Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images

A neurocomputational method for fully automated 3D dendritic spine detection and segmentation of medium-sized spiny neurons

Acquisition and quantitative analysis of high resolution images of dendritic spines are challenging tasks but are necessary for the study of animal models of neurological and psychiatric diseases. Currently available methods for automated dendritic spine detection are for the most part customized for 2D image slices, not volumetric 3D images. In this work, a fully automated method is proposed to detect and segment dendritic spines from 3D confocal microscopy images of medium-sized spiny neurons (MSNs). MSNs constitute a major neuronal population in striatum, and abnormalities in their function are associated with several neurological and psychiatric diseases. Such automated detection is critical for the development of new 3D neuronal assays which can be used for the screening of drugs and the studies of their therapeutic effects. The proposed method utilizes a generalized gradient vector flow (GGVF) with a new smoothing constraint and then detects feature points near the central regions of dendrites and spines. Then, the central regions are refined and separated based on eigen-analysis and multiple shape measurements. Finally, the spines are segmented in 3D space using the fast marching algorithm, taking the detected central regions of spines as initial points. The proposed method is compared with three popular existing methods for centerline extraction and also with manual results for dendritic spine detection in 3D space. The experimental results and comparisons show that the proposed method is able to automatically and accurately detect, segment, and quantitate dendritic spines in 3D images of MSNs.

Detecting tubular structures via direct vector field singularity characterization

The initial step of vessel segmentation in 3D is the detection of vessel centerlines. The proposed methods in literature are either dependent on vessel radius and/or have low response at vessel bifurcations. In this paper we propose a 3D tubular structure detection method that removes these two drawbacks. The proposed method exploits the observations on the eigenvalues of the Hessian matrix as is done in literature, yet it employs a direct 3D vector field singularity characterization. The Gradient Vector Flow vector field is used and the eigenvalues of its Jacobian are exploited in computing a parameter free vesselness map. Results on phantom and real patient data exhibit robustness to scale, high response at vessel bifurcations, and good noise/non-vessel structure suppression.

Algorithm-based method for detection of blood vessels in breast MRI for development of computer-aided diagnosis

PURPOSE

To develop a computer-based algorithm for detecting blood vessels that appear in breast dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI), and to evaluate the improvement in reducing the number of vascular pixels that are labeled by computer-aided diagnosis (CAD) systems as being suspicious of malignancy.

MATERIALS AND METHODS

The analysis was performed in 34 cases. The algorithm applied a filter bank based on wavelet transform and the Hessian matrix to detect linear structures as blood vessels on a two-dimensional maximum intensity projection (MIP). The vessels running perpendicular to the MIP plane were then detected based on the connectivity of enhanced pixels above a threshold. The nonvessel enhancements were determined and excluded based on their morphological properties, including those showing scattered small segment enhancements or nodular or planar clusters. The detected vessels were first converted to a vasculature skeleton by thinning and subsequently compared to the vascular track manually drawn by a radiologist.

RESULTS

When evaluating the performance of the algorithm in identifying vascular tissue, the correct-detection rate refers to pixels identified by both the algorithm and radiologist, while the incorrect-detection rate refers to pixels identified by only the algorithm, and the missed-detection rate refers to pixels identified only by the radiologist. From 34 analyzed cases the median correct-detection rate was 85.6% (mean 84.9% +/- 7.8%), the incorrect-detection rate was 13.1% (mean 15.1% +/- 7.8%), and the missed-detection rate was 19.2% (mean 21.3% +/- 12.8%). When detected vessels were excluded in the hot-spot color-coding of the CAD system, they could reduce the labeling of vascular vessels in 2.6%-68.6% of hot-spot pixels (mean 16.6% +/- 15.9%).

CONCLUSION

The computer algorithm-based method can detect most large vessels and provide an effective means in reducing the labeling of vascular pixels as suspicious on a DCE-MRI CAD system. This algorithm may improve the workflow of radiologists using CAD for image display, but will be particularly useful for development of automated CAD that gives diagnostic impression.

Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images

This paper describes an algorithm for extracting pulmonary vascular trees (arteries plus veins) from three-dimensional (3D) thoracic computed tomographic (CT) images. The algorithm integrates tube enhancement filter and traversal approaches which are based on eigenvalues and eigenvectors of a Hessian matrix to extract thin peripheral segments as well as thick vessels close to the lung hilum. The resultant algorithm was applied to a simulation data set and 44 scans from 22 human subjects imaged via multidetector-row CT (MDCT) during breath holds at 85% and 20% of their vital capacity. A quantitative validation was performed with more than 1000 manually identified points selected from inside the vessel segments to assess true positives (TPs) and 1000 points randomly placed outside of the vessels to evaluate false positives (FPs) in each case. On average, for both the high and low volume lung images, 99% of the points was properly marked as vessel and 1% of the points were assessed as FPs. Our hybrid segmentation algorithm provides a highly reliable method of segmenting the combined pulmonary venous and arterial trees which in turn will serve as a critical starting point for further quantitative analysis tasks and aid in our overall goal of establishing a normative atlas of the human lung.

