Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction

Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures

Motivated by the goals of improving detection of low-contrast and narrow vessels and eliminating false detections at nonvascular structures, a new technique is presented for extracting vessels in retinal images. The core of the technique is a new likelihood ratio test that combines matched-filter responses, confidence measures and vessel boundary measures. Matched filter responses are derived in scale-space to extract vessels of widely varying widths. A vessel confidence measure is defined as a projection of a vector formed from a normalized pixel neighborhood onto a normalized ideal vessel profile. Vessel boundary measures and associated confidences are computed at potential vessel boundaries. Combined, these responses form a six-dimensional measurement vector at each pixel. A training technique is used to develop a mapping of this vector to a likelihood ratio that measures the "vesselness" at each pixel. Results comparing this vesselness measure to matched filters alone and to measures based on the Hessian of intensities show substantial improvements, both qualitatively and quantitatively. The Hessian can be used in place of the matched filter to obtain similar but less-substantial improvements or to steer the matched filter by preselecting kernel orientations. Finally, the new vesselness likelihood ratio is embedded into a vessel tracing framework, resulting in an efficient and effective vessel centerline extraction algorithm.

Model-based automated extraction of microtubules from electron tomography volume

We propose a model-based automated approach to extracting microtubules from noisy electron tomography volume. Our approach consists of volume enhancement, microtubule localization, and boundary segmentation to exploit the unique geometric and photometric properties of microtubules. The enhancement starts with an anisotropic invariant wavelet transform to enhance the microtubules globally, followed by a three-dimensional (3-D) tube-enhancing filter based on Weingarten matrix to further accentuate the tubular structures locally. The enhancement ends with a modified coherence-enhancing diffusion to complete the interruptions along the microtubules. The microtubules are then localized with a centerline extraction algorithm adapted for tubular objects. To perform segmentation, we novelly modify and extend active shape model method. We first use 3-D local surface enhancement to characterize the microtubule boundary and improve shape searching by relating the boundary strength with the weight matrix of the searching error. We then integrate the active shape model with Kalman filtering to utilize the longitudinal smoothness along the microtubules. The segmentation improved in this way is robust against missing boundaries and outliers that are often present in the tomography volume. Experimental results demonstrate that our automated method produces results close to those by manual process and uses only a fraction of the time of the latter.

Robust detection and classification of longitudinal changes in color retinal fundus images for monitoring diabetic retinopathy

A fully automated approach is presented for robust detection and classification of changes in longitudinal time-series of color retinal fundus images of diabetic retinopathy. The method is robust to: 1) spatial variations in illumination resulting from instrument limitations and changes both within, and between patient visits; 2) imaging artifacts such as dust particles; 3) outliers in the training data; 4) segmentation and alignment errors. Robustness to illumination variation is achieved by a novel iterative algorithm to estimate the reflectance of the retina exploiting automatically extracted segmentations of the retinal vasculature, optic disk, fovea, and pathologies. Robustness to dust artifacts is achieved by exploiting their spectral characteristics, enabling application to film-based, as well as digital imaging systems. False changes from alignment errors are minimized by subpixel accuracy registration using a 12-parameter transformation that accounts for unknown retinal curvature and camera parameters. Bayesian detection and classification algorithms are used to generate a color-coded output that is readily inspected. A multiobserver validation on 43 image pairs from 22 eyes involving nonproliferative and proliferative diabetic retinopathies, showed a 97% change detection rate, a 3% miss rate, and a 10% false alarm rate. The performance in correctly classifying the changes was 99.3%. A self-consistency metric, and an error factor were developed to measure performance over more than two periods. The average self consistency was 94% and the error factor was 0.06%. Although this study focuses on diabetic changes, the proposed techniques have broader applicability in ophthalmology.

Automated extraction of fine features of kinetochore microtubules and plus-ends from electron tomography volume

Kinetochore microtubules (KMTs) and the associated plus-ends have been areas of intense investigation in both cell biology and molecular medicine. Though electron tomography opens up new possibilities in understanding their function by imaging their high-resolution structures, the interpretation of the acquired data remains an obstacle because of the complex and cluttered cellular environment. As a result, practical segmentation of the electron tomography data has been dominated by manual operation, which is time consuming and subjective. In this paper, we propose a model-based automated approach to extracting KMTs and the associated plus-ends with a coarse-to-fine scale scheme consisting of volume preprocessing, microtubule segmentation and plus-end tracing. In volume preprocessing, we first apply an anisotropic invariant wavelet transform and a tube-enhancing filter to enhance the microtubules at coarse level for localization. This is followed with a surface-enhancing filter to accentuate the fine microtubule boundary features. The microtubule body is then segmented using a modified active shape model method. Starting from the segmented microtubule body, the plus-ends are extracted with a probabilistic tracing method improved with rectangular window based feature detection and the integration of multiple cues. Experimental results demonstrate that our automated method produces results comparable to manual segmentation but using only a fraction of the manual segmentation time.

Pulmonary fissure segmentation on CT

A pulmonary fissure is a boundary between the lobes in the lungs. Its segmentation is of clinical interest as it facilitates the assessment of lung disease on a lobar level. This paper describes a new approach for segmenting the major fissures in both lungs on thin-section computed tomography (CT). An image transformation called "ridge map" is proposed for enhancing the appearance of fissures on CT. A curve-growing process, modeled by a Bayesian network, is described that is influenced by both the features of the ridge map and prior knowledge of the shape of the fissure. The process is implemented in an adaptive regularization framework that balances these influences and reflects the causal dependencies in the Bayesian network using an entropy measure. The method effectively alleviates the problem of inappropriate weights of regularization terms, an effect that can occur with static regularization methods. The method was applied to segment and visualize the lobes of the lungs on chest CT of 10 patients with pulmonary nodules. Only 78 out of 3286 left or right lung regions with fissures (2.4%) required manual correction. The average distance between the automatically segmented and the manually delineated "ground-truth" fissures was 1.01 mm, which was similar to the average distance of 1.03 mm between two sets of manually segmented fissures. The method has a linear-time worst-case complexity and segments the upper lung from the lower lung on a standard computer in less than 5 min.

