Shape recovery algorithms using level sets in 2-D/3-D medical imagery: a state-of-the-art review

Efficacy of texture, shape, and intensity feature fusion for posterior-fossa tumor segmentation in MRI

Our previous works suggest that fractal texture feature is useful to detect pediatric brain tumor in multimodal MRI. In this study, we systematically investigate efficacy of using several different image features such as intensity, fractal texture, and level-set shape in segmentation of posterior-fossa (PF) tumor for pediatric patients. We explore effectiveness of using four different feature selection and three different segmentation techniques, respectively, to discriminate tumor regions from normal tissue in multimodal brain MRI. We further study the selective fusion of these features for improved PF tumor segmentation. Our result suggests that Kullback-Leibler divergence measure for feature ranking and selection and the expectation maximization algorithm for feature fusion and tumor segmentation offer the best results for the patient data in this study. We show that for T1 and fluid attenuation inversion recovery (FLAIR) MRI modalities, the best PF tumor segmentation is obtained using the texture feature such as multifractional Brownian motion (mBm) while that for T2 MRI is obtained by fusing level-set shape with intensity features. In multimodality fused MRI (T1, T2, and FLAIR), mBm feature offers the best PF tumor segmentation performance. We use different similarity metrics to evaluate quality and robustness of these selected features for PF tumor segmentation in MRI for ten pediatric patients.

Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation

The performance of the level set segmentation is subject to appropriate initialization and optimal configuration of controlling parameters, which require substantial manual intervention. A new fuzzy level set algorithm is proposed in this paper to facilitate medical image segmentation. It is able to directly evolve from the initial segmentation by spatial fuzzy clustering. The controlling parameters of level set evolution are also estimated from the results of fuzzy clustering. Moreover the fuzzy level set algorithm is enhanced with locally regularized evolution. Such improvements facilitate level set manipulation and lead to more robust segmentation. Performance evaluation of the proposed algorithm was carried on medical images from different modalities. The results confirm its effectiveness for medical image segmentation.

Development of a virtual reality guided diagnostic tool based on magnetic resonance imaging

Computed tomography (CT) and virtual reality (VR) made it possible to create internal views of the human body without actual penetration. During the last two decades, several endoscopic diagnosis procedures have received virtual counter candidates. This paper presents an own concept of a virtual reality guided diagnostic tool, based on magnetic resonance images representing parallel cross-sections of the investigated organ. A series of image processing methods are proposed for image quality enhancement, accurate segmentation in two dimensions, and three-dimensional reconstruction of detected surfaces. These techniques provide improved accuracy in image segmentation, and thus they represent excellent support for three dimensional imaging. The implemented software system allows interactive navigation within the investigated volume, and provides several facilities to quantify important physical properties including distances, areas, and volumes.

Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy c-means clustering and level set segmentation

The goal of this study was to develop an automated method to segment breast masses on dynamic contrast-enhanced (DCE) magnetic resonance (MR) scans and to evaluate its potential for estimating tumor volume on pre- and postchemotherapy images and tumor change in response to treatment. A radiologist experienced in interpreting breast MR scans defined a cuboid volume of interest (VOI) enclosing the mass in the MR volume at one time point within the sequence of DCE-MR scans. The corresponding VOIs over the entire time sequence were then automatically extracted. A new 3D VOI representing the local pharmacokinetic activities in the VOI was generated from the 4D VOI sequence by summarizing the temporal intensity enhancement curve of each voxel with its standard deviation. The method then used the fuzzy c-means (FCM) clustering algorithm followed by morphological filtering for initial mass segmentation. The initial segmentation was refined by the 3D level set (LS) method. The velocity field of the LS method was formulated in terms of the mean curvature which guaranteed the smoothness of the surface, the Sobel edge information which attracted the zero LS to the desired mass margin, and the FCM membership function which improved segmentation accuracy. The method was evaluated on 50 DCE-MR scans of 25 patients who underwent neoadjuvant chemotherapy. Each patient had pre- and postchemotherapy DCE-MR scans on a 1.5 T magnet. The in-plane pixel size ranged from 0.546 to 0.703 mm and the slice thickness ranged from 2.5 to 4.5 mm. The flip angle was 15 degrees, repetition time ranged from 5.98 to 6.7 ms, and echo time ranged from 1.2 to 1.3 ms. Computer segmentation was applied to the coronal T1-weighted images. For comparison, the same radiologist who marked the VOI also manually segmented the mass on each slice. The performance of the automated method was quantified using an overlap measure, defined as the ratio of the intersection of the computer and the manual segmentation volumes to the manual segmentation volume. Pre- and postchemotherapy masses had overlap measures of 0.81 +/- 0.13 (mean +/- s.d.) and 0.71 +/- 0.22, respectively. The percentage volume reduction (PVR) estimated by computer and the radiologist were 55.5 +/- 43.0% (mean +/- s.d.) and 57.8 +/- 51.3%, respectively. Paired Student's t test indicated that the difference between the mean PVRs estimated by computer and the radiologist did not reach statistical significance (p = 0.641). The automated mass segmentation method may have the potential to assist physicians in monitoring volume change in breast masses in response to treatment.