Control of on/off glomerular signaling by a local GABAergic microcircuit in the olfactory bulb

Odors are coded at the input level of the olfactory bulb by a spatial map of activated glomeruli, reflecting different odorant receptors (ORs) stimulated in the nose. Here we examined the function of local synaptic processing within glomeruli in transforming these input patterns into an output for the bulb, using patch-clamp recordings and calcium imaging in rat bulb slices. Two types of transformations were observed at glomeruli, the first of which produced a bimodal, "on/off" glomerular signal that varied probabilistically depending on olfactory receptor neuron (ORN) input levels. The bimodal response behavior was seen in glomerular synaptic responses, as well as in action potential ("spike") firing, wherein all mitral cells affiliated with a glomerulus either engaged in prolonged spike bursts or did not spike at all. In addition, evidence was obtained that GABAergic periglomerular (PG) cells that surround a glomerulus can prevent activation of a glomerulus through inhibitory inputs targeted onto excitatory external tufted cells. The path of PG cell activation appeared to be confined to one glomerulus, such that ORNs at one glomerulus initiated inhibition of the same glomerulus. The observed glomerular "self-inhibition" provides a mechanism of filtering odor signals that would be an alternative to commonly proposed mechanisms of lateral inhibition between OR-specific glomeruli. In this case, selective suppression of weak odor signals could be achieved based on the difference in the input resistance of PG cells versus excitatory neurons at a glomerulus.

Radiation-induced damage to microstructure of parotid gland: evaluation using high-resolution magnetic resonance imaging

PURPOSE

To elucidate the radiation-induced damage to the microstructure of the parotid gland using high-resolution magnetic resonance imaging.

METHODS AND MATERIALS

High-resolution magnetic resonance imaging of the parotid gland was performed before radiotherapy (RT) and during the RT period or < or =3 weeks after RT completion for 12 head-and-neck cancer patients using a 1.5-T scanner with a microscopy coil. The maximal cross-sectional area of the gland was evaluated, and changes in the internal architecture of the gland were assessed both visually and quantitatively.

RESULTS

Magnetic resonance images were obtained at a median parotid gland dose of 36 Gy (range, 11-64). According to the quantitative analysis, the maximal cross-sectional area of the gland was reduced, the width of the main duct was narrowed, and the intensity ratio of the main duct lumen to background was significantly decreased after RT (p <.0001). According to the visual assessment, the width of the main duct tended to narrow and the contrast of the duct lumen tended to be decreased, but no significant differences were noted. The visibility of the duct branches was unclear in 10 patients (p = .039), and the septum became dense in 11 patients (p = .006) after RT.

CONCLUSION

High-resolution magnetic resonance imaging is a noninvasive method of evaluating radiation-induced changes to the internal architecture of the parotid gland. Morphologic changes in the irradiated parotid gland were demonstrated during the RT course even when a relatively small dose was delivered to the gland.

Integrating automatic and interactive methods for coronary artery segmentation: let the PACS workstation think ahead

PURPOSE

To present newly developed software that can provide fast coronary artery segmentation and accurate centerline extraction for later lesion visualization and quantitative measurement while minimizing user interaction.

METHODS

Previously reported fully automatic and interactive methods for coronary artery extraction were optimized and integrated into a user-friendly workflow. The user's waiting time is saved by running the non-supervised coronary artery segmentation and centerline tracking in the background as soon as the images are received. When the user opens the data, the software provides an intuitive interactive analysis environment.

RESULTS

The average overlap between the centerline created in our software and the reference standard was 96.0%. The average distance between them was 0.38 mm. The automatic procedure runs for 1.4-2.5 min as a single-thread application in the background. Interactive processing takes 3 min in average.

CONCLUSION

In preliminary experiments, the software achieved higher efficiency than the former interactive method, and reasonable accuracy compared to manual vessel extraction.

Hardware accelerated segmentation of complex volumetric filament networks

We present a framework for segmenting and storing filament networks from scalar volume data. Filament networks are encountered more and more commonly in biomedical imaging due to advances in high-throughput microscopy. These data sets are characterized by a complex volumetric network of thin filaments embedded in a scalar volume field. High-throughput microscopy volumes are also difficult to manage since they can require several terabytes of storage, even though the total volume of the embedded structure is much smaller. Filaments in microscopy data sets are difficult to segment because their diameter is often near the sampling resolution of the microscope, yet these networks can span large regions of the data set. We describe a novel method to trace filaments through scalar volume data sets that is robust to both noisy and undersampled data. We use graphics hardware to accelerate the tracing algorithm, making it more useful for large data sets. After the initial network is traced, we use an efficient encoding scheme to store volumetric data pertaining to the network.

Volume of pulmonary lobes and segments in chronic obstructive pulmonary diseases calculated using newly developed three-dimensional software

PURPOSE

The aim of this study was to measure the volume of each pulmonary segment by volumetric computed tomography (CT) data using a newly developed three-dimensional software application and to identify the differences between those with chronic obstructive pulmonary disease (COPD) and controls.

MATERIALS AND METHODS

CT scans of 11 COPD patients and 16 controls were included. The volume of each pulmonary segment was measured by each of two operators to evaluate the reproducibility of the software. This measured volume was then divided by the total lung volume to revise individual variations.

RESULTS

Volumes of the right (rt) S2, rt S5, left (lt) S1 + S2, lt S3, and lt S5 were significantly larger in COPD patients than in controls (P < 0.05). Regarding the ratio of the volume of each pulmonary segment per total lung volume, the areas of rt S2 and lt S1 + S2 were significantly larger in COPD patients than in controls (P < 0.05), whereas lt S10 was significantly smaller in COPD patients than in controls (P < 0.05).

CONCLUSION

We measured the volume of each pulmonary segment based on volumetric CT data using this software. In addition, we demonstrated that the upper lung volume of COPD subjects was larger than that of controls, whereas the lower lung volumes were almost the same.

