Segmentation of wall and plaque in in vitro vascular MR images

Artificial Intelligence in Symptomatic Carotid Plaque Detection: A Narrative Review

Identifying atherosclerotic disease is the mainstay for the correct diagnosis of the large artery atherosclerosis ischemic stroke subtype and for choosing the right therapeutic strategy in acute ischemic stroke. Classification into symptomatic and asymptomatic plaque and estimation of the cardiovascular risk are essential to select patients eligible for pharmacological and/or surgical therapy in order to prevent future cerebral ischemic events. The difficulties in a “vulnerability” definition and the methodical issues concerning its detectability and quantification are still subjects of debate. Non-invasive imaging studies commonly used to detect arterial plaque are computed tomographic angiography, magnetic resonance imaging, and ultrasound. Characterization of a carotid plaque type using the abovementioned imaging modalities represents the basis for carotid atherosclerosis management. Classification into symptomatic and asymptomatic plaque and estimation of the cardiovascular risk are essential to select patients eligible for pharmacological and/or surgical therapy in order to prevent future cerebral ischemic events. In this setting, artificial intelligence (AI) can offer suggestive solutions for tissue characterization and classification concerning carotid artery plaque imaging by analyzing complex data and using automated algorithms to obtain a final output. The aim of this review is to provide overall knowledge about the role of AI models applied to non-invasive imaging studies for the detection of symptomatic and vulnerable carotid plaques.

Microcalcifications, Their Genesis, Growth, and Biomechanical Stability in Fibrous Cap Rupture

For many decades, cardiovascular calcification has been considered as a passive process, accompanying atheroma progression, correlated with plaque burden, and apparently without a major role on plaque vulnerability. Clinical and pathological analyses have previously focused on the total amount of calcification (calcified area in a whole atheroma cross section) and whether more calcification means higher risk of plaque rupture or not. However, this paradigm has been changing in the last decade or so. Recent research has focused on the presence of microcalcifications (μCalcs) in the atheroma and more importantly on whether clusters of μCalcs are located in the cap of the atheroma. While the vast majority of μCalcs are found in the lipid pool or necrotic core, they are inconsequential to vulnerable plaque. Nevertheless, it has been shown that μCalcs located within the fibrous cap could be numerous and that they behave as an intensifier of the background circumferential stress in the cap. It is now known that such intensifying effect depends on the size and shape of the μCalc as well as the proximity between two or more μCalcs. If μCalcs are located in caps with very low background stress, the increase in stress concentration may not be sufficient to reach the rupture threshold. However, the presence of μCalc(s) in the cap with a background stress of about one fifth to one half the rupture threshold (a stable plaque) will produce a significant increase in local stress, which may exceed the cap rupture threshold and thus transform a non-vulnerable plaque into a vulnerable one. Also, the classic view that treats cardiovascular calcification as a passive process has been challenged, and emerging data suggest that cardiovascular calcification may encompass both passive and active processes. The passive calcification process comprises biochemical factors, specifically circulating nucleating complexes, which would lead to calcification of the atheroma. The active mechanism of atherosclerotic calcification is a cell-mediated process via cell death of macrophages and smooth muscle cells (SMCs) and/or the release of matrix vesicles by SMCs.

Computerized System for Quantitative Assessment of Atherosclerotic Plaques in the Femoral and Iliac Arteries Visualized by Multislice Computed Tomography

OBJECTIVE

The investigation is aimed at the development of a semiautomatic method of examining the femoral and iliac arteries, and quantifying atherosclerotic plaques visible in the multislice computed tomography images.

METHODS

We have utilized the advanced morphology and segmentation methods for processing of a series of the images. In particular, a novel sorted pixel intensity approach to segment the artery into the lumen/plaque regions has been used, and effectively combined with the Gaussian mixture modeling to increase the accuracy of the segmentation.

RESULTS

Our numerical results are compared with those obtained manually by two experts. Statistics relevant to the progression of atherosclerosis have also been suggested. Results of the semiautomatic tracking of the femoral and iliac arteries and of the quantitative evaluation of atherosclerotic alterations therein have been shown to correspond well with the expert's results.