Multiphase level set algorithm for coupled segmentation of multiple regions. Application to MRI segmentation

Classic geometric active contour algorithms have the limitation of segmenting the image into only two regions: background and object of interest. A new multiphase level set algorithm for the segmentation of two or more regions of interest is proposed. This algorithm avoids by construction the presence of overlapped and void regions and no additional coupling terms are required. In addition, the number of iterations needed to reach convergence is small. The algorithm has been tested against a state-of-the-art multiphase method on both simulated and real Magnetic Resonance Imaging (MRI) volumes with favorable results.

The Virtual Family--development of surface-based anatomical models of two adults and two children for dosimetric simulations

The objective of this study was to develop anatomically correct whole body human models of an adult male (34 years old), an adult female (26 years old) and two children (an 11-year-old girl and a six-year-old boy) for the optimized evaluation of electromagnetic exposure. These four models are referred to as the Virtual Family. They are based on high resolution magnetic resonance (MR) images of healthy volunteers. More than 80 different tissue types were distinguished during the segmentation. To improve the accuracy and the effectiveness of the segmentation, a novel semi-automated tool was used to analyze and segment the data. All tissues and organs were reconstructed as three-dimensional (3D) unstructured triangulated surface objects, yielding high precision images of individual features of the body. This greatly enhances the meshing flexibility and the accuracy with respect to thin tissue layers and small organs in comparison with the traditional voxel-based representation of anatomical models. Conformal computational techniques were also applied. The techniques and tools developed in this study can be used to more effectively develop future models and further improve the accuracy of the models for various applications. For research purposes, the four models are provided for free to the scientific community.

Three-dimensional coupled-object segmentation using symmetry and tissue type information

This paper presents an automatic method for segmentation of brain structures using their symmetry and tissue type information. The proposed method generates segmented structures that have homogenous tissues. It benefits from general symmetry of the brain structures in the two hemispheres. It also benefits from the tissue regions generated by fuzzy c-means clustering. All in all, the proposed method can be described as a dynamic knowledge-based method that eliminates the need for statistical shape models of the structures while generating accurate segmentation results. The proposed approach is implemented in MATLAB and tested on the Internet Brain Segmentation Repository (IBSR) datasets. To this end, it is applied to the segmentation of caudate and ventricles three-dimensionally in magnetic resonance images (MRI) of the brain. Impacts of each of the steps of the proposed approach are demonstrated through experiments. It is shown that the proposed method generates accurate segmentation results that are insensitive to initialization and parameter selection. The proposed method is compared to four previous methods illustrating advantages and limitations of each method.

Smooth 3-D reconstruction for 2-D histological images

We present an image driven approach to the reconstruction of 3-D volumes from stacks of 2-D post-mortem sections (histology, cryoimaging, autoradiography or immunohistochemistry) in the absence of any external information. We note that a desirable quality of the reconstructed volume is the smoothness of its notable structures (e.g. the gray/white matter surfaces in brain images). Here we propose to use smoothness as a means to drive the reconstruction process itself. From an initial rigid pair-wise reconstruction of the input 2-D sections, we extract the boundaries of structures of interest. Those are then evolved under a mean curvature flow modified to constrain the flow within 2-D planes. Sparse displacement fields are then computed, independently for each slice, from the resulting flow. A variety of transformations, from globally rigid to arbitrarily flexible ones, can then be estimated from those fields and applied to the individual input 2-D sections to form a smooth volume. We detail our method and discuss preliminary results on both real histological data and synthetic examples.