Multi-scale model-based vessel enhancement using local line integrals

This paper presents a novel vessel enhancement method. By regarding a vessel segment as a local line and exploiting the second order information along the line, our method embeds a vessel model to capture vessel structures. The vessel model is the key to better performances of our method than the Hessian-based methods and makes the Hessian-based methods fall in an extreme case of our method. It is experimentally shown that our method gives more accurate 'vesselness' measures and vessel direction estimations. In particular, our method achieves better background suppression, smoother 'vesselness' measures inside vessels and better responses at crossings (where two relatively straight vessels meet).

Detection of the optimal neuron traces in confocal microscopy images

Quantitative methods of analysis of neural circuits rely on large datasets of neurons reconstructed accurately in three dimensions (3D). Due to the complexity of neuronal arbors, large datasets of reconstructed neurons must be generated with automated algorithms. Here, we attempted to automate the process of neuron tracing from sparsely labeled 3D stacks of confocal microscopy images. Our algorithm involves two steps. In the first step, the segmented image of neurites in the stack is voxel-coded. Centers of intensity of consecutively coded wave fronts are connected into a branched structure, which represents a coarse trace of the neurites. In the second step, this trace is optimized with the modified active contour method, which tends to maximize the intensity along the trace while keeping it under tension. To assess the performance of the algorithm we used manual reconstructions of neurons and converted them into artificial stacks of intensity images. These images were traced using the developed algorithm and quantitatively compared to the corresponding manual traces. The optimal traces were on average 6.0% shorter than the manual traces. This reduction in length resulted from the smoothness of the optimal traces, which, in comparison to the manual ones, were built out of shorter segments, and, as a result, were 3.3% less tortuous. The average distance between the optimal and the manual traces was 0.14 microm, and the average distance between their corresponding branch-points was 2.2 microm, illustrating good agreement between the traces.

A non-parametric vessel detection method for complex vascular structures

Modern medical imaging techniques enable the acquisition of in vivo high resolution images of the vascular system. Most common methods for the detection of vessels in these images, such as multiscale Hessian-based operators and matched filters, rely on the assumption that at each voxel there is a single cylinder. Such an assumption is clearly violated at the multitude of branching points that are easily observed in all, but the most focused vascular image studies. In this paper, we propose a novel method for detecting vessels in medical images that relaxes this single cylinder assumption. We directly exploit local neighborhood intensities and extract characteristics of the local intensity profile (in a spherical polar coordinate system) which we term as the polar neighborhood intensity profile. We present a new method to capture the common properties shared by polar neighborhood intensity profiles for all the types of vascular points belonging to the vascular system. The new method enables us to detect vessels even near complex extreme points, including branching points. Our method demonstrates improved performance over standard methods on both 2D synthetic images and 3D animal and clinical vascular images, particularly close to vessel branching regions.

3-D respiratory motion compensation during EP procedures by image-based 3-D lasso catheter model generation and tracking

Radio-frequency catheter ablation of the pulmonary veins attached to the left atrium is usually carried out under fluoroscopy guidance. Two-dimensional X-ray navigation may involve overlay images derived from a static pre-operative 3-D volumetric data set to add anatomical details. However, respiratory motion may impair the utility of static overlay images for catheter navigation. We developed a system for image-based 3-D motion estimation and compensation as a solution to this problem for which no previous solution is yet known. It is based on 3-D catheter tracking involving 2-D/3-D registration. A biplane X-ray C-arm system is used to image a special circumferential (lasso) catheter from two directions. In the first step of the method, a 3-D model of the device is reconstructed. 3-D respiratory motion at the site of ablation is then estimated by tracking the reconstructed model in 3-D from biplane fluoroscopy. In our experiments, the circumferential catheter was tracked in 231 biplane fluoro frames (462 monoplane fluoro frames) with an average 2-D tracking error of 1.0 mm +/- 0.5 mm.

Visualization of cellular and microvascular relationships

Understanding the structure of microvasculature structures and their relationship to cells in biological tissue is an important and complex problem. Brain microvasculature in particular is known to play an important role in chronic diseases. However, these networks are only visible at the microscopic level and can span large volumes of tissue. Due to recent advances in microscopy, large volumes of data can be imaged at the resolution necessary to reconstruct these structures. Due to the dense and complex nature of microscopy data sets, it is important to limit the amount of information displayed. In this paper, we describe methods for encoding the unique structure of microvascular data, allowing researchers to selectively explore microvascular anatomy. We also identify the queries most useful to researchers studying microvascular and cellular relationships. By associating cellular structures with our microvascular framework, we allow researchers to explore interesting anatomical relationships in dense and complex data sets.