Coronary vessel trees from 3D imagery: a topological approach

We propose a simple method for reconstructing vascular trees from 3D images. Our algorithm extracts persistent maxima of the intensity on all axis-aligned 2D slices of the input image. The maxima concentrate along 1D intensity ridges, in particular along blood vessels. We build a forest connecting the persistent maxima with short edges. The forest tends to approximate the blood vessels present in the image, but also contains numerous spurious features and often fails to connect segments belonging to one vessel in low contrast areas. We improve the forest by applying simple geometric filters that trim short branches, fill gaps in blood vessels and remove spurious branches from the vascular tree to be extracted. Experiments show that our technique can be applied to extract coronary trees from heart CT scans.

Automatic mammary duct detection in 3D ultrasound

This paper presents a method for the initial detection of ductal structures within 3D ultrasound images using second-order shape measurements. The desire to detect ducts is motivated in a number of way, principally as step in the detection and assessment of ductal carcinoma in-situ. Detection is performed by measuring the variation of the local second-order shape from a prototype shape corresponding to a perfect tube. We believe this work is the first demonstration of the ability to detect sections of duct automatically in ultrasound images. The detection is performed with a view to employing vessel tracking method to delineate the full ductal structure.

Comparison of simultaneous and sequential two-view registration for 3D/2D registration of vascular images

Accurate 3D/2D vessel registration is complicated by issues of image quality, occlusion, and other problems. This study performs a quantitative comparison of 3D/2D vessel registration in which vessels segmented from preoperative CT or MR are registered with biplane x-ray angiograms by either a) simultaneous two-view registration with advance calculation of the relative pose of the two views, or b) sequential registration with each view. We conclude on the basis of phantom studies that, even in the absence of image errors, simultaneous two-view registration is more accurate than sequential registration. In more complex settings, including clinical conditions, the relative accuracy of simultaneous two-view registration is even greater.

Automatic vascular tree formation using the Mahalanobis distance

We present a novel technique for the automatic formation of vascular trees from segmented tubular structures. Our method combines a minimum spanning tree algorithm with a minimization criterion of the Mahalanobis distance. First, a multivariate class of connected junctions is defined using a set of trained vascular trees and their corresponding image volumes. Second, a minimum spanning tree algorithm forms the tree using the Mahalanobis distance of each connection from the "connected" class as a cost function. Our technique allows for the best combination of the discrimination criteria between connected and non-connected junctions and is also modality, organ and segmentation specific.

Augmented vessels for quantitative analysis of vascular abnormalities and endovascular treatment planning

Endovascular treatment plays an important role in the minimally invasive treatment of patients with vascular diseases, a major cause of morbidity and mortality worldwide. Given a segmentation of an angiography, quantitative analysis of abnormal structures can aid radiologists in choosing appropriate treatments and apparatuses. However, effective quantitation is only attainable if the abnormalities are identified from the vasculature. To achieve this, a novel method is developed, which works on the simpler shape of normal vessels to identify different vascular abnormalities (viz. stenotic atherosclerotic plaque, and saccular and fusiform aneurysmal lumens) in an indirect fashion, instead of directly manipulating the complex-shaped abnormalities. The proposed method has been tested on three synthetic and 17 clinical data sets. Comparisons with two related works are also conducted. Experimental results show that our method can produce satisfactory identification of the abnormalities and approximations of the ideal post-treatment vessel lumens. In addition, it can help increase the repeatability of the measurement of clinical parameters significantly.

Segmentation of volumetric MRA images by using capillary active contour

Precise segmentation of three-dimensional (3D) magnetic resonance angiography (MRA) images can be a very useful computer aided diagnosis (CAD) tool for clinical routines. Level sets based evolution schemes, which have been shown to be effective and easy to implement for many segmentation applications, are being applied to MRA data sets. In this paper, we present a segmentation scheme for accurately extracting vasculature from MRA images. Our proposed algorithm models capillary action and derives a capillary active contour for segmentation of thin vessels. The algorithm is implemented using the level set method and has been applied successfully on real 3D MRA images. Compared with other state-of-the-art MRA segmentation algorithms, experiments show that our method facilitates more accurate segmentation of thin blood vessels.

CT angiography of peripheral arterial bypass grafts: Accuracy and time-effectiveness of quantitative image analysis with an automated software tool

RATIONALE AND OBJECTIVES

Qualitative analysis of computed tomography (CT) angiography data often is limited by intra- and interobserver variability. The purpose of this study was to evaluate the time-effectiveness and accuracy of a quantitative CT angiography data analysis using automated software in comparison with qualitative axial and coronal CT image reading in patients with peripheral bypass grafts.

MATERIALS AND METHODS

Twenty-eight patients with 33 saphenous bypass grafts underwent 4-channel (n = 21) and 16-channel (n = 7) CT angiography. Two readers evaluated in consensus the CT data qualitatively on axial and coronal reconstructions and with the software regarding the presence of graft stenoses, aneurysmal changes, and arteriovenous fistulas. The time for data analysis was taken and the accuracy was compared with the results from digital subtraction angiography (DSA).

RESULTS

No significant difference was present between data analysis time using axial and coronal CT images (4.9 +/- 1.5 minutes) and when using the software tool (5.5 +/- 1.4 minutes). Good (kappa = 0.652) to excellent (kappa = 1.000) intermodality agreement was present between qualitative and quantitative CT analysis regarding graft-related abnormalities. Sensitivity and specificity for diagnosing stenoses, aneurysms, and fistula did not differ significantly (P > .025) between qualitative CT image reading and the automated software tool.