Variational B-spline level-set: a linear filtering approach for fast deformable model evolution

In the field of image segmentation, most level-set-based active-contour approaches take advantage of a discrete representation of the associated implicit function. We present in this paper a different formulation where the implicit function is modeled as a continuous parametric function expressed on a B-spline basis. Starting from the active-contour energy functional, we show that this formulation allows us to compute the solution as a restriction of the variational problem on the space spanned by the B-splines. As a consequence, the minimization of the functional is directly obtained in terms of the B-spline coefficients. We also show that each step of this minimization may be expressed through a convolution operation. Because the B-spline functions are separable, this convolution may in turn be performed as a sequence of simple 1-D convolutions, which yields an efficient algorithm. As a further consequence, each step of the level-set evolution may be interpreted as a filtering operation with a B-spline kernel. Such filtering induces an intrinsic smoothing in the algorithm, which can be controlled explicitly via the degree and the scale of the chosen B-spline kernel. We illustrate the behavior of this approach on simulated as well as experimental images from various fields.

Incorporating temporal information into level set functional for robust ventricular boundary detection from echocardiographic image sequence

Echocardiographic images often suffer from dropouts that lead to loss of signals on the ventricular boundary and cause the level set curve used to detect the boundary leaking out from the gaps on the boundary. In this paper, a novel method that incorporates temporal information into the level set functional is proposed to solve the leakage problem encountered when detecting the heart wall boundary from the echocardiographic image sequence. The ventricular boundary is quantitatively partitioned and classified into strong and weak segments. The weak segments are considered to be weakened by dropouts and there is low confidence on the presence of boundary. Temporal information from neighboring frames is exploited as a regularizer into the level set equation. Hence, the original boundary information in the weak segments can be reconstructed and the curve leakage problem can be remedied. Experimental results demonstrate the advantages of the proposed method for the intended task.

Intraretinal layer segmentation of macular optical coherence tomography images using optimal 3-D graph search

Current techniques for segmenting macular optical coherence tomography (OCT) images have been 2-D in nature. Furthermore, commercially available OCT systems have only focused on segmenting a single layer of the retina, even though each intraretinal layer may be affected differently by disease. We report an automated approach for segmenting (anisotropic) 3-D macular OCT scans into five layers. Each macular OCT dataset consisted of six linear radial scans centered at the fovea. The six surfaces defining the five layers were identified on each 3-D composite image by transforming the segmentation task into that of finding a minimum-cost closed set in a geometric graph constructed from edge/regional information and a priori determined surface smoothness and interaction constraints. The method was applied to the macular OCT scans of 12 patients (24 3-D composite image datasets) with unilateral anterior ischemic optic neuropathy (AION). Using the average of three experts' tracings as a reference standard resulted in an overall mean unsigned border positioning error of 6.1 +/- 2.9 microm, a result comparable to the interobserver variability (6.9 +/- 3.3 microm). Our quantitative analysis of the automated segmentation results from AION subject data revealed that the inner retinal layer thickness for the affected eye was 24.1 microm (21%) smaller on average than for the unaffected eye (p < 0.001), supporting the need for segmenting the layers separately.

Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning

Multimodality imaging information is regularly used now in radiotherapy treatment planning for cancer patients. The authors are investigating methods to take advantage of all the imaging information available for joint target registration and segmentation, including multimodality images or multiple image sets from the same modality. In particular, the authors have developed variational methods based on multivalued level set deformable models for simultaneous 2D or 3D segmentation of multimodality images consisting of combinations of coregistered PET, CT, or MR data sets. The combined information is integrated to define the overall biophysical structure volume. The authors demonstrate the methods on three patient data sets, including a nonsmall cell lung cancer case with PET/CT, a cervix cancer case with PET/CT, and a prostate patient case with CT and MRI. CT, PET, and MR phantom data were also used for quantitative validation of the proposed multimodality segmentation approach. The corresponding Dice similarity coefficient (DSC) was 0.90 +/- 0.02 (p < 0.0001) with an estimated target volume error of 1.28 +/- 1.23% volume. Preliminary results indicate that concurrent multimodality segmentation methods can provide a feasible and accurate framework for combining imaging data from different modalities and are potentially useful tools for the delineation of biophysical structure volumes in radiotherapy treatment planning.