Structure-analysis method for electronic cleansing in cathartic and noncathartic CT colonography

Electronic cleansing (EC) is an emerging method for segmentation of fecal material in CT colonography (CTC) that is used for reducing or eliminating the requirement for cathartic bowel preparation and hence for improving patients' adherence to recommendations for colon cancer screening. In EC, feces tagged by an x-ray-opaque oral contrast agent are removed from the CTC images, effectively cleansing the colon after image acquisition. Existing EC approaches tend to suffer from the following cleansing artifacts: degradation of soft-tissue structures because of pseudo-enhancement caused by the surrounding tagged fecal materials, and pseudo soft-tissue structures and false fistulas caused by partial volume effects at the boundary between the air lumen and the tagged regions, called the air-tagging boundary (AT boundary). In this study, we developed a novel EC method, called structure-analysis cleansing, which effectively avoids these cleansing artifacts. In our method, submerged soft-tissue structures are recognized by their local morphologic signatures that are characterized based on the eigenvalues of a three-dimensional Hessian matrix. A structure-enhancement function is formulated for enhancing of the soft-tissue structures. In addition, thin folds sandwiched between the air lumen and tagged regions are enhanced by analysis of the local roughness based on multi-scale volumetric curvedness. Both values of the structure-enhancement function and the local roughness are integrated into the speed function of a level set method for delineating the tagged fecal materials. Thus, submerged soft-tissue structures as well as soft-tissue structures adhering to the tagged regions are preserved, whereas the tagged regions are removed along with the associated AT boundaries from CTC images. Evaluation of the quality of the cleansing based on polyps and folds in a colon phantom, as well as on polyps in clinical cathartic and noncathartic CTC cases with fluid and stool tagging, showed that our structure-analysis cleansing method is significantly superior to that of our previous thresholding-based EC method. It provides a cleansed colon with substantially reduced subtraction artifacts.

A variational method for geometric regularization of vascular segmentation in medical images

In this paper, a level-set-based geometric regularization method is proposed which has the ability to estimate the local orientation of the evolving front and utilize it as shape induced information for anisotropic propagation. We show that preserving anisotropic fronts can improve elongations of the extracted structures, while minimizing the risk of leakage. To that end, for an evolving front using its shape-offset level-set representation, a novel energy functional is defined. It is shown that constrained optimization of this functional results in an anisotropic expansion flow which is usefull for vessel segmentation. We have validated our method using synthetic data sets, 2-D retinal angiogram images and magnetic resonance angiography volumetric data sets. A comparison has been made with two state-of-the-art vessel segmentation methods. Quantitative results, as well as qualitative comparisons of segmentations, indicate that our regularization method is a promising tool to improve the efficiency of both techniques.

3D Axon structure extraction and analysis in confocal fluorescence microscopy images

The morphological properties of axons, such as their branching patterns and oriented structures, are of great interest for biologists in the study of the synaptic connectivity of neurons. In these studies, researchers use triple immunofluorescent confocal microscopy to record morphological changes of neuronal processes. Three-dimensional (3D) microscopy image analysis is then required to extract morphological features of the neuronal structures. In this article, we propose a highly automated 3D centerline extraction tool to assist in this task. For this project, the most difficult part is that some axons are overlapping such that the boundaries distinguishing them are barely visible. Our approach combines a 3D dynamic programming (DP) technique and marker-controlled watershed algorithm to solve this problem. The approach consists of tracking and updating along the navigation directions of multiple axons simultaneously. The experimental results show that the proposed method can rapidly and accurately extract multiple axon centerlines and can handle complicated axon structures such as cross-over sections and overlapping objects.

Automated segmentation of hepatic vessels in non-contrast X-ray CT images

Hepatic-vessel trees are the key structures in the liver. Knowledge of the hepatic-vessel tree is required because it provides information for liver lesion detection in the computer-aided diagnosis (CAD) system. However, hepatic vessels cannot easily be distinguished from other liver tissues in plain CT images. Automated segmentation of hepatic vessels in plain (non-contrast) CT images is a challenging issue. In this paper, an approach to automatic segmentation of hepatic vessels is proposed. The approach consists of two processing steps: enhancement of hepatic vessels and hepatic-vessel extractions. Enhancement of the vessels was performed with two techniques: (1) histogram transformation based on a Gaussian function; (2) multi-scale line filtering based on eigenvalues of a Hessian matrix. After the enhancement of the vessels, candidates of hepatic vessels were extracted by a thresholding method. Small connected regions in the final results were considered as false positives and were removed. This approach was applied to 2 normal-liver cases for whom plain CT images were obtained. Hepatic vessels segmented from the contrast-enhanced CT images of the same patient were used as the ground truth in evaluation of the performance of the proposed approach. The index of separation ratio between the CT number distributions in hepatic vessels and other liver tissue regions was also used in the evaluation. A subjective evaluation of the hepatic-vessel extraction results based on the additional 16 plain CT cases was carried out for a further validation by a radiologist. The preliminary experimental results showed that the proposed method could enhance and segment the hepatic-vessel regions even in plain CT images.

Multiscale active contour model for vessel segmentation

This paper presents a novel multiscale active contour model for vessel segmentation. The model is based on accurate analysis of the vessel structure in the image. According to different scale response of the eigenvalues of local second order derivative (Hessian matrix), a new vessel region information function, which shows a valid estimation of the vesselness measure, is defined. We introduce the posteriori probability estimation into the active contours framework and design a new objective function. The defined objective function is minimized using the variational method, and a new region-based external force is obtained, which is more accurate to the vessel structure and not sensitive to the initial condition. This active contour model combines the obtained region-based and conventional boundary-based force, which aims at finding more accurate vessel edges even when the vessel branches are low contrast or blurry. Furthermore, the proposed model is implemented by an implicit method of level set framework, the solution of which is steady and suitable for various topology changes. Moreover, two new speed functions for vessel segmentation in the level set method are presented, one for fast marching and the other for a narrow-band algorithm. The vessel segmentation experiments compared with previous geometric active contour models are shown on several medical images. The experimental results demonstrate the performance of our approach.

In vitro, nonrigid model of aortic arch aneurysm

PURPOSE

To develop and validate a controlled patient-derived process for producing an in vitro, nonrigid model of aortic arch aneurysm.