CONCLUSIONS

CT angiography analysis of peripheral bypass grafts using an automated software tool is similar regarding time-effectiveness and accuracy when compared with qualitative CT data analysis on axial and coronal images. It may assist in determining the significance of an abnormality and can yield objective morphometric data of vessel calibers.

Magnetic resonance angiography: From anatomical knowledge modeling to vessel segmentation

Magnetic resonance angiography (MRA) has become a common way to study cerebral vascular structures. Indeed, it enables to obtain information on flowing blood in a totally non-invasive and non-irradiant fashion. MRA exams are generally performed for three main applications: detection of vascular pathologies, neurosurgery planning, and vascular landmark detection for brain functional analysis. This large field of applications justifies the necessity to provide efficient vessel segmentation tools. Several methods have been proposed during the last fifteen years. However, the obtained results are still not fully satisfying. A solution to improve brain vessel segmentation from MRA data could consist in integrating high-level a priori knowledge in the segmentation process. A preliminary attempt to integrate such knowledge is proposed here. It is composed of two methods devoted to phase contrast MRA (PC MRA) data. The first method is a cerebral vascular atlas creation process, composed of three steps: knowledge extraction, registration, and data fusion. Knowledge extraction is performed using a vessel size determination algorithm based on skeletonization, while a topology preserving non-rigid registration method is used to fuse the information into the atlas. The second method is a segmentation process involving adaptive sets of gray-level hit-or-miss operators. It uses anatomical knowledge modeled by the cerebral vascular atlas to adapt the parameters of these operators (number, size, and orientation) to the searched vascular structures. These two methods have been tested by creating an atlas from a 18 MRA database, and by using it to segment 30 MRA images, comparing the results to those obtained from a region-growing segmentation method.

Computer analysis of computed tomography scans of the lung: a survey

Current computed tomography (CT) technology allows for near isotropic, submillimeter resolution acquisition of the complete chest in a single breath hold. These thin-slice chest scans have become indispensable in thoracic radiology, but have also substantially increased the data load for radiologists. Automating the analysis of such data is, therefore, a necessity and this has created a rapidly developing research area in medical imaging. This paper presents a review of the literature on computer analysis of the lungs in CT scans and addresses segmentation of various pulmonary structures, registration of chest scans, and applications aimed at detection, classification and quantification of chest abnormalities. In addition, research trends and challenges are identified and directions for future research are discussed.

Level set based cerebral vasculature segmentation and diameter quantification in CT angiography

A level set based method is presented for cerebral vascular tree segmentation from computed tomography angiography (CTA) data. The method starts with bone masking by registering a contrast enhanced scan with a low-dose mask scan in which the bone has been segmented. Then an estimate of the background and vessel intensity distributions is made based on the intensity histogram which is used to steer the level set to capture the vessel boundaries. The relevant parameters of the level set evolution are optimized using a training set. The method is validated by a diameter quantification study which is carried out on phantom data, representing ground truth, and 10 patient data sets. The results are compared to manually obtained measurements by two expert observers. In the phantom study, the method achieves similar accuracy as the observers, but is unbiased whereas the observers are biased, i.e., the results are 0.00+/-0.23 vs. -0.32+/-0.23 mm. Also, the method's reproducibility is slightly better than the inter-and intra-observer variability. In the patient study, the method is in agreement with the observers and also, the method's reproducibility -0.04+/-0.17 mm is similar to the inter-observer variability 0.06+/-0.17 mm. Since the method achieves comparable accuracy and reproducibility as the observers, and since the method achieves better performance than the observers with respect to ground truth, we conclude that the level set based vessel segmentation is a promising method for automated and accurate CTA diameter quantification.

2D-3D registration of coronary angiograms for cardiac procedure planning and guidance

We present a completely automated 2D-3D registration technique that accurately maps a patient-specific heart model, created from preoperative images, to the patient's orientation in the operating room. This mapping is based on the registration of preoperatively acquired 3D vascular data with intraoperatively acquired angiograms. Registration using both single and dual-plane angiograms is explored using simulated but realistic datasets that were created from clinical images. Heart deformations and cardiac phase mismatches are taken into account in our validation using a digital 4D human heart model. In an ideal situation where the pre- and intraoperative images were acquired at identical time points within the cardiac cycle, the single-plane and the dual-plane registrations resulted in 3D root-mean-square (rms) errors of 1.60 +/- 0.21 and 0.53 +/- 0.08 mm, respectively. When a 10% timing offset was added between the pre- and the intraoperative acquisitions, the single-plane registration approach resulted in inaccurate registrations in the out-of-plane axis, whereas the dual-plane registration exhibited a 98% success rate with a 3D rms error of 1.33 +/- 0.28 mm. When all potential sources of error were included, namely, the anatomical background, timing offset, and typical errors in the vascular tree reconstruction, the dual-plane registration performed at 94% with an accuracy of 2.19 +/- 0.77 mm.

Statistical cerebrovascular segmentation in three-dimensional rotational angiography based on maximum intensity projections

Segmentation of three-dimensional rotational angiography (3D-RA) can provide quantitative 3D morphological information of vasculature. The expectation maximization-(EM-) based segmentation techniques have been widely used in the medical image processing community, because of the implementation simplicity, and computational efficiency of the approach. In a brain 3D-RA, vascular regions usually occupy a very small proportion (around 1%) inside an entire image volume. This severe imbalance between the intensity distributions of vessels and background can lead to inaccurate statistical modeling in the EM-based segmentation methods, and thus adversely affect the segmentation quality for 3D-RA. In this paper we present a new method for the extraction of vasculature in 3D-RA images. The new method is fully automatic and computationally efficient. As compared with the original 3D-RA volume, there is a larger proportion (around 20%) of vessels in its corresponding maximum intensity projection (MIP) image. The proposed method exploits this property to increase the accuracy of statistical modeling with the EM algorithm. The algorithm takes an iterative approach to compiling the 3D vascular segmentation progressively with the segmentation of MIP images along the three principal axes, and use a winner-takes-all strategy to combine the results obtained along individual axes. Experimental results on 12 3D-RA clinical datasets indicate that the segmentations obtained by the new method exhibit a high degree of agreement to the ground truth segmentations and are comparable to those produced by the manual optimal global thresholding method.