Characterization of mammographic masses based on level set segmentation with new image features and patient information

Computer-aided diagnosis (CAD) for characterization of mammographic masses as malignant or benign has the potential to assist radiologists in reducing the biopsy rate without increasing false negatives. The purpose of this study was to develop an automated method for mammographic mass segmentation and explore new image based features in combination with patient information in order to improve the performance of mass characterization. The authors' previous CAD system, which used the active contour segmentation, and morphological, textural, and spiculation features, has achieved promising results in mass characterization. The new CAD system is based on the level set method and includes two new types of image features related to the presence of microcalcifications with the mass and abruptness of the mass margin, and patient age. A linear discriminant analysis (LDA) classifier with stepwise feature selection was used to merge the extracted features into a classification score. The classification accuracy was evaluated using the area under the receiver operating characteristic curve. The authors' primary data set consisted of 427 biopsy-proven masses (200 malignant and 227 benign) in 909 regions of interest (ROIs) (451 malignant and 458 benign) from multiple mammographic views. Leave-one-case-out resampling was used for training and testing. The new CAD system based on the level set segmentation and the new mammographic feature space achieved a view-based Az value of 0.83 +/- 0.01. The improvement compared to the previous CAD system was statistically significant (p = 0.02). When patient age was included in the new CAD system, view-based and case-based Az values were 0.85 +/- 0.01 and 0.87 +/- 0.02, respectively. The study also demonstrated the consistency of the newly developed CAD system by evaluating the statistics of the weights of the LDA classifiers in leave-one-case-out classification. Finally, an independent test on the publicly available digital database for screening mammography with 132 benign and 197 malignant ROIs containing masses achieved a view-based Az value of 0.84 +/- 0.02.

A new methodology based on q-entropy for breast lesion classification in 3-D ultrasound images

Classification of breast lesions is clinically most relevant for breast radiologists and pathologists for early breast cancer detection. This task is not easy due to poor ultrasound resolution and large amount of patient data size. This paper proposes a five step novel and automatic methodology for breast lesion classification in 3-D ultrasound images. The first three steps yield an accurate segmentation of the breast lesions based on the combination of (a) novel non-extensive entropy, (b) morphologic cleaning and (c) accurate region and boundary extraction in level set framework. Segmented lesions then undergo five feature extractions consisting of: area, circularity, protuberance, homogeneity, and acoustic shadow. These breast lesion features are then input to a support vector machine (SVM)-based classifier that classifies the breast lesions between malignant and benign types. SVM utilizes B-spline as a kernel in its framework. Using a data base of 250 breast ultrasound images (100 benign and 150 malignant) and utilizing the cross-validation protocol, we demonstrate system's accuracy, sensitivity, specificity, positive predictive value and negative predictive value as: 95%, 97%, 94%, 92% and 98% respectively in terms of ROC curves and A_z areas, better in performance than the current literature offers.

A 3D level sets method for segmenting the mouse spleen and follicles in volumetric microCT images

We present a semi-automatic, 3D approach for segmenting the mouse spleen, and its interior follicles, in volumetric microCT imagery. Based upon previous 2D level sets work, we develop a fully 3D implementation and provide the corresponding finite difference formulas. We incorporate statistical and proximity weighting schemes to improve segmentation performance. We also note an issue with the original algorithm and propose a solution that proves beneficial in our experiments. Experimental results are provided for artificial and real data.

Segmentation of the left ventricle of the heart in 3-D+t MRI data using an optimized nonrigid temporal model

Modern medical imaging modalities provide large amounts of information in both the spatial and temporal domains and the incorporation of this information in a coherent algorithmic framework is a significant challenge. In this paper, we present a novel and intuitive approach to combine 3-D spatial and temporal (3-D + time) magnetic resonance imaging (MRI) data in an integrated segmentation algorithm to extract the myocardium of the left ventricle. A novel level-set segmentation process is developed that simultaneously delineates and tracks the boundaries of the left ventricle muscle. By encoding prior knowledge about cardiac temporal evolution in a parametric framework, an expectation-maximization algorithm optimally tracks the myocardial deformation over the cardiac cycle. The expectation step deforms the level-set function while the maximization step updates the prior temporal model parameters to perform the segmentation in a nonrigid sense.