MATERIALS AND METHODS

A three-dimensional magnetic resonance (MR) angiogram derived from a patient with an aortic arch aneurysm was segmented by using a homemade software package, meshed and converted to Standard Tessellation Language (STL) file format. The authors transferred this format to a stereolithography machine to produce a replica of the entire aorta, including the arch aneurysm and supraaortic arteries, by pouring silicone rubber.

RESULTS

A sturdy, life-size, soft, transparent plastic cast, accurately reproducing both the internal and external anatomy of the aortic aneurysm, was produced in less than 1 week. Comparison between the STL file format of MR angiographic images of both the patient's aorta and model enabled validation of the reliability of the manufacturing process.

CONCLUSIONS

The combination of easy segmentation and conversion to the STL file format with stereolithography techniques enabled a realistic, life-size, silicone vascular phantom to be created from a live patient imaging dataset.

Clinical validation of three-dimensional tortuosity metrics based on the minimum curvature of approximating polynomial splines

The clinical recognition of abnormal vascular tortuosity is important in the diagnosis of many diseases. Metrics based on three-dimensional (3D) curvature, using approximating polynomial spline-fitting to "data balls" centered along the mid-line of the vessel, minimize digitization errors and give tortuosity values largely independent of the resolution of the imaging system. We applied two of these metrics to a number of clinical vascular systems, using both 2D and 3D datasets. Using abdominal aortograms of low tortuosity, we established their validity by their strong correlation with the ranking of an expert panel of three vascular surgeons. The values of the Spearman rank correlation coefficient between our rankings, using a data ball radius of one-quarter of the local vessel radius, and the average ranking of the expert panel were 0.96 (with a 95% confidence interval of [0.91, 0.99]) for the mean curvature and 0.98 ([0.94, 0.99]) for the root-mean-square (RMS) curvature. These confidence intervals indicate that our automated analysis is producing rankings whose reliability is similar to that of a human expert, and is significantly better than that achieved with existing algorithms. The metrics provided good discrimination between vessels of different tortuosity for both 2D and 3D datasets, and produced values sufficiently discriminating to assess the relative utility of arteries for endoluminal repair of aneurysms.

Immune activation is required for NT-3-induced axonal plasticity in chronic spinal cord injury

After an unilateral lesion of the corticospinal tract (CST) at the level of the medulla over-expression of Neurotrophin-3 (NT-3) in lumbar spinal cord motoneurons induced axonal sprouting of the intact CST in the acutely injured but not uninjured or chronically injured spinal cord in rats. This suggested that processes associated with immune-mediated wound healing may act with NT-3 to induce neuroplasticity. To test whether immune processes were involved we measured NT-3-induced axonal sprouting in immunosuppressed compared to immunocompetent rats. Rats were immunosuppressed with anti-leukocyte antibodies 1 day before receiving a CST lesion and then 2 weeks later NT-3 was over-expressed in the lumbar spinal motoneurons with an adenoviral vector carrying the NT-3 gene targeted to the motoneurons by retrograde transport. At 35 days post-lesion no axonal sprouting was measured in immunosuppressed rats whereas axonal sprouting was measured in the immunocompetent rats. We then tested whether re-evoking an immune response in chronically lesioned rats would induce neuroplasticity. Rats received CST lesions and then 4 months later were treated with systemic injections of lipopolysaccharide (LPS) 7 days before NT-3 was over-expressed in the lumbar spinal motoneurons. Axonal sprouting was observed in the LPS treated rats but not in control animals that were not treated with LPS. Further studies showed that lesioning the CST activated and LPS reactivated microglia and CD4(+) T-cells in the acutely lesioned and chronically lesioned rats, respectively. However, immunosuppression only decreased the number of activated CD4(+) T-cells suggesting they were responsible for the support of axonal growth. These observations demonstrate that processes associated with immune-mediated wound healing play a role in NT-3-induced neuroplasticity after injury.

Automatic centerline extraction of irregular tubular structures using probability volumes from multiphoton imaging

In this paper, we present a general framework for extracting 3D centerlines from volumetric datasets. Unlike the majority of previous approaches, we do not require a prior segmentation of the volume nor we do assume any particular tubular shape. Centerline extraction is performed using a morphology-guided level set model. Our approach consists of: i) learning the structural patterns of a tubular-like object, and ii) estimating the centerline of a tubular object as the path with minimal cost with respect to outward flux in gray level images. Such shortest path is found by solving the Eikonal equation. We compare the performance of our method with existing approaches in synthetic, CT, and multiphoton 3D images, obtaining substantial improvements, especially in the case of irregular tubular objects.

Tagged volume rendering of the heart

We present a novel system for 3-D visualisation of the heart and coronary arteries. Binary tags (generated offline) are combined with value-gradient transfer functions (specified online) allowing for interactive visualisation, while relaxing the offline segmentation criteria. The arteries are roughly segmented using a Hessian-based line filter and the pericardial cavity using a Fast Marching active contour. A comparison of different contour initialisations reveals that simple geometric shapes (such as spheres or extruded polygons) produce suitable results.

