Maciej Orkisz

Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms.

Efficiently obtaining a reliable coronary artery centerline from computed tomography angiography data is relevant in clinical practice. Whereas numerous methods have been presented for this purpose, up to now no standardized evaluation methodology has been published to reliably evaluate and compare the performance of the existing or newly developed coronary artery centerline extraction algorithms. This paper describes a standardized evaluation methodology and reference database for the quantitative evaluation of coronary artery centerline extraction algorithms. The contribution of this work is fourfold: (1) a method is described to create a consensus centerline with multiple observers, (2) well-defined measures are presented for the evaluation of coronary artery centerline extraction algorithms, (3) a database containing 32 cardiac CTA datasets with corresponding reference standard is described and made available, and (4) 13 coronary artery centerline extraction algorithms, implemented by different research groups, are quantitatively evaluated and compared. The presented evaluation framework is made available to the medical imaging community for benchmarking existing or newly developed coronary centerline extraction algorithms.

Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography

Though conventional coronary angiography (CCA) has been the standard of reference for diagnosing coronary artery disease in the past decades, computed tomography angiography (CTA) has rapidly emerged, and is nowadays widely used in clinical practice. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms devised to detect and quantify the coronary artery stenoses, and to segment the coronary artery lumen in CTA data. The objective of this evaluation framework is to demonstrate the feasibility of dedicated algorithms to: (1) (semi-)automatically detect and quantify stenosis on CTA, in comparison with quantitative coronary angiography (QCA) and CTA consensus reading, and (2) (semi-)automatically segment the coronary lumen on CTA, in comparison with experts manual annotation. A database consisting of 48 multicenter multivendor cardiac CTA datasets with corresponding reference standards are described and made available. The algorithms from 11 research groups were quantitatively evaluated and compared. The results show that (1) some of the current stenosis detection/quantification algorithms may be used for triage or as a second-reader in clinical practice, and that (2) automatic lumen segmentation is possible with a precision similar to that obtained by experts. The framework is open for new submissions through the website, at http://coronary.bigr.nl/stenoses/.

Evaluation framework for carotid bifurcation lumen segmentation and stenosis grading.

This paper describes an evaluation framework that allows a standardized and objective quantitative comparison of carotid artery lumen segmentation and stenosis grading algorithms. We describe the data repository comprising 56 multi-center, multi-vendor CTA datasets, their acquisition, the creation of the reference standard and the evaluation measures. This framework has been introduced at the MICCAI 2009 workshop 3D Segmentation in the Clinic: A Grand Challenge III, and we compare the results of eight teams that participated. These results show that automated segmentation of the vessel lumen is possible with a precision that is comparable to manual annotation. The framework is open for new submissions through the website http://cls2009.bigr.nl.

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.

Evaluation of a Kalman-based block matching method to assess the bi-dimensional motion of the carotid artery wall in B-mode ultrasound sequences

We aim at investigating arterial diseases at early stage, by assessing the longitudinal (i.e. in the same direction as the blood flow) motion of the intima-media complex. This recently evidenced phenomenon has been shown to provide relevant and complementary information about vascular health. Our method assesses the longitudinal and radial motion from clinical in vivo B-mode ultrasound sequences. To estimate the trajectory of a selected point during the cardiac cycle, we introduce a block matching method that involves a temporal update of the reference block using a pixel-wise Kalman filter. The filter uses the initial gray-level of the pixel as control signal to avoid divergence due to cumulating errors. The block and search-window sizes are adapted to the tissue of interest. The method was evaluated on image sequences of the common carotid artery, acquired in 57 healthy volunteers and in 25 patients at high cardiovascular risk. Reference trajectories were generated for each sequence by averaging the tracings performed by three observers. Six different computerized techniques were also compared to our method. With a pixel size of 30 μm, the average absolute motion estimation errors were 84 ± 107 μm and 20 ± 19 μm for the longitudinal and radial directions, respectively. This accuracy was of the same order of magnitude as the inter- and intra-observers variability, and smaller than for the other methods. The estimated longitudinal motion amplitude was significantly reduced in at-risk patients compared with healthy volunteers (408 ± 281 μm vs. 643 ± 274 μm, p<0.0001). Our method can constitute a reliable and time-saving technique to investigate the arterial stiffness in clinical studies, in the objective to detect early-stage atherosclerosis.