Edge intensity normalization as a bias field correction during balloon snake segmentation of breast MRI

Segmentation of fat suppressed dynamic contrast enhanced MRI (DCE-MRI) image data can pose significant problems because of the inherently poor signal-to-noise ratio (SNR) and intensity variations due to the bias field. Segmentation methods such as balloon snakes, while able to operate in a poor SNR environment, are sensitive to variations in edge intensity, which are regularly encountered within DCE-MRI due to the bias field. In order to overcome the effects of the bias field, an intensity normalization based on the strength of the strongest edge, i.e. the skin-air-boundary, is proposed and evaluated. This normalization allows balloon segmentations to be run three times faster while maintaining, or even improving accuracy.

A computational framework for approximating boundary surfaces in 3-D biomedical images

We propose a new method for detecting and approximating the boundary surfaces in three-dimensional (3-D) biomedical images. Using this method, each boundary surface in the original 3-D image is normalized as a zero-value isosurface of a new 3-D image transformed from the original 3-D image. A novel computational framework is proposed to perform such an image transformation. According to this framework, we first detect boundary surfaces from the original 3-D image and compute discrete samplings of the boundary surfaces. Based on these discrete samplings, a new 3-D image is constructed for each boundary surface such that the boundary surface can be well approximated by a zero-value isosurface in the new 3-D image. In this way, the complex problem of reconstructing boundary surfaces in the original 3-D image is converted into a task to extract a zero-value isosurface from the new 3-D image. The proposed technique is not only capable of adequately reconstructing complex boundary surfaces in 3-D biomedical images, but it also overcomes vital limitations encountered by the isosurface-extracting method when the method is used to reconstruct boundary surfaces from 3-D images. The performances and advantages of the proposed computational framework are illustrated by many examples from different 3-D biomedical images.

Weighted local variance-based edge detection and its application to vascular segmentation in magnetic resonance angiography

Accurate detection of vessel boundaries is particularly important for a precise extraction of vasculatures in magnetic resonance angiography (MRA). In this paper, we propose the use of weighted local variance (WLV)-based edge detection scheme for vessel boundary detection in MRA. The proposed method is robust against changes of intensity contrast of edges and capable of giving high detection responses on low contrast edges. These robustness and capabilities are essential for detecting the boundaries of vessels in low contrast regions of images, which can contain intensity inhomogeneity, such as bias field, interferences induced from other tissues, or fluctuation of the speed related vessel intensity. The performance of the WLV-based edge detection scheme is studied and shown to be able to return strong and consistent detection responses on low contrast edges in the experiments. The proposed edge detection scheme can be embedded naturally in the active contour models for vascular segmentation. The WLV-based vascular segmentation method is tested using MRA image volumes. It is experimentally shown that the WLV-based edge detection approach can achieve high-quality segmentation of vasculatures in MRA images.

Incorporation of regional information in optimal 3-D graph search with application for intraretinal layer segmentation of optical coherence tomography images

We present a method for the incorporation of regional image information in a 3-D graph-theoretic approach for optimal multiple surface segmentation. By transforming the multiple surface segmentation task into finding a minimum-cost closed set in a vertex-weighted graph, the optimal set of feasible surfaces with respect to an objective function can be found. In the past, this family of graph search applications only used objective functions which incorporated "on-surface" costs. Here, novel "in-region" costs are incorporated. Our new approach is applied to the segmentation of seven intraretinal layer surfaces of 24 3-D macular optical coherence tomography images from 12 subjects. Compared to an expert-defined independent standard, unsigned border positioning errors are comparable to the inter-observer variability (7.8 +/- 5.0 microm and 8.1 +/- 3.6 microm, respectively).