Epifluorescence-based quantitative microvasculature remodeling using geodesic level-sets and shape-based evolution

Accurate vessel segmentation is the first step in analysis of microvascular networks for reliable feature extraction and quantitative characterization. Segmentation of epifluorescent imagery of microvasculature presents a unique set of challenges and opportunities compared to traditional angiogram-based vessel imagery. This paper presents a novel system that combines methods from mathematical morphology, differential geometry, and active contours to reliably detect and segment microvasculature under varying background fluorescence conditions. The system consists of three main modules: vessel enhancement, shape-based initialization, and level-set based segmentation. Vessel enhancement deals with image noise and uneven background fluorescence using anisotropic diffusion and mathematical morphology techniques. Shape-based initialization uses features from the second-order derivatives of the enhanced vessel image and produces a coarse ridge (vessel) mask. Geodesic level-set based active contours refine the coarse ridge map and fix possible discontinuities or leakage of the level set contours that may arise from complex topology or high background fluorescence. The proposed system is tested on epifluorescence-based high resolution images of porcine dura mater microvasculature. Preliminary experiments show promising results.

CT and image processing non-invasive indicators of sickle cell secondary pulmonary hypertension

This retrospective study investigates the potential of image analysis to quantify for the presence and extent of pulmonary hypertension secondary to sickle cell disease (SCD). A combination of fast marching and geodesic active contours level sets were employed to segment the pulmonary artery from smoothed CT-Angiography images from 16 SCD patients and 16 matching controls. An algorithm based on fast marching methods was used to compute the centerline of the segmented arteries to measure automatically the diameters of the pulmonary trunk and first branches of the pulmonary arteries. Results show that the pulmonary trunk and arterial branches are significantly larger in diameter in SCD patients as compared to controls (p-values of 0.002 for trunk and 0.0003 for branches). For validation, the results were compared with manually measured values and did not demonstrate significant difference (mean p-values 0.71). CT with image processing shows great potential as a surrogate indicator of pulmonary hemodynamics or response to therapy, which could be an important tool for drug discovery and noninvasive clinical surveillance.

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.

[Automated middle hepatic vessel extraction method using electronic atlas and line enhancement filter on non-contrast torso X-ray CT images]

Classification of the liver region of the Couinaud segment provides significant information for a computer-aided diagnostic system to localize the position of lesions in the liver region. Hepatic vessels provide essential information to classify the liver region of the Couinaud segment. However, automated segmentation and classification of hepatic vessels are difficult in non-contrast CT images owing to the low contrast between hepatic vessels and liver tissue. In this paper, we propose an automated extraction schema for extracting the middle hepatic vein (MHV), and we employ this schema to classify the liver region into right and left lobes. We applied our method to 22 non-contrast X-ray CT images. All of the cases were normal liver cases. The results for the MHV extraction were evaluated using three parameters for the volume ratio to the correct region of liver. The results show that hepatic vessels extracted using the proposed method were found to be satisfactory in 41% (9/22) of cases.

Automatic multiscale enhancement and segmentation of pulmonary vessels in CT pulmonary angiography images for CAD applications

The authors are developing a computerized pulmonary vessel segmentation method for a computer-aided pulmonary embolism (PE) detection system on computed tomographic pulmonary angiography (CTPA) images. Because PE only occurs inside pulmonary arteries, an automatic and accurate segmentation of the pulmonary vessels in 3D CTPA images is an essential step for the PE CAD system. To segment the pulmonary vessels within the lung, the lung regions are first extracted using expectation-maximization (EM) analysis and morphological operations. The authors developed a 3D multiscale filtering technique to enhance the pulmonary vascular structures based on the analysis of eigenvalues of the Hessian matrix at multiple scales. A new response function of the filter was designed to enhance all vascular structures including the vessel bifurcations and suppress nonvessel structures such as the lymphoid tissues surrounding the vessels. An EM estimation is then used to segment the vascular structures by extracting the high response voxels at each scale. The vessel tree is finally reconstructed by integrating the segmented vessels at all scales based on a "connected component" analysis. Two CTPA cases containing PEs were used to evaluate the performance of the system. One of these two cases also contained pleural effusion disease. Two experienced thoracic radiologists provided the gold standard of pulmonary vessels including both arteries and veins by manually tracking the arterial tree and marking the center of the vessels using a computer graphical user interface. The accuracy of vessel tree segmentation was evaluated by the percentage of the "gold standard" vessel center points overlapping with the segmented vessels. The results show that 96.2% (2398/2494) and 96.3% (1910/1984) of the manually marked center points in the arteries overlapped with segmented vessels for the case without and with other lung diseases. For the manually marked center points in all vessels including arteries and veins, the segmentation accuracy are 97.0% (4546/4689) and 93.8% (4439/4732) for the cases without and with other lung diseases, respectively. Because of the lack of ground truth for the vessels, in addition to quantitative evaluation of the vessel segmentation performance, visual inspection was conducted to evaluate the segmentation. The results demonstrate that vessel segmentation using our method can extract the pulmonary vessels accurately and is not degraded by PE occlusion to the vessels in these test cases.

An improved algorithm for vessel centerline tracking in coronary angiograms

For automated visualization and quantification of artery diseases, the accurate determination of the arterial centerline is a prerequisite. Existing tracking-based approaches usually suffer from the inaccuracy, inflexion and discontinuity in the extracted centerlines, and they may even fail in complicated situations. In this paper, an improved algorithm for coronary arterial centerline extraction is proposed, which incorporates a new tracking direction updating scheme, a self-adaptive magnitude of linear extrapolation and a dynamic-size search window for matched filtering. A simulation study is conducted for the determination of the optimal weighting factor which is used to combine the geometrical topology information and intensity distribution information to obtain the proposed tracking direction. Synthetic and clinical examples, representing some difficult situations that may occur in coronary angiograms, are presented. Results show that the proposed algorithm outperforms the conventional methods. By adopting the proposed algorithm, centerlines are successfully extracted under these complicated situations, and with satisfactory accuracy.