Virtual Contrast for Coronary Vessels Based on Level Set Generated Subvoxel Accurate Centerlines

We present a tool for tracking coronary vessels in MRI scans of the human heart to aid in the screening of heart diseases. The vessels are identified through a single click inside each vessel present in a standard orthogonal view. The vessel identification results from a series of computational steps including eigenvalue analysis of the Hessian of the MRI image followed by a level set-based extraction of the vessel centerline. All identified vessels are highlighted using a virtual contrast agent and displayed simultaneously in a spherical curved reformation view. In cases of over segmentation, the vessel traces can be shortened by a click on each vessel end point. Intermediate analysis results of the vessel computation steps can be displayed as well. We successfully validated the tool on 40 MRI scans demonstrating accuracy and significant time savings over manual vessel tracing.

Towards an automatic coronary artery segmentation algorithm

A method is presented that aims at minimizing image processing time during X-ray fluoroscopy interventions. First, an automatic frame extraction algorithm is proposed in order to extract relevant image frames with respect to their cardiac phase (systole or diastole). Secondly, a 4-step filter is suggested in order to enhance vessel contours. The reciprocal of the enhanced image is used as an alternative speed function to initialize the fast marching method. The complete algorithm was tested on eight clinical angiographic data sets and comparisons with two other vessel enhancement filters (Lorenz and Frangi) are made for the centerline extraction procedure. In order to assess the suitability of our filter the extracted centerline coordinates are compared with the manually traced axis.

Automatic detection of three-dimensional vascular tree centerlines and bifurcations in high-resolution magnetic resonance angiography

OBJECTIVES

We sought to develop a simple and robust algorithm capable of automatically detecting centerlines and bifurcations of a three-dimensional (3D) vascular bed.

MATERIALS AND METHODS

After necessary preprocessing, an appropriate cost function is computed for all vessel voxels and Dijkstra's minimum-cost-path algorithm is implemented. By back tracing all the minimum-cost paths, centerlines and bifurcation are detected. The detected paths are then split into segments between adjacent nodes (bifurcations or vessel end-points) and smoothed by curve fitting.

RESULTS

Application of the algorithm to both simulated 3D vessels and 3D magnetic resonance angiography (MRA) images of an actual intracranial arterial tree produced well-centered vessel skeletons. Quantitative assessment of the algorithm was performed. For the simulated data, the root mean square error for centerline detection is about half a voxel. For the human intracranial MRA data, the sensitivity, positive predictive value (PPV), and accuracy of bifurcation detection were calculated for different cost functions. The best case gave a sensitivity of 91.4%, a PPV of 91.4%, and an RMS error of 1.7 voxels.

CONCLUSIONS

To the extent that imperfections are eliminated from the segmented image, the algorithm is effective and robust in automatic and accurate detection of centerlines and bifurcations. The cost function and algorithm used are demonstrated to be an improvement over similar algorithms in the literature.

Magnetic resonance angiography visualization of abnormal tumor vasculature in genetically engineered mice

Previous research on the vasculature of tumor-bearing animals has focused upon the microvasculature. Magnetic resonance angiography (MRA) offers a noninvasive, complementary approach that provides information about larger vessels. Quantitative analysis of MRA images of spontaneous preclinical tumor models has not been previously reported. Eleven TgT121;p53+/- mice, which invariably develop choroid plexus carcinoma (CPC), and nine age-matched healthy controls were imaged using T1, T2, and a high-resolution three-dimensional time-of-flight MRA sequences at 3 T. Tumors and vessels were segmented to determine tumor volume and vascular attributes, including number of terminal branches, vessel count, and the average vessel radii of MRA-visible vessels within the tumor. Differences in the vasculature between tumor-bearing animals and healthy controls were analyzed statistically. Although the spatial resolution of MRA prohibits visualization of capillaries, a high density of intratumor blood vessels was visualized in CPC mice. A significant increase in terminal branch count and vessel count, but not average vessel radius, was observed in CPCs when compared with normal controls. Both terminal branch count and vessel count were highly correlated with tumor volume. This study represents the first MRA analysis of a spontaneous preclinical brain tumor model. Although the spatial resolution of MRA is less than histologic analysis, MRA-obtained vascular attributes provide useful information with full brain coverage. We show that consistent tumor vasculature properties can be determined by MRA. Such methods are critical for developing preclinical therapeutic testing and will help guide the development of human brain tumor analyses.

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.

Vessel tortuosity and brain tumor malignancy: a blinded study

RATIONALE AND OBJECTIVES

Malignancy provokes regional changes to vessel shape. Characteristic vessel tortuosity abnormalities appear early during tumor development, affect initially healthy vessels, spread beyond the confines of tumor margins, and do not simply mirror tissue perfusion. The ability to detect and quantify tortuosity abnormalities on high-resolution magnetic resonance angiography (MRA) images offers a new approach to the noninvasive diagnosis of malignancy. This report evaluates a computerized, statistical method of analyzing the shapes of vessels extracted from MRA in diagnosing cancer.

