presented. It begins with a rough identification of all the axon centers by use of an elliptical Hough transform procedure. Boundaries of each axons are then extracted based on active contour model, or snakes, approach where physical properties of the axons and the given image data are used in an optimization scheme to guide the snakes to converge to axon boundaries for accurate sheath measurement. However, false axon detection is still common due to poor image quality and the presence of other irrelevant cell features, thus a conflict resolution scheme is developed to eliminate false axons to further improve the performance of detection. The developed method has been tested on a number of nerve images and its results are presented.     

Automated optic disk boundary detection by modified active contour model

This paper presents a novel deformable-model-based algorithm for fully automated detection of optic disk boundary in fundus images. The proposed method improves and extends the original snake (deforming-only technique) in two aspects: clustering and smoothing update. The contour points are first self-separated into edge-point group or uncertain-point group by clustering after each deformation, and these contour points are then updated by different criteria based on different groups. The updating process combines both the local and global information of the contour to achieve the balance of contour stability and accuracy. The modifications make the proposed algorithm more accurate and robust to blood vessel occlusions, noises, ill-defined edges and fuzzy contour shapes. The comparative results show that the proposed method can estimate the disk boundaries of 100 test images closer to the groundtruth, as measured by mean distance to closest point (MDCP) <3 pixels, with the better success rate when compared to those obtained by gradient vector flow snake (GVF-snake) and modified active shape models (ASM).     

Automated detection of the left ventricular region in gated nuclearcardiac imaging

An approach to automated outlining the left ventricular contour and its bounded area in gated isotopic ventriculography is proposed. Its purpose is to determine the ejection fraction (EF), an important parameter for measuring cardiac function. The method uses a modified version of the fuzzy C-means (MFCM) algorithm and a labeling technique. The MFCM algorithm is applied to the end diastolic (ED) frame and then the (FCM) is applied to the remaining images in a “box” of interest. The MFCM generates a number of fuzzy clusters. Each cluster is a substructure of the heart (left ventricle, ...). A cluster validity index to estimate the optimum clusters number present in image data point is used. This index takes account of the homogeneity in each cluster and is connected to the geometrical property of data set. The labeling is only performed to achieve the detection process in the ED frame. Since the left ventricle (LV) cluster has the greatest area of the cardiac images sequence in ED phase, a framing operation is performed to obtain, automatically, the “box” enclosing the LV cluster. The EF assessed in 50 patients by the proposed method and a semi-automatic one, routinely used, are presented. A good correlation between the two methods EF values is obtained (R=0.93). The LV contour found has been judged very satisfactory by a team of trained clinicians     

Automated left ventricular segmentation in cardiac MRI

We present an automated left ventricular (LV) myocardial boundary extraction method. Automatic localization of the LV is achieved using a motion map and an expectation maximization algorithm. The myocardial region is then segmented using an intensity-based fuzzy affinity map and the myocardial contours are extracted by cost minimization through a dynamic programming approach. The results from the automated algorithm compared against the experienced radiologists using Bland and Altman analysis were found to have consistent mean bias of 7% and limits of agreement comparable to the inter-observer variability inherent in the manual method.     

The detection and quantification of retinopathy using digital angiograms

An algorithm is presented for the analysis and quantification of the vascular structures of the human retina. Information about retinal blood vessel morphology is used in grading the severity and progression of a number of diseases. These disease processes are typically followed over relatively long time courses, and subjective analysis of the sequential images dictates the appropriate therapy for these patients. In this research, retinal fluorescein angiograms are acquired digitally in a 1024x1024 16-b image format and are processed using an automated vessel tracking program to identify and quantitate stenotic and/or tortuous vessel segments. The algorithm relies on a matched filtering approach coupled with a priori knowledge about retinal vessel properties to automatically detect the vessel boundaries, track the midline of the vessel, and extract useful parameters of clinical interest. By modeling the vessel profile using Gaussian functions, improved estimates of vessel diameters are obtained over previous algorithms. An adaptive densitometric tracking technique based on local neighborhood information is also used to improve computational performance in regions where the vessel is relatively straight.     

基于小波域和活动轮廓模型的纹理图像分割

提出一种双树复小波域局部二值模式和活动轮廓模型的纹理图像分割方法.该方法首先使用双树复合小波分解纹理图像,然后使用局部二值模式提取纹理特征.利用最大熵准则对纹理特征图像进行选择,活动轮廓模型用于最后的分割.实验结果表明提出的方法对于合成纹理和自然场景数据集,达到了较高的分割精度.     