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.

Automatic segmentation of 3D micro-CT coronary vascular images

Although there are many algorithms available in the literature aimed at segmentation and model reconstruction of 3D angiographic images, many are focused on characterizing only a part of the vascular network. This study is motivated by the recent emerging prospects of whole-organ simulations in coronary hemodynamics, autoregulation and tissue oxygen delivery for which anatomically accurate vascular meshes of extended scale are highly desirable. The key requirements of a reconstruction technique for this purpose are automation of processing and sub-voxel accuracy. We have designed a vascular reconstruction algorithm which satisfies these two criteria. It combines automatic seeding and tracking of vessels with radius detection based on active contours. The method was first examined through a series of tests on synthetic data, for accuracy in reproduced topology and morphology of the network and was shown to exhibit errors of less than 0.5 voxel for centerline and radius detections, and 3 degrees for initial seed directions. The algorithm was then applied on real-world data of full rat coronary structure acquired using a micro-CT scanner at 20 microm voxel size. For this, a further validation of radius quantification was carried out against a partially rescanned portion of the network at 8 microm voxel size, which estimated less than 10% radius error in vessels larger than 2 voxels in radius.

Segmentation and quantification of human vessels using a 3-D cylindrical intensity model

We introduce a new approach for 3-D segmentation and quantification of vessels. The approach is based on a 3-D cylindrical parametric intensity model, which is directly fitted to the image intensities through an incremental process based on a Kalman filter. Segmentation results are the vessel centerline and shape, i.e., we estimate the local vessel radius, the 3-D position and 3-D orientation, the contrast, as well as the fitting error. We carried out an extensive validation using 3-D synthetic images and also compared the new approach with an approach based on a Gaussian model. In addition, the new model has been successfully applied to segment vessels from 3-D MRA and computed tomography angiography image data. In particular, we compared our approach with an approach based on the randomized Hough transform. Moreover, a validation of the segmentation results based on ground truth provided by a radiologist confirms the accuracy of the new approach. Our experiments show that the new model yields superior results in estimating the vessel radius compared to previous approaches based on a Gaussian model as well as the Hough transform.

Computer-aided detection of colonic polyps at CT colonography using a Hessian matrix-based algorithm: preliminary study

OBJECTIVE

The purpose of our study was to develop a Hessian matrix-based computer-aided detection (CAD) algorithm for polyp detection on CT colonography (CTC) and to analyze its performance in a high-risk population.

SUBJECTS AND METHODS

The CTC data sets of 35 patients with at least one colonoscopically proven polyp were interpreted with a Hessian matrix-based CAD algorithm, which was designed to depict bloblike structures protruding into the lumen. Our gold standard was a combination of segmental unblinded optical colonoscopy and retrospective unblinded consensus review by two radiologists. Sensitivity of CAD for polyp detection was evaluated on both per-polyp and per-patient bases. The average number of false-positive detections was calculated, and the causes of false-positives and false-negatives were analyzed.

RESULTS

Ninety-four polyps were identified on colonoscopy. Forty-six polyps were smaller than 6 mm and 48 were 6 mm or larger. Seventy-five (79.8%) of these 94 polyps were identified by radiologists in a retrospective review. When colonoscopy was used as a standard of reference, the sensitivity of CAD was 77.1% for polyps 6 mm or larger. For large polyps (> or = 6 mm) that could be identified on retrospective review, the CAD algorithm achieved sensitivities of 92.5% (37/40) and 91.7% (22/24), respectively, on per-polyp and per-patient bases. There were an average of 5.5 false-positive detections per patient and 3.1 false-positive detections per data set for CAD. The two most frequent causes of false-positives on CAD were prominent or converging fold (78/191) and feces (50/191). Of the three polyps 6 mm or larger that were missed by CAD, two had a flat appearance on colonoscopy and the remaining one was located in the narrow area between the rectal tube and the rectal wall.

CONCLUSION

A Hessian matrix-based CAD algorithm for CTC has the potential to depict polyps larger than or equal to 6 mm with high sensitivity and an acceptable false-positive rate.

Automated classification of lung bronchovascular anatomy in CT using AdaBoost

Lung CAD systems require the ability to classify a variety of pulmonary structures as part of the diagnostic process. The purpose of this work was to develop a methodology for fully automated voxel-by-voxel classification of airways, fissures, nodules, and vessels from chest CT images using a single feature set and classification method. Twenty-nine thin section CT scans were obtained from the Lung Image Database Consortium (LIDC). Multiple radiologists labeled voxels corresponding to the following structures: airways (trachea to 6th generation), major and minor lobar fissures, nodules, and vessels (hilum to peripheral), and normal lung parenchyma. The labeled data was used in conjunction with a supervised machine learning approach (AdaBoost) to train a set of ensemble classifiers. Each ensemble classifier was trained to detect voxels part of a specific structure (either airway, fissure, nodule, vessel, or parenchyma). The feature set consisted of voxel attenuation and a small number of features based on the eigenvalues of the Hessian matrix (used to differentiate structures by shape). When each ensemble classifier was composed of 20 weak classifiers, the AUC values for the airway, fissure, nodule, vessel, and parenchyma classifiers were 0.984+/-0.011, 0.949+/-0.009, 0.945+/-0.018, 0.953+/-0.016, and 0.931+/-0.015, respectively. The strong results suggest that this could be an effective input to higher-level anatomical based segmentation models with the potential to improve CAD performance.