MATERIALS AND METHODS

The regional vasculature of 34 healthy subjects was compared with the tumor-associated vasculature of 30 brain tumors before surgical resection. The operator performing the analysis was blinded to the diagnosis. Vessels were segmented from an MRA of each subject, a region of interest was defined in each tumor patient and was mapped to all healthy controls, and a statistical analysis of vessel shape measures was then performed over the region of interest. Many difficult cases were included, such as pinpoint, hemorrhagic, and irradiated tumors, as were hypervascular benign tumors. Tumors were identified as benign or malignant on the basis of histological evaluation.

RESULTS

A discriminant analysis performed at the study's conclusion successfully classified all but one of the 30 tumors as benign or malignant on the basis of vessel tortuosity.

CONCLUSIONS

Quantitative, statistical measures of vessel shape offer a new approach to the diagnosis and staging of disease. Although the methods developed under the current report must be tested against a new series of cases, initial results are promising.

Evaluation of an improved technique for automated center lumen line definition in cardiovascular image data

The aim of the study was to evaluate a new method for automated definition of a center lumen line in vessels in cardiovascular image data. This method, called VAMPIRE, is based on improved detection of vessel-like structures. A multiobserver evaluation study was conducted involving 40 tracings in clinical CTA data of carotid arteries to compare VAMPIRE with an established technique. This comparison showed that VAMPIRE yields considerably more successful tracings and improved handling of stenosis, calcifications, multiple vessels, and nearby bone structures. We conclude that VAMPIRE is highly suitable for automated definition of center lumen lines in vessels in cardiovascular image data.

Automated curved planar reformation of 3D spine images

Traditional techniques for visualizing anatomical structures are based on planar cross-sections from volume images, such as images obtained by computed tomography (CT) or magnetic resonance imaging (MRI). However, planar cross-sections taken in the coordinate system of the 3D image often do not provide sufficient or qualitative enough diagnostic information, because planar cross-sections cannot follow curved anatomical structures (e.g. arteries, colon, spine, etc). Therefore, not all of the important details can be shown simultaneously in any planar cross-section. To overcome this problem, reformatted images in the coordinate system of the inspected structure must be created. This operation is usually referred to as curved planar reformation (CPR). In this paper we propose an automated method for CPR of 3D spine images, which is based on the image transformation from the standard image-based to a novel spine-based coordinate system. The axes of the proposed spine-based coordinate system are determined on the curve that represents the vertebral column, and the rotation of the vertebrae around the spine curve, both of which are described by polynomial models. The optimal polynomial parameters are obtained in an image analysis based optimization framework. The proposed method was qualitatively and quantitatively evaluated on five CT spine images. The method performed well on both normal and pathological cases and was consistent with manually obtained ground truth data. The proposed spine-based CPR benefits from reduced structural complexity in favour of improved feature perception of the spine. The reformatted images are diagnostically valuable and enable easier navigation, manipulation and orientation in 3D space. Moreover, reformatted images may prove useful for segmentation and other image analysis tasks.

Region-growing segmentation of brain vessels: an atlas-based automatic approach

PURPOSE

To propose an atlas-based method that uses both phase and magnitude images to integrate anatomical information in order to improve the segmentation of blood vessels in cerebral phase-contrast magnetic resonance angiography (PC-MRA).

MATERIAL AND METHODS

An atlas of the whole head was developed to store the anatomical information. The atlas divides a magnitude image into several vascular areas, each of which has specific vessel properties. It can be applied to any magnitude image of an entire or nearly entire head by deformable matching, which helps to segment blood vessels from the associated phase image. The segmentation method used afterwards consists of a topology-preserving, region-growing algorithm that uses adaptive threshold values depending on the current region of the atlas. This algorithm builds the arterial and venous trees by iteratively adding voxels that are selected according to their grayscale value and the variation of values in their neighborhood. The topology preservation is guaranteed because only simple points are selected during the growing process.

RESULTS

The method was performed on 40 PC-MRA images of the brain. The results were validated using maximum-intensity projection (MIP) and three-dimensional surface rendering visualization, and compared with results obtained with two non-atlas-based methods.

CONCLUSION

The results show that the proposed method significantly improves the segmentation of cerebral vascular structures from PC-MRA. These experiments tend to prove that the use of vascular atlases is an effective way to optimize vessel segmentation of cerebral images.

Algorithms for automated oximetry along the retinal vascular tree from dual-wavelength fundus images

We present an automated method to perform accurate, rapid, and objective measurement of the blood oxygen saturation over each segment of the retinal vascular hierarchy from dual-wavelength fundus images. Its speed and automation (2 s per entire image versus 20 s per segment for manual methods) enables detailed level-by-level measurements over wider areas. An automated tracing algorithm is used to estimate vessel centerlines, thickness, directions, and locations of landmarks such as bifurcations and crossover points. The hierarchical structure of the vascular network is recovered from the trace fragments and landmarks by a novel algorithm. Optical densities (OD) are measured from vascular segments using the minimum reflected intensities inside and outside the vessel. The OD ratio (ODR=OD600/OD570) bears an inverse relationship to systemic HbO2 saturation (SO2). The sensitivity for detecting saturation change when breathing air versus pure oxygen was calculated from the measurements made on six subjects and was found to be 0.0226 ODR units, which is in good agreement with previous manual measurements by the dual-wavelength technique, indicating the validity of the automation. A fully automated system for retinal vessel oximetry would prove useful to achieve early assessments of risk for progression of disease conditions associated with oxygen utilization.

3D stereo interactive medical visualization

Transjugular intrahepatic portosystemic shunt formation (TIPS) is an effective treatment for portal hypertension [LaBerge 1995]. The procedure requires the insertion of a needle through the liver to connect the hepatic and portal veins. This operation is traditionally guided by fluoroscopic images that do not show the location of the target veins during needle insertion. We propose to provide the clinician an interactive, three-dimensional (3D), stereo display so that the position and orientation of the clinician’s needle can be seen relative to the target vasculature intraoperatively. This paper describes the visualizations we are providing for intraoperative guidance.