Automated brain structure segmentation based on atlas registration and appearance models

Accurate automated brain structure segmentation methods facilitate the analysis of large-scale neuroimaging studies. This work describes a novel method for brain structure segmentation in magnetic resonance images that combines information about a structure's location and appearance. The spatial model is implemented by registering multiple atlas images to the target image and creating a spatial probability map. The structure's appearance is modeled by a classifier based on Gaussian scale-space features. These components are combined with a regularization term in a Bayesian framework that is globally optimized using graph cuts. The incorporation of the appearance model enables the method to segment structures with complex intensity distributions and increases its robustness against errors in the spatial model. The method is tested in cross-validation experiments on two datasets acquired with different magnetic resonance sequences, in which the hippocampus and cerebellum were segmented by an expert. Furthermore, the method is compared to two other segmentation techniques that were applied to the same data. Results show that the atlas- and appearance-based method produces accurate results with mean Dice similarity indices of 0.95 for the cerebellum, and 0.87 for the hippocampus. This was comparable to or better than the other methods, whereas the proposed technique is more widely applicable and robust.     

Intracranial hemorrhage detection using spatial fuzzy c-mean and region-based active contour on brain CT imaging

Intracranial hemorrhage (ICH) detection is the primary task for the patients suffering from neurological disturbances and head injury. This paper presents a segmentation technique that combines the features of fuzzy c-mean (FCM) clustering and region-based active contour method. In the suggested method, the fuzzy membership degree from FCM clustering is first used to initialize the active contour, which propagates for the detection of the desired object. In addition to active contour initialization, the fuzzy clustering is also used to estimate the contour propagation controlling parameters. The level set function as used by active contour in the proposed method does not need re-initialization process; thus, it fastens the convergent speed of the contour propagation. The efficacy of the suggested method is demonstrated on a dataset of 20 brain computed tomography (CT) images suffered with ICH. Experimental results show that the proposed method has advantages in accuracy in comparison with standard region growing method and FCM for the detection of hemorrhage from brain CT images.     

Tag and contour detection in tagged MR images of the left ventricle

Tracking magnetic resonance tags in myocardial tissue promises to be an effective tool for the assessment of myocardial motion. The authors describe a hierarchy of image processing steps which rapidly detects both the contours of the myocardial boundaries of the left ventricle and the tags within the myocardium. The method works on both short axis and long axis images containing radial and parallel tag patterns, respectively. Left ventricular boundaries are detected by first removing the tags using morphological closing and then selecting candidate edge points. The best inner and outer boundaries are found using a dynamic program that minimizes a nonlinear combination of several local cost functions. Tags are tracked by matching a template of their expected profile using a least squares estimate. Since blood pooling, contiguous and adjacent tissue, and motion artifacts sometimes cause detection errors, a graphical user interface was developed to allow user correction of anomalous points. The authors present results on several tagged images of a human. A fully automated run generally finds the endocardial boundary and the tag lines extremely well, requiring very little manual correction. The epicardial boundary sometimes requires more intervention to obtain an acceptable result. These methods are currently being used in the analysis of cardiac strain and as a basis for the analysis of alternate tag geometries.     

Accurate automatic detection of end-diastole from left ventricular pressure using peak curvature

Precise identification of end-diastole (ED), corresponding to the end of diastole and start of systole, is crucial for accurate assessment of cardiac function. The aims of this study were to develop a new algorithm based on peak curvature (kappa(p)) for detecting ED as a "corner" in left ventricular pressure (LVP) signals, and to compare this approach with "gold-standard" ED obtained by manual annotation (ED(man)) and ED calculated with previously described algorithms that use an LVP first-derivative threshold (dP/dt(0) or dP/dt(100)), the peak LVP second-derivative (d(2)P/dt(2)(p)) or ECG R-wave peak (ECG(R)). Using customized software, all algorithms were applied to data derived from 213 large animal studies spanning a wide range of animal ages (fetus to adult), heart rates, inotropic states, and loading conditions. Differences between ED(man) and each algorithm were then compared after defining an acceptance region for the ED detection based on ED(man) interobserver variability. ED detected with kappa(p) was the most accurate (p < 0.001) and least variable (p < 0.001), with 97% of measurements within the acceptance region and difference from ED(man) of (1.5 +/- 4.2) ms. By contrast, ED was often detected early with dP/dt(0) and dP/dt(100) , and late with d(2)P/dt(2)(p) and ECG(R). These results indicate that the peak curvature algorithm using LVP provides accurate and reliable detection of ED.     

Integrating machine learning with region-based active contour models in medical image segmentation

Region-based active contour models are effective in segmenting images with poorly defined boundaries but often fail when applied to images containing intensity inhomogeneity. The traditional models utilize pixel intensity and are very sensitive to parameter tuning. On the other hand, machine learning algorithms are highly effective in handling inhomogeneities but often result in noise from misclassified pixels. In addition, there is no objective function. We propose a framework which integrates machine learning with a region-based active contour model. Classification probability scores from machine learning algorithm, which are regularized using a non-linear function, are used to replace the pixel intensity values during energy minimization. In our experiments, we integrate the k-nearest neighbours and the support vector machine with the Chan-Vese method and compare the results obtained with the traditional methods of Chan-Vese and Li et al. The proposed framework gives better accuracy and less sensitive to parameter tuning.     