Compactly supported radial basis functions based collocation method for level-set evolution in image segmentation

The partial differential equation driving level-set evolution in segmentation is usually solved using finite differences schemes. In this paper, we propose an alternative scheme based on radial basis functions (RBFs) collocation. This approach provides a continuous representation of both the implicit function and its zero level set. We show that compactly supported RBFs (CSRBFs) are particularly well suited to collocation in the framework of segmentation. In addition, CSRBFs allow us to reduce the computation cost using a kd-tree-based strategy for neighborhood representation. Moreover, we show that the usual reinitialization step of the level set may be avoided by simply constraining the l1-norm of the CSRBF parameters. As a consequence, the final solution is topologically more flexible, and may develop new contours (i.e., new zero-level components), which are difficult to obtain using reinitialization. The behavior of this approach is evaluated from numerical simulations and from medical data of various kinds, such as 3-D CT bone images and echocardiographic ultrasound images.

Segmentation of the surfaces of the retinal layer from OCT images

We have developed a method for the automated segmentation of the internal limiting membrane and the pigment epithelium in 3-D OCT retinal images. Each surface was found as a minimum s-t cut from a geometric graph constructed from edge/regional information and a priori-determined surface constraints. Our approach was tested on 18 3-D data sets (9 from patients with normal optic discs and 9 from patients with papilledema) obtained using a Stratus OCT-3 scanner. Qualitative analysis of surface detection correctness indicates that our method consistently found the correct surfaces and outperformed the proprietary algorithm used in the Stratus OCT-3 scanner. For example, for the internal limiting membrane, 4% of the 2-D scans had minor failures with no major failures using our approach, but 19% of the 2-D scans using the Stratus OCT-3 scanner had minor or complete failures.

A generalized level set formulation of the Mumford-Shah functional for brain MR image segmentation

Brain MR image segmentation is an important research topic in medical image analysis area. In this paper, we propose an active contour model for brain MR image segmentation, based on a generalized level set formulation of the Mumford-Shah functional. The model embeds explicitly gradient information into the Mumford-Shah functional, and incorporates in a generic framework both regional and gradient information into segmentation process simultaneously. The proposed method has been evaluated on real brain MR images and the obtained results have shown the desirable segmentation performance.

3D statistical models for tooth surface reconstruction

This paper presents a method to reconstruct the 3D surface of a tooth given partial information about its shape. A statistical model comprising a mean shape and a series of deformation modes is obtained offline using a set of specimens. During reconstruction, rigid registration is performed to align the mean shape with the target. The mean shape is then deformed to approximate the target by minimizing the sum of squared distances between the two surfaces according to the deformation modes. The method is shown to be efficient for the recovery of tooth shape given crown information.

Brain image segmentation for virtual endoscopy

This paper presents an algorithm for fuzzy segmentation of MR brain images. Starting from the standard FCM and its bias-corrected version BCFCM algorithm, by splitting up the two major steps of the latter, and by introducing a new factor gamma, the amount of required calculations is considerably reduced. The algorithm provides good-quality segmented 2-D brain slices a very quick way, which makes it an excellent tool to support a virtual brain endoscope.

Medical image segmentation using minimal path deformable models with implicit shape priors

This paper presents a new method for segmentation of medical images by extracting organ contours, using minimal path deformable models incorporated with statistical shape priors. In our approach, boundaries of structures are considered as minimal paths, i.e., paths associated with the minimal energy, on weighted graphs. Starting from the theory of minimal path deformable models, an intelligent "worm" algorithm is proposed for segmentation, which is used to evaluate the paths and finally find the minimal path. Prior shape knowledge is incorporated into the segmentation process to achieve more robust segmentation. The shape priors are implicitly represented and the estimated shapes of the structures can be conveniently obtained. The worm evolves under the joint influence of the image features, its internal energy, and the shape priors. The contour of the structure is then extracted as the worm trail. The proposed segmentation framework overcomes the short-comings of existing deformable models and has been successfully applied to segmenting various medical images.

A hierarchical 3D segmentation method and the definition of vertebral body coordinate systems for QCT of the lumbar spine