Automatic selection of parameters for vessel/neurite segmentation algorithms

An automated method is presented for selecting optimal parameter settings for vessel/neurite segmentation algorithms using the minimum description length principle and a recursive random search algorithm. It trades off a probabilistic measure of image-content coverage against its conciseness. It enables nonexpert users to select parameter settings objectively, without knowledge of underlying algorithms, broadening the applicability of the segmentation algorithm, and delivering higher morphometric accuracy. It enables adaptation of parameters across batches of images. It simplifies the user interface to just one optional parameter and reduces the cost of technical support. Finally, the method is modular, extensible, and amenable to parallel computation. The method is applied to 223 images of human retinas and cultured neurons, from four different sources, using a single segmentation algorithm with eight parameters. Improvements in segmentation quality compared to default settings using 1000 iterations ranged from 4.7%-21%. Paired t-tests showed that improvements are statistically significant (p < 0.0005). Most of the improvement occurred in the first 44 iterations. Improvements in description lengths and agreement with the ground truth were strongly correlated (p = 0.78).

Quantitative analysis of pulmonary airway tree structures

A method for computationally efficient skeletonization of three-dimensional tubular structures is reported. The method is specifically targeting skeletonization of vascular and airway tree structures in medical images but it is general and applicable to many other skeletonization tasks. The developed approach builds on the following novel concepts and properties: fast curve-thinning algorithm to increase computational speed, endpoint re-checking to avoid generation of spurious side branches, depth-and-length sensitive pruning, and exact tree-branch partitioning allowing branch volume and surface measurements. The method was validated in computer and physical phantoms and in vivo CT scans of human lungs. The validation studies demonstrated sub-voxel accuracy of branch point positioning, insensitivity to changes of object orientation, and high reproducibility of derived quantitative indices of the tubular structures offering a significant improvement over previously reported methods (p<<0.001).

Analyzing attributes of vessel populations

Almost all diseases affect blood vessel attributes (vessel number, radius, tortuosity, and branching pattern). Quantitative measurement of vessel attributes over relevant vessel populations could thus provide an important means of diagnosing and staging disease. Unfortunately, little is known about the statistical properties of vessel attributes. In particular, it is unclear whether vessel attributes fit a Gaussian distribution, how dependent these values are upon anatomical location, and how best to represent the attribute values of the multiple vessels comprising a population of interest in a single patient. The purpose of this report is to explore the distributions of several vessel attributes over vessel populations located in different parts of the head. In 13 healthy subjects, we extract vessels from MRA data, define vessel trees comprising the anterior cerebral, right and left middle cerebral, and posterior cerebral circulations, and, for each of these four populations, analyze the vessel number, average radius, branching frequency, and tortuosity. For the parameters analyzed, we conclude that statistical methods employing summary measures for each attribute within each region of interest for each patient are preferable to methods that deal with individual vessels, that the distributions of the summary measures are indeed Gaussian, and that attribute values may differ by anatomical location. These results should be useful in designing studies that compare patients with suspected disease to a database of healthy subjects and are relevant to groups interested in atlas formation and in the statistics of tubular objects.

Geometric modeling of the human normal cerebral arterial system

We propose an anatomy-based approach for an efficient construction of a three-dimensional human normal cerebral arterial model from segmented and skeletonized angiographic data. The centerline-based model is used for an accurate angiographic data representation. A vascular tree is represented by tubular segments and bifurcations whose construction takes into account vascular anatomy. A bifurcation is defined quantitatively and the algorithm calculating it is given. The centerline is smoothed by means of a sliding average filter. As the vessel radius is sensitive to quality of data as well as accuracy of segmentation and skeletonization, radius outlier removal and radius regression algorithms are formulated and applied. In this way, the approach compensates for some inaccuracies introduced during segmentation and skeletonization. To create the frame of vasculature, we use two different topologies: tubular and B-subdivision based. We also propose a technique to prevent vessel twisting. The analysis of the vascular model is done on a variety of data containing 258 vascular segments and 131 bifurcations. Our approach gives acceptable results from anatomical, topological and geometrical standpoints as well as provides fast visualization and manipulation of the model. The approach is applicable for building a reference cerebrovascular atlas, developing applications for simulation and planning of interventional radiology procedures and vascular surgery, and in education.

Non-rigid image registration: theory and practice

Image registration is an important enabling technology in medical image analysis. The current emphasis is on development and validation of application-specific non-rigid techniques, but there is already a plethora of techniques and terminology in use. In this paper we discuss the current state of the art of non-rigid registration to put on-going research in context and to highlight current and future clinical applications that might benefit from this technology. The philosophy and motivation underlying non-rigid registration is discussed and a guide to common terminology is presented. The core components of registration systems are described and outstanding issues of validity and validation are confronted.

Correlation of MR perfusion imaging and vessel tortuosity parameters in assessment of intracranial neoplasms

Advances in noninvasive imaging techniques such as magnetic resonance perfusion imaging have been found useful in grading cerebral neoplasms and have potential for significant clinical benefit. The purpose of this study was to determine the correlation between tumor vessel tortuosity as measured from vessels extracted from magnetic resonance angiograms (MRA) and perfusion parameters of cerebral blood flow (CBF) and cerebral blood volume (CBV) in intracranial neoplasms. We hypothesized that tumor blood vessel tortuosity measures and perfusion measures would be correlated, since both are increased by tumor angiogenesis. 18 patients with 19 cerebral neoplasms were evaluated with conventional MR imaging and dynamic contrast-enhanced T2-weighted perfusion MR imaging (PWI). Both benign and malignant lesions were included, as were hyper- and hypovascular tumors. Regions of interest were plotted within the tumor area to locate foci of maximum CBV and CBF. CBV and CBF measurements were also recorded in contralateral normal appearing white matter to calculate relative CBV (rCBV) and relative CBF (rCBF). Vessel tortuosity analyses were conducted upon vessels segmented from MRA images of the same patients using two tortuosity descriptors (SOAM and ICM), which have previously been demonstrated to have efficacy in separating benign from malignant disease. Linear regression analyses were conducted to determine if correlations exist between CBV or CBF and the two tortuosity measurements. For the overall set of tumors, no significant correlations were found between flow or volume measures and the tortuosity measures. However, when the 7 glioblastoma multiforme tumors were examined as a subgroup, the following significant correlations were found: rCBV and SOAM (R2=0.799), rCBV and ICM (R2=0.214). Our results demonstrate that MR perfusion imaging data do not correlate significantly with vessel tortuosity parameters as determined from the larger vessels seen by MRA. However, for subgroups of a particular tumor type such as GBM, there may be significant correlations. It appears that perfusion and tortuosity data may provide independently useful data in the assessment of cerebral neoplasms.