Unsupervised segmentation based on robust estimation and color active contour models.

One of the most commonly used clinical tests performed today is the routine evaluation of peripheral blood smears. In this paper, we investigate the design, development, and implementation of a robust color gradient vector flow (GVF) active contour model for performing segmentation, using a database of 1791 imaged cells. The algorithms developed for this research operate in Luv color space, and introduce a color gradient and L2E robust estimation into the traditional GVF snake. The accuracy of the new model was compared with the segmentation results using a mean-shift approach, the traditional color GVF snake, and several other commonly used segmentation strategies. The unsupervised robust color snake with L2E robust estimation was shown to provide results which were superior to the other unsupervised approaches, and was comparable with supervised segmentation, as judged by a panel of human experts.     

Estimation of 3-D left ventricular deformation from medical images using biomechanical models

The quantitative estimation of regional cardiac deformation from three-dimensional (3-D) image sequences has important clinical implications for the assessment of viability in the heart wall. We present here a generic methodology for estimating soft tissue deformation which integrates image-derived information with biomechanical models, and apply it to the problem of cardiac deformation estimation. The method is image modality independent. The images are segmented interactively and then initial correspondence is established using a shape-tracking approach. A dense motion field is then estimated using a transversely isotropic, linear-elastic model, which accounts for the muscle fiber directions in the left ventricle. The dense motion field is in turn used to calculate the deformation of the heart wall in terms of strain in cardiac specific directions. The strains obtained using this approach in open-chest dogs before and after coronary occlusion, exhibit a high correlation with strains produced in the same animals using implanted markers. Further, they show good agreement with previously published results in the literature. This proposed method provides quantitative regional 3-D estimates of heart deformation.     

Robust active appearance models and their application to medical image analysis

Active appearance models (AAMs) have been successfully used for a variety of segmentation tasks in medical image analysis. However, gross disturbances of objects can occur in routine clinical setting caused by pathological changes or medical interventions. This poses a problem for AAM-based segmentation, since the method is inherently not robust. In this paper, a novel robust AAM (RAAM) matching algorithm is presented. Compared to previous approaches, no assumptions are made regarding the kind of gray-value disturbance and/or the expected magnitude of residuals during matching. The method consists of two main stages. First, initial residuals are analyzed by means of a mean-shift-based mode detection step. Second, an objective function is utilized for the selection of a mode combination not representing the gross outliers. We demonstrate the robustness of the method in a variety of examples with different noise conditions. The RAAM performance is quantitatively demonstrated in two substantially different applications, diaphragm segmentation and rheumatoid arthritis assessment. In all cases, the robust method shows an excellent behavior, with the new method tolerating up to 50% object area covered by gross gray-level disturbances.     

Estimation of current leakage in left and right ventricular conductance volumetry using a dynamic finite element model

Leakage of electric current through cardiac structures surrounding the ventricle is a primary source of error during ventricular volume measurements using a conductance catheter. This error can be represented as a leakage volume, VL. VL is generally estimated by a saline-bolus method, and is assumed constant throughout the cardiac cycle. However, dynamic changes in ventricular volume and cardiac wall thickness could change VL. To estimate VL, a dynamic finite element model of the heart was developed based on MR images. Conductance measurements were simulated using a modeled conductance catheter, and true VL was calculated. VL varied from 22.7 ml (end-systole) to 26.4 ml (end-diastole) in the left ventricle and from 19.9 ml (end-systole) to 26.9 ml (end-diastole) in the right ventricle. The saline-bolus method underestimated VL in both the left (VL = 19.4 ml) and the right (VL = 4.1 ml) ventricular volume measurements. VL increased linearly with the ratio of blood to tissue resistivity, and changed minimally with catheter position. These results indicate that VL has to be estimated dynamically throughout the cardiac cycle to obtain accurate cardiac volume measurements. The results also show that the saline bolus method does not estimate current leakage accurately, especially in the right ventricular volume measurement.     