We have developed a new hierarchical 3D technique to segment the vertebral bodies in order to measure bone mineral density (BMD) with high trueness and precision in volumetric CT datasets. The hierarchical approach starts with a coarse separation of the individual vertebrae, applies a variety of techniques to segment the vertebral bodies with increasing detail and ends with the definition of an anatomic coordinate system for each vertebral body, relative to which up to 41 trabecular and cortical volumes of interest are positioned. In a pre-segmentation step constraints consisting of Boolean combinations of simple geometric shapes are determined that enclose each individual vertebral body. Bound by these constraints viscous deformable models are used to segment the main shape of the vertebral bodies. Volume growing and morphological operations then capture the fine details of the bone-soft tissue interface. In the volumes of interest bone mineral density and content are determined. In addition, in the segmented vertebral bodies geometric parameters such as volume or the length of the main axes of inertia can be measured. Intra- and inter-operator precision errors of the segmentation procedure were analyzed using existing clinical patient datasets. Results for segmented volume, BMD, and coordinate system position were below 2.0%, 0.6%, and 0.7%, respectively. Trueness was analyzed using phantom scans. The bias of the segmented volume was below 4%; for BMD it was below 1.5%. The long-term goal of this work is improved fracture prediction and patient monitoring in the field of osteoporosis. A true 3D segmentation also enables an accurate measurement of geometrical parameters that may augment the clinical value of a pure BMD analysis.

Towards quantitative analysis of retinal features in optical coherence tomography

The purpose of this paper was to propose a new computer method for quantitative evaluation of representative features of the retina using optical coherence tomography (OCT). A multi-step approach was devised and positively tested for segmentation of the three main retinal layers: the vitreo-retinal interface and the inner and outer retina. Following a preprocessing step, three regions of interest were delimited. Significant peaks corresponding to high and low intensity strips were located along the OCT A-scan lines and accurate boundaries between different layers were obtained by maximizing an edge likelihood function. For a quantitative description, thickness measurement, densitometry, texture and curvature analyses were performed. As a first application, the effect of intravitreal injection of triamcinolone acetonide (IVTA) for the treatment of vitreo-retinal interface syndrome was evaluated. Almost all the parameters, measured on a set of 16 pathologic OCT images, were statistically different before and after IVTA injection (p<0.05). Shape analysis of the internal limiting membrane confirmed the reduction of the pathological traction state. Other significant parameters, such as reflectivity and texture contrast, exhibited relevant changes both at the vitreo-retinal interface and in the inner retinal layers. Texture parameters in the inner and outer retinal layers significantly correlated with the visual acuity restoration. According to these findings an IVTA injection might be considered a possible alternative to surgery for selected patients. In conclusion, the proposed approach appeared to be a promising tool for the investigation of tissue changes produced by pathology and/or therapy.

Segmentation of neighboring organs in medical image with model competition

This paper presents a novel approach for image segmentation by introducing competition between neighboring shape models. Our method is motivated by the observation that evolving neighboring contours should avoid overlapping with each other and this should be able to aid in multiple neighboring objects segmentation. A novel energy functional is proposed, which incorporates both prior shape information and interactions between deformable models. Accordingly, we also propose an extended maximum a posteriori (MAP) shape estimation model to obtain the shape estimate of the organ. The contours evolve under the influence of image information, their own shape priors and neighboring MAP shape estimations using level set methods to recover organ shapes. Promising results and comparisons from experiments on both synthetic data and medical imagery demonstrate the potential of our approach.

2-D ultrasound strain images for breast cancer diagnosis using nonrigid subregion registration

Tissue elasticity of a lesion is a useful criterion for the diagnosis of breast ultrasound (US). Elastograms are created by comparing ultrasonic radio-frequency waveforms before and after a light-tissue compression. In this study, we evaluate the accuracy of continuous US strain image in the classification of benign from malignant breast tumors. A series of B-mode US images is applied and each case involves 60 continuous images obtained by using the steady artificial pressure of the US probe. In general, after compression by the US probe, a soft benign tumor will become flatter than a stiffened malignant tumor. We proposed a computer-aided diagnostic (CAD) system by utilizing the nonrigid image registration modality on the analysis of tumor deformation. Furthermore, we used some image preprocessing methods, which included the level set segmentation, to improve the performance. One-hundred pathology-proven cases, including 60 benign breast tumors and 40 malignant tumors, were used in the experiments to test the classification accuracy of the proposed method. Four characteristic values--normalized slope of metric value (NSM), normalized area difference (NAD), normalized standard deviation (NSD) and normalized center translation (NCT)--were computed for all cases. By using the support vector machine, the accuracy, sensitivity, specificity and positive and negative predictive values of the classification of continuous US strain images were satisfactory. The A(z) value of the support vector machine based on the four characteristic values used for the classification of solid breast tumors was 0.9358.