A Deformable Vessel Model with Single Point Initialization for Segmentation, Quantification and Visualization of Blood Vessels in 3D MRA

We deal with image segmentation applied to three-dimensional (3D) analysis of of vascular morphology in magnetic resonance angiography (MRA) images. The main goal of our work is to develop a fast and reliable method for stenosis quantification. The first step towards this purpose is the extraction of the vessel axis by an expansible skeleton method. Vessel boundaries are then detected in the planes locally orthogonal to the centerline using an improved active contour. Finally, area measurements based on the resulting contours allow the calculation of stenosis parameters. The expansible nature of the skeleton associated with a single point initialization of the active contour allows overcoming some limitations of traditional deformable models. As a result, the algorithm performs well even for severe stenosis and significant vessel curvatures. Experimental results are presented in 3D phantom images as well as in real images of patients.

IMAGE BASED RENAL STONE TRACKING TO IMPROVE EFFICACY IN EXTRACORPOREAL LITHOTRIPSY

PURPOSE We describe a method to reduce the number of shocks necessary to fragment renal stones during extracorporeal shock wave lithotripsy by automatically taking into account stone movements. MATERIALS AND METHODS Echotrack computer software was developed and implemented on a lithotriptor. One software module uses image processing to detect instantaneous stone location based on ultrasound images generated by the lithotriptor. A second module uses the detected location to control the shock wave generator position, and automatically adjusts it to improve coincidence between the focal volume and stone. The reliability of the tracking algorithm was clinically tested in 65 patients with renal stones. These in vivo tests were qualitative and the goal was to assess software ability to track stones during actual treatments. A quantitative evaluation of the reduction in shocks necessary for fragmentation was performed in vitro. Artificial stones were moved according to computer generated trajectories. Each trajectory was applied once with and once without automatic adjustment of the generator position. RESULTS The in vivo tests demonstrated software ability to track stones as far as they were visible in the images. During in vitro tests automatic adjustments of the generator position reduced the number of shocks necessary to fragment stones completely by a factor of 1.64. CONCLUSIONS Image based renal stone tracking software that automatically adjusts the shock wave generator position according to the displacement of renal stones is useful during extracorporeal shock wave lithotripsy. Treatment time was significantly shorter with this software.

Quantification of Multicontrast Vascular MR Images with NLSnake, an Active Contour Model: In Vitro Validation and In Vivo Evaluation

Vessel‐wall measurements from multicontrast MRI provide information on plaque structure and evolution. This requires the extraction of numerous contours. In this work a contour‐extraction method is proposed that uses an active contour model (NLSnake) adapted for a wide range of MR vascular images. This new method employs length normalization for the purpose of deformation computation and offers the advantages of simplified parameter tuning, fast convergence, and minimal user interaction. The model can be initialized far from the boundaries of the region to be segmented, even by only one pixel. The accuracy and reproducibility of NLSnake endoluminal contours were assessed on vascular phantom MR angiography (MRA) and high‐resolution in vitro MR images of rabbit aorta. An in vivo evaluation was performed on rabbit and clinical data for both internal and external vessel‐wall contours. In phantoms with 95% stenoses, NLSnake measured 94.3% ± 3.8%, and the accuracy was even better for milder stenoses. In the images of rabbit aorta, variability between NLSnake and experts was less than interobserver variability, while the maximum intravariability of NLSnake was equal to 1.25%. In conclusion, the NLSnake technique successfully quantified the vessel lumen in multicontrast MR images using constant parameters. Magn Reson Med 51:370–379, 2004.

Progressive attenuation of the longitudinal kinetics in the common carotid artery: preliminary in vivo assessment.

Longitudinal kinetics (LOKI) of the arterial wall consists of the shearing motion of the intima-media complex over the adventitia layer in the direction parallel to the blood flow during the cardiac cycle. The aim of this study was to investigate the local variability of LOKI amplitude along the length of the vessel. By use of a previously validated motion-estimation framework, 35 in vivo longitudinal B-mode ultrasound cine loops of healthy common carotid arteries were analyzed. Results indicated that LOKI amplitude is progressively attenuated along the length of the artery, as it is larger in regions located on the proximal side of the image (i.e., toward the heart) and smaller in regions located on the distal side of the image (i.e., toward the head), with an average attenuation coefficient of -2.5 ± 2.0%/mm. Reported for the first time in this study, this phenomenon is likely to be of great importance in improving understanding of atherosclerosis mechanisms, and has the potential to be a novel index of arterial stiffness.

Segmentation and Quantification of Blood Vessels in 3D Images using a Right Generalized Cylinder State Model

We present a vascular segmentation and quantification method based on the right generalized cylinder state model (RGC-sm). The RGC-sm model includes a curvilinear axis associated to a stack of contours. The axis is described by a state vector (local curvature, torsion and rotation). The contours are described by a Fourier series decomposition. The challenge is to automatically adjust this model to 3D vascular data (segmentation). By fitting the synthetic model to the actual medical data, it is possible to get the state model parameters and quantification measures. We present quantitative results on a set of calibrated phantoms and qualitative results on clinical datasets (carotid 3D-CTA and aortic 3D-MRA).