Automated optimization of JPEG 2000 encoder options based on model observer performance for detecting variable signals in X-ray coronary angiograms

Image compression is indispensable in medical applications where inherently large volumes of digitized images are presented. JPEG 2000 has recently been proposed as a new image compression standard. The present recommendations on the choice of JPEG 2000 encoder options were based on nontask-based metrics of image quality applied to nonmedical images. We used the performance of a model observer [non-prewhitening matched filter with an eye filter (NPWE)] in a visual detection task of varying signals [signal known exactly but variable (SKEV)] in X-ray coronary angiograms to optimize JPEG 2000 encoder options through a genetic algorithm procedure. We also obtained the performance of other model observers (Hotelling, Laguerre-Gauss Hotelling, channelized-Hotelling) and human observers to evaluate the validity of the NPWE optimized JPEG 2000 encoder settings. Compared to the default JPEG 2000 encoder settings, the NPWE-optimized encoder settings improved the detection performance of humans and the other three model observers for an SKEV task. In addition, the performance also was improved for a more clinically realistic task where the signal varied from image to image but was not known a priori to observers [signal known statistically (SKS)]. The highest performance improvement for humans was at a high compression ratio (e.g., 30:1) which resulted in approximately a 75% improvement for both the SKEV and SKS tasks.     

Medical image segmentation by combining graph cuts and oriented active appearance models

In this paper, we propose a novel method based on a strategic combination of the active appearance model (AAM), live wire (LW), and graph cuts (GCs) for abdominal 3-D organ segmentation. The proposed method consists of three main parts: model building, object recognition, and delineation. In the model building part, we construct the AAM and train the LW cost function and GC parameters. In the recognition part, a novel algorithm is proposed for improving the conventional AAM matching method, which effectively combines the AAM and LW methods, resulting in the oriented AAM (OAAM). A multiobject strategy is utilized to help in object initialization. We employ a pseudo-3-D initialization strategy and segment the organs slice by slice via a multiobject OAAM method. For the object delineation part, a 3-D shape-constrained GC method is proposed. The object shape generated from the initialization step is integrated into the GC cost computation, and an iterative GC-OAAM method is used for object delineation. The proposed method was tested in segmenting the liver, kidneys, and spleen on a clinical CT data set and also on the MICCAI 2007 Grand Challenge liver data set. The results show the following: 1) The overall segmentation accuracy of true positive volume fraction TPVF > 94.3% and false positive volume fraction can be achieved; 2) the initialization performance can be improved by combining the AAM and LW; 3) the multiobject strategy greatly facilitates initialization; 4) compared with the traditional 3-D AAM method, the pseudo-3-D OAAM method achieves comparable performance while running 12 times faster; and 5) the performance of the proposed method is comparable to state-of-the-art liver segmentation algorithm. The executable version of the 3-D shape-constrained GC method with a user interface can be downloaded from http://xinjianchen.wordpress.com/research/.     

Automated microaneurysm detection using local contrast normalization and local vessel detection

Screening programs using retinal photography for the detection of diabetic eye disease are being introduced in the UK and elsewhere. Automatic grading of the images is being considered by health boards so that the human grading task is reduced. Microaneurysms (MAs) are the earliest sign of this disease and so are very important for classifying whether images show signs of retinopathy. This paper describes automatic methods for MA detection and shows how image contrast normalization can improve the ability to distinguish between MAs and other dots that occur on the retina. Various methods for contrast normalization are compared. Best results were obtained with a method that uses the watershed transform to derive a region that contains no vessels or other lesions. Dots within vessels are handled successfully using a local vessel detection technique. Results are presented for detection of individual MAs and for detection of images containing MAs. Images containing MAs are detected with sensitivity 85.4% and specificity 83.1%.     

Moving object segmentation and detection for monocular robot based on active contour model

A novel geodesic active contour model based on optical flow information is proposed to segment and detect the moving object for monocular robots. More specifically, an active contour is formulated using the level set method, which eliminates the need of re-initialisation. The developed scheme alleviates the effect of optical flow noise, increasing the robustness of the detection of moving objects. Experimental results show that this algorithm can successfully track a moving target, e.g. a human being.     

Parameter distribution models for estimation of population based left ventricular deformation using sparse fiducial markers

We present a method to estimate left ventricular (LV) motion based on three-dimensional (3-D) images that can be derived from any anatomical tomographic or 3-D modality, such as echocardiography, computed tomography, or magnetic resonance imaging. A finite element mesh of the LV was constructed to fit the geometry of the wall. The mesh was deformed by optimizing the nodal parameters to the motion of a sparse number of fiducial markers that were manually tracked in the images through the cardiac cycle. A parameter distribution model (PDM) of LV deformations was obtained from a database of MR tagging studies. This was used to filter the calculated deformation and incorporate a priori information on likely motions. The estimated deformation obtained from 13 normal untagged studies was compared with the deformation obtained from MR tagging. The end systolic (ES) circumferential and longitudinal strain values matched well with a mean difference of 0.1 +/- 3.2% and 0.3 +/- 3.0%, respectively. The calculated apex-base twist angle at ES had a mean difference of 1.0 +/- 2.3 degrees. We conclude that fiducial marker fitting in conjunction with a PDM provides accurate reconstruction of LV deformation in normal subjects.