Abnormal vessel tortuosity as a marker of treatment response of malignant gliomas: preliminary report

Despite multiple advances in medical imaging, noninvasive monitoring of therapeutic efficacy for malignant gliomas remains problematic. An underutilized observation is that malignancy induces characteristic abnormalities of vessel shape. These characteristic shape abnormalities affect both capillaries and much larger vessels in the tumor vicinity, involve larger vessels prior to sprout formation, and are generally not present in hypervascular benign tumors. Vessel shape abnormalities associated with malignancy thus may appear independently of increase in vessel density. We hypothesize that an automated, computerized analysis of vessel shape as defined from high-resolution MRA can provide valuable information about tumor activity during the treatment of malignant gliomas. This report describes vessel shape properties in 10 malignant gliomas prior to treatment, in 2 patients in remission during treatment, and in 2 patients with recurrent disease. One subject was scanned multiple times. The method involves an automated, statistical analysis of vessel shape within a region of interest for each tumor, normalized by the values obtained from the vessels within the same region of interest of 34 healthy subjects. Results indicate that untreated tumors display statistically significant vessel tortuosity abnormalities. These abnormalities involve vessels not only within the tumor margins as defined from MR but also vessels in the surrounding tissue. The abnormalities resolve during effective treatment and recur with tumor recurrence. We conclude that vessel shape analysis could provide an important means of assessing tumor activity.

New methods for the computer-assisted 3-D reconstruction of neurons from confocal image stacks

Exact geometrical reconstructions of neuronal architecture are indispensable for the investigation of neuronal function. Neuronal shape is important for the wiring of networks, and dendritic architecture strongly affects neuronal integration and firing properties as demonstrated by modeling approaches. Confocal microscopy allows to scan neurons with submicron resolution. However, it is still a tedious task to reconstruct complex dendritic trees with fine structures just above voxel resolution. We present a framework assisting the reconstruction. User time investment is strongly reduced by automatic methods, which fit a skeleton and a surface to the data, while the user can interact and thus keeps full control to ensure a high quality reconstruction. The reconstruction process composes a successive gain of metric parameters. First, a structural description of the neuron is built, including the topology and the exact dendritic lengths and diameters. We use generalized cylinders with circular cross sections. The user provides a rough initialization by marking the branching points. The axes and radii are fitted to the data by minimizing an energy functional, which is regularized by a smoothness constraint. The investigation of proximity to other structures throughout dendritic trees requires a precise surface reconstruction. In order to achieve accuracy of 0.1 microm and below, we additionally implemented a segmentation algorithm based on geodesic active contours that allow for arbitrary cross sections and uses locally adapted thresholds. In summary, this new reconstruction tool saves time and increases quality as compared to other methods, which have previously been applied to real neurons.

MRA image segmentation with capillary active contour

Precise segmentation of three-dimensional (3D) magnetic resonance angiography (MRA) image can be a very useful computer aided diagnosis (CAD) tool in clinical routines. Our objective is to develop a specific segmentation scheme for accurately extracting vasculature from MRA images. Our proposed algorithm, called the capillary active contour (CAC), models capillary action where liquid can climb along the boundaries of thin tubes. The CAC, which is implemented based on level sets, is able to segment thin vessels and has been applied for verification on synthetic volumetric images and real 3D MRA images. Compared with other state-of-the-art MRA segmentation algorithms, our experiments show that the introduced capillary force can facilitate more accurate segmentation of blood vessels.

Comparison of Vessel Segmentations Using STAPLE

We propose a novel method for the validation of vascular segmentations. Our technique combines morphological operators and the TAPLE algorithm to obtain ground truth of centerline extractions as well as a measure of accuracy of the methods to be compared. Moreover, ur method can be extended to the validation of any open-curves. We also present a comparison study of three vascular segmentation methods: ridge traversal, statistical and curves level set. They are compared with manual segmentations from five experts.

Differential Fly-Throughs (DFT): A General Framework for Computing Flight Paths

In this paper, we propose a new variational framework based on distance transform and gradient vector flow, to compute flight paths through tubular and non-tubular structures, for virtual endoscopy. The proposed framework propagates two wave fronts of different speeds from a point source voxel, which belongs to the medial curves of the anatomical structure. The first wave traverses the 3D structure with a moderate speed that is a function of the distance field to extract its topology, while the second wave propagates with a higher speed that is a function of the magnitude of the gradient vector flow to extract the flight paths. The motion of the fronts are governed by a nonlinear partial equation, whose solution is computed efficiently using the higher accuracy fast marching level set method (HAFMM). The framework is robust, fully automatic, and computes flight paths that are centered, connected, thin, and less sensitive to boundary noise. We have validated the robustness of the proposed method both quantitatively and qualitatively against synthetic and clinical datasets.

