Conference Paper

A Quantitative Vascular Analysis System for Evaluation of Atherosclerotic Lesions by MRI.

DOI: 10.1007/3-540-45468-3_94 Conference: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2001, 4th International Conference, Utrecht, The Netherlands, October 14-17, 2001, Proceedings
Source: DBLP

ABSTRACT An analysis package called QVAS (quantitative vascular analysis system) is presented for the evaluation of atherosclerotic
arterial lesions visualized in vivo by magnetic resonance imaging. QVAS permits interactive identification of vessel and lesion
boundaries, segmentation of tissue classes within the lesion, quantitative analysis of lesion features, and three dimensional
display of lesion structure. The performance of QVAS is demonstrated using images of carotid artery lesions.

0 Followers
 · 
117 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: The information contained within multicontrast magnetic resonance images (MRI) promises to improve tissue classification accuracy, once appropriately analyzed. Predictive models capture relationships empirically, from known outcomes thereby combining pattern classification with experience. In this study, we examine the applicability of predictive modeling for atherosclerotic plaque component classification of multicontrast ex vivo MR images using stained, histopathological sections as ground truth. Ten multicontrast images from seven human coronary artery specimens were obtained on a 9.4 T imaging system using multicontrast-weighted fast spin-echo (T1-, proton density-, and T2-weighted) imaging with 39-mum isotropic voxel size. Following initial data transformations, predictive modeling focused on automating the identification of specimen's plaque, lipid, and media. The outputs of these three models were used to calculate statistics such as total plaque burden and the ratio of hard plaque (fibrous tissue) to lipid. Both logistic regression and an artificial neural network model (Relevant Input Processor Network-RIPNet) were used for predictive modeling. When compared against segmentation resulting from cluster analysis, the RIPNet models performed between 25 and 30% better in absolute terms. This translates to a 50% higher true positive rate over given levels of false positives. This work indicates that it is feasible to build an automated system of plaque detection using MRI and data mining.
    Biosystems 09/2007; 90(2):456-66. DOI:10.1016/j.biosystems.2006.11.005 · 1.47 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Magnetic Resonance in Medicine 02/2004; 51(2):370-9. DOI:10.1002/mrm.10722 · 3.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: High-resolution MRI provides unique information about morphology of atherosclerotic carotid plaque. In this study, the accuracy and precision of measurements of carotid plaque burden and lumen narrowing were determined for in vivo black blood MRI assessment with respect to ex vivo MRI in a group of 37 atherosclerosis patients who underwent carotid endarterectomy (CEA). Three different plaque measures were compared between paired in vivo and ex vivo MR images: maximum wall area (MWA), minimum lumen area (mLA), and wall volume (WV). MWA and WV are measures of plaque burden, while mLA is a measure of lumen narrowing. The matched in vivo and ex vivo measurements showed good agreement (the correlation coefficients for in/ex vivo WV, MWA, and mLA were 0.92, 0.91, 0.90, respectively) with predictable bias. This study indicates that in vivo black blood MRI can be used to directly estimate the morphology of the plaque. Comparison of the three plaque measures showed that mLA and MWA or WV provide different information regarding the atherosclerotic lesions (the correlation coefficients between mLA and MWA or WV were less than 0.3). Black blood MRI technique is a potentially powerful clinical tool to characterize the severity of atherosclerotic plaque. It can provide accurate measurements on different aspects of the plaque, from plaque burden to lumen narrowing.
    Magnetic Resonance in Medicine 07/2003; 50(1):75-82. DOI:10.1002/mrm.10503 · 3.40 Impact Factor