Implicit dual snakes for medical imaging

Dual snake models are powerful techniques for boundary extraction and segmentation of 2D medical images. In these methods one contour contracts from outside the target and another one expands from inside as a balanced technique with the ability to reject local minima. Such approach was originally proposed in the context of parametric snakes. Recently, two implicit formulation for dual snakes were presented: our proposal, called the Dual-Level-Set, and the Dual-Front approach. In this paper we review these methods and offer some comparisons. We survey applications for shape recovery in 2D cell and human brain MRI images.

Model-based quantitative AAA image analysis using a priori knowledge

Abdominal aortic aneurysm (AAA) is a serious vascular disease which may have a fatal outcome. AAA shape and size is important for diagnostics and intervention planning. In this paper, we present a new method for segmentation of AAA from computed tomography (CT) angiography images. The method works by segmenting the inner and the outer aortic border. Segmentation of AAA is a challenging problem because of low contrast of the outer aortic border. In our method, the inner aortic border is segmented using a geometric deformable model (GDM) and morphological postprocessing. The GDM is implemented using the level-set algorithm. The outer aortic border is segmented by a preprocessing method utilizing a priori knowledge about the aorta shape, followed by the GDM-based method, and morphological postprocessing. The preprocessing algorithm operates on a slice-by-slice basis with some information flow among neighboring slices. The GDM performs three-dimensional (3D) segmentation, reducing possible errors in the previous step. The proposed method is automatic and requires minimal user assistance. The method was statistically validated on 12 patient scans having a total number of 497 image slices. Statistical analysis has confirmed high correlation between the results obtained by the proposed method and the gold standard obtained by manual segmentation by an expert radiologist.

Bayesian image segmentation using local iso-intensity structural orientation

Image segmentation is a fundamental problem in early computer vision. In segmentation of flat shaded, nontextured objects in real-world images, objects are usually assumed to be piecewise homogeneous. This assumption, however, is not always valid with images such as medical images. As a result, any techniques based on this assumption may produce less-than-satisfactory image segmentation. In this work, we relax the piecewise homogeneous assumption. By assuming that the intensity nonuniformity is smooth in the imaged objects, a novel algorithm that exploits the coherence in the intensity profile to segment objects is proposed. The algorithm uses a novel smoothness prior to improve the quality of image segmentation. The formulation of the prior is based on the coherence of the local structural orientation in the image. The segmentation process is performed in a Bayesian framework. Local structural orientation estimation is obtained with an orientation tensor. Comparisons between the conventional Hessian matrix and the orientation tensor have been conducted. The experimental results on the synthetic images and the real-world images have indicated that our novel segmentation algorithm produces better segmentations than both the global thresholding with the maximum likelihood estimation and the algorithm with the multilevel logistic MRF model.

A Segmentation and Reconstruction Technique for 3D Vascular Structures

In the context of stroke therapy simulation, a method for the segmentation and reconstruction of human vasculature is presented and evaluated. Based on CTA scans, semi-automatic tools have been developed to reduce dataset noise, to segment using active contours, to extract the skeleton, to estimate the vessel radii and to reconstruct the associated surface. The robustness and accuracy of our technique are evaluated on a vascular phantom scanned in different orientations. The reconstructed surface is compared to a surface generated by marching cubes followed by decimation and smoothing. Experiments show that the proposed technique reaches a good balance in terms of smoothness, number of triangles, and distance error. The reconstructed surface is suitable for real-time simulation, interactive navigation and visualization.

CPM: a deformable model for shape recovery and segmentation based on charged particles

A novel, physically motivated deformable model for shape recovery and segmentation is presented. The model, referred to as the charged-particle model (CPM), is inspired by classical electrodynamics and is based on a simulation of charged particles moving in an electrostatic field. The charges are attracted towards the contours of the objects of interest by an electrostatic field, whose sources are computed based on the gradient-magnitude image. The electric field plays the same role as the potential forces in the snake model, while internal interactions are modeled by repulsive Coulomb forces. We demonstrate the flexibility and potential of the model in a wide variety of settings: shape recovery using manual initialization, automatic segmentation, and skeleton computation. We perform a comparative analysis of the proposed model with the active contour model and show that specific problems of the latter are surmounted by our model. The model is easily extendable to 3D and copes well with noisy images.