PDE-Based Three Dimensional Path Planning for Virtual Endoscopy

Three dimensional medial paths or curve skeletons (CS) are an essential component of any virtual endoscopy (VE) system, because they serve as flight paths for a virtual camera to navigate the human organ and to examine its internal structures. In this paper, we propose a novel framework for computing flight paths of tubular structures for VE using partial differential equation (PDE). The method works in two passes. In the first pass, the overall topology of the organ is analyzed and its important topological nodes are identified, while in the second pass, the actual flight paths are computed by tracking them starting from each identified node. The proposed framework is robust, fully automatic, computationally efficient, and computes CS that are centered, connected, thin, and less sensitive to boundary noise. We have extensively validated the robustness of the proposed method both quantitatively and qualitatively against several synthetic phantoms and clinical datasets.

Depth-map-based scene analysis for active navigation in virtual angioscopy

This paper presents a new approach dealing with virtual exploratory navigation inside vascular structures. It is based on the notion of active vision in which only visual perception drives the motion of the virtual angioscope. The proposed fly-through approach does not require a premodeling of the volume dataset or an interactive control of the virtual sensor during the fly-through. Active navigation combines the on-line computation of the scene view and its analysis, to automatically define the three-dimensional sensor path. The navigation environment and the camera-like model are first sketched. The basic stages of the active navigation framework are then described: the virtual image computation (based on ray casting), the scene analysis process (using depth map), the navigation strategy, and the virtual path estimation. Experimental results obtained from phantom model and patient computed tomography data are finally reported.

Three-dimensional path planning for virtual bronchoscopy

Multidetector computed-tomography (MDCT) scanners provide large high-resolution three-dimensional (3-D) images of the chest. MDCT scanning, when used in tandem with bronchoscopy, provides a state-of-the-art approach for lung-cancer assessment. We have been building and validating a lung-cancer assessment system, which enables virtual-bronchoscopic 3-D MDCT image analysis and follow-on image-guided bronchoscopy. A suitable path planning method is needed, however, for using this system. We describe a rapid, robust method for computing a set of 3-D airway-tree paths from MDCT images. The method first defines the skeleton of a given segmented 3-D chest image and then performs a multistage refinement of the skeleton to arrive at a final tree structure. The tree consists of a series of paths and branch structural data, suitable for quantitative airway analysis and smooth virtual navigation. A comparison of the method to a previously devised path-planning approach, using a set of human MDCT images, illustrates the efficacy of the method. Results are also presented for human lung-cancer assessment and the guidance of bronchoscopy.

Quantifying 3-D vascular structures in MRA images using hybrid PDE and geometric deformable models

The aim of this paper is to present a hybrid approach to accurate quantification of vascular structures from magnetic resonance angiography (MRA) images using level set methods and deformable geometric models constructed with 3-D Delaunay triangulation. Multiple scale filtering based on the analysis of local intensity structure using the Hessian matrix is used to effectively enhance vessel structures with various diameters. The level set method is then applied to automatically segment vessels enhanced by the filtering with a speed function derived from enhanced MRA images. Since the goal of this paper is to obtain highly accurate vessel borders, suitable for use in fluid flow simulations, in a subsequent step, the vessel surface determined by the level set method is triangulated using 3-D Delaunay triangulation and the resulting surface is used as a parametric deformable model. Energy minimization is then performed within a variational setting with a first-order internal energy; the external energy is derived from 3-D image gradients. Using the proposed method, vessels are accurately segmented from MRA data.

Robust Model-Based Vasculature Detection in Noisy Biomedical Images

This paper presents a set of algorithms for robust detection of vasculature in noisy retinal video images. Three methods are studied for effective handling of outliers. The first method is based on Huber's censored likelihood ratio test. The second is based on the use of a alpha-trimmed test statistic. The third is based on robust model selection algorithms. All of these algorithms rely on a mathematical model for the vasculature that accounts for the expected variations in intensity/texture profile, width, orientation, scale, and imaging noise. These unknown parameters are estimated implicitly within a robust detection and estimation framework. The proposed algorithms are also useful as nonlinear vessel enhancement filters. The proposed algorithms were evaluated over carefully constructed phantom images, where the ground truth is known a priori, as well as clinically recorded images for which the ground truth was manually compiled. A comparative evaluation of the proposed approaches is presented. Collectively, these methods outperformed prior approaches based on Chaudhuri et al. (1989) matched filtering, as well as the verification methods used by prior exploratory tracing algorithms, such as the work of Can et aL (1999). The Huber censored likelihood test yielded the best overall improvement, with a 145.7% improvement over the exploratory tracing algorithm, and a 43.7% improvement in detection rates over the matched filter.

Diagnostic fidelity of the Z-buffer segmentation algorithm: preliminary assessment based on intracranial aneurysm detection

We have developed an algorithm known as the Z-buffer segmentation (ZBS) algorithm for segmenting vascular structures from 3D MRA images. Previously we evaluated the accuracy of the ZBS algorithm on a voxel level in terms of inclusion and exclusion of vascular and background voxels. In this paper we evaluate the diagnostic fidelity of the ZBS algorithm. By diagnostic fidelity we mean that the data preserves the structural information necessary for diagnostic evaluation. This evaluation is necessary to establish the potential usefulness of the segmentation for improved image display, or whether the segmented data could form the basis of a computerized analysis tool. We assessed diagnostic fidelity by measuring how well human observers could detect aneurysms in the segmented data sets. ZBS segmentation of 30 MRA cases containing 29 aneurysms was performed. Image display used densitometric reprojections with shaded surface highlighting that were generated from the segmented data. Three neuroradiologists independently reviewed the generated ZBS images for aneurysms. The observers had 80% sensitivity (90% for aneurysms larger than 2mm) with 0.13 false positives per image. Good agreement with the gold standard for describing aneurysm size and orientation was shown. These preliminary results suggest that the segmentation has diagnostic fidelity with the original data and may be useful for improved visualization or automated analysis of the vasculature.