Pulmonary nodule registration in serial CT scans based on rib anatomy and nodule template matching

An automated method is being developed in order to identify corresponding nodules in serial thoracic CT scans for interval change analysis. The method uses the rib centerlines as the reference for initial nodule registration. A spatially adaptive rib segmentation method first locates the regions where the ribs join the spine, which define the starting locations for rib tracking. Each rib is tracked and locally segmented by expectation-maximization. The ribs are automatically labeled, and the centerlines are estimated using skeletonization. For a given nodule in the source scan, the closest three ribs are identified. A three-dimensional (3D) rigid affine transformation guided by simplex optimization aligns the centerlines of each of the three rib pairs in the source and target CT volumes. Automatically defined control points along the centerlines of the three ribs in the source scan and the registered ribs in the target scan are used to guide an initial registration using a second 3D rigid affine transformation. A search volume of interest (VOI) is then located in the target scan. Nodule candidate locations within the search VOI are identified as regions with high Hessian responses. The initial registration is refined by searching for the maximum cross-correlation between the nodule template from the source scan and the candidate locations. The method was evaluated on 48 CT scans from 20 patients. Experienced radiologists identified 101 pairs of corresponding nodules. Three metrics were used for performance evaluation. The first metric was the Euclidean distance between the nodule centers identified by the radiologist and the computer registration, the second metric was a volume overlap measure between the nodule VOIs identified by the radiologist and the computer registration, and the third metric was the hit rate, which measures the fraction of nodules whose centroid computed by the computer registration in the target scan falls within the VOI identified by the radiologist. The average Euclidean distance error was 2.7 +/- 3.3 mm. Only two pairs had an error larger than 10 mm. The average volume overlap measure was 0.71 +/- 0.24. Eighty-three of the 101 pairs had ratios larger than 0.5, and only two pairs had no overlap. The final hit rate was 93/101.

Bone enhancement filtering: application to sinus bone segmentation and simulation of pituitary surgery

The simulation of pituitary gland surgery requires a precise classification of soft tissues, vessels and bones. Bone structures tend to be thin and have diffuse edges in CT data, and thus the common method of thresholding can produce incomplete segmentations. In this paper, we present a novel multi-scale sheet enhancement measure and apply it to paranasal sinus bone segmentation. The measure uses local shape information obtained from an eigenvalue decomposition of the Hessian matrix. It attains a maximum in the middle of a sheet, and also provides local estimates of its width and orientation. These estimates are used to create a vector field orthogonal to bone boundaries, so that a flux maximizing flow algorithm can be applied to recover them. Hence, the sheetness measure has the essential properties to be incorporated into the computation of anatomical models for the simulation of pituitary surgery, enabling it to better account for the presence of sinus bones. We validate the approach quantitatively on synthetic examples, and provide comparisons with existing segmentation techniques on paranasal sinus CT data.

Detection of Cerebral Vessels in MRA Using 3D Steerable Filters

This paper describes a fully automatic method for enhancement and segmentation of three-dimensional(3D) cerebral vessels in MRA. We obtain the 3D dyadic B-spline wavelets by extending corresponding 1D wavelet. A 3D steerable filter is then developed based on 3D dyadic B-spline wavelets. One can adaptively steer the filter to an arbitrary direction. The oriented energy of filter response is introduced for detecting orientation strength of vessels in that direction. The points with maximum of local oriented energy across multiple scales are regarded as vessel points. This method was tested on real MRA data and promising results have been obtained. It could be suitable for other types of curvilinear structures such as cardiovascular vessels, bronchial tree.

Extraction of brain vessels from magnetic resonance angiographic images: concise literature review, challenges, and proposals

The automated extraction of brain vessels from magnetic resonance angiography (MRA) has found its applications in vascular disease diagnosis, endovascular operation and neurosurgical planning. In this paper we first present a concise technical review on cerebral vasculature extraction from MRA. It reveals the latest development in the area of vessel extraction. Then we detail the main challenges to the researchers working in the vessel extraction and segmentation area. Based on the review and our experience in the area, we finally present our proposals on ways of developing robust vessel extracting algorithm. Examples of brain vasculature extracted with advanced hybrid approach are shown. Twenty one references are given.

Automated neurite extraction using dynamic programming for high-throughput screening of neuron-based assays

High-throughput screening (HTS) of cell-based assays has recently emerged as an important tool of drug discovery. The analysis and modeling of HTS microscopy neuron images, however, is particularly challenging. In this paper we present a novel algorithm for extraction and quantification of neurite segments from HTS neuron images. The algorithm is designed to be able to detect and link neurites even with complex neuronal structures and of poor imaging quality. Our proposed algorithm automatically detects initial seed points on a set of grid lines and estimates the ending points of the neurite by iteratively tracing the centerline points along the line path representing the neurite segment. The live-wire method is then applied to link the seed points and the corresponding ending points using dynamic programming techniques, thus enabling the extraction of the centerlines of the neurite segments accurately and robustly against noise, discontinuity, and other image artifacts. A fast implementation of our algorithm using dynamic programming is also provided in the paper. Any thin neurite and its segments with low intensity contrast can be well preserved by detecting the starting and ending points of the neurite. All these properties make the proposed algorithm attractive for high-throughput screening of neuron-based assays.