CONCLUSION

The developed system is likely to be valuable tool for supporting the quantitative evaluation of atherosclerotic changes in arteries.

SIGNIFICANCE

In its present form the system can be used for planning surgical treatment and/or predicting the course of the atherosclerotic alterations.

Advances in the development of an imaging device for plaque measurement in the area of the carotid artery

This paper describes the advances in the development and subsequent testing of an imaging device for three-dimensional ultrasound measurement of atherosclerotic plaque in the carotid artery. The embolization from the atherosclerotic carotid plaque is one of the most common causes of ischemic stroke and, therefore, we consider the measurement of the plaque as extremely important. The paper describes the proposed hardware for enhancing the standard ultrasonic probe to provide a possibility of accurate probe positioning and synchronization with the cardiac activity, allowing the precise plaque measurements that were impossible with the standard equipment. The synchronization signal is derived from the output signal of the patient monitor (electrocardiogram (ECG)), processed by a microcontroller-based system, generating the control commands for the linear motion moving the probe. The controlling algorithm synchronizes the movement with the ECG waveform to obtain clear images not disturbed by the heart activity.

Changing views of the biomechanics of vulnerable plaque rupture: a review

This review examines changing perspectives on the biomechanics of vulnerable plaque rupture over the past 25 years from the first finite element analyses (FEA) showing that the presence of a lipid pool significantly increases the local tissue stress in the atheroma cap to the latest imaging and 3D FEA studies revealing numerous microcalcifications in the cap proper and a new paradigm for cap rupture. The first part of the review summarizes studies describing the role of the fibrous cap thickness, tissue properties, and lesion geometry as main determinants of the risk of rupture. Advantages and limitations of current imaging technologies for assessment of vulnerable plaques are also discussed. However, the basic paradoxes as to why ruptures frequently did not coincide with location of PCS and why caps >65 μm thickness could rupture at tissue stresses significantly below the 300 kPa critical threshold still remained unresolved. The second part of the review describes recent studies in the role of microcalcifications, their origin, shape, and clustering in explaining these unresolved issues including the actual mechanism of rupture due to the explosive growth of tiny voids (cavitation) in local regions of high stress concentration between closely spaced microinclusions oriented along their tensile axis.

THE LAYERED NET SURFACE PROBLEMS IN DISCRETE GEOMETRY AND MEDICAL IMAGE SEGMENTATION

Efficient detection of multiple inter-related surfaces representing the boundaries of objects of interest in d-D images (d >/= 3) is important and remains challenging in many medical image analysis applications. In this paper, we study several layered net surface (LNS) problems captured by an interesting type of geometric graphs called ordered multi-column graphs in the d-D discrete space (d >/= 3 is any constant integer). The LNS problems model the simultaneous detection of multiple mutually related surfaces in three or higher dimensional medical images. Although we prove that the d-D LNS problem (d >/= 3) on a general ordered multi-column graph is NP-hard, the (special) ordered multi-column graphs that model medical image segmentation have the self-closure structures and thus admit polynomial time exact algorithms for solving the LNS problems. Our techniques also solve the related net surface volume (NSV) problems of computing well-shaped geometric regions of an optimal total volume in a d-D weighted voxel grid. The NSV problems find applications in medical image segmentation and data mining. Our techniques yield the first polynomial time exact algorithms for several high dimensional medical image segmentation problems. Experiments and comparisons based on real medical data showed that our LNS algorithms and software are computationally efficient and produce highly accurate and consistent segmentation results.

Automated versus manual segmentation of atherosclerotic carotid plaque volume and components in CTA: associations with cardiovascular risk factors

The purpose of this study was to validate automated atherosclerotic plaque measurements in carotid arteries from CT angiography (CTA). We present an automated method (three initialization points are required) to measure plaque components within the carotid vessel wall in CTA. Plaque components (calcifications, fibrous tissue, lipids) are determined by different ranges of Hounsfield Unit values within the vessel wall. On CTA scans of 40 symptomatic patients with atherosclerotic plaque in the carotid artery automatically segmented plaque volume, calcified, fibrous and lipid percentages were 0.97 ± 0.51 cm(3), 10 ± 11%, 63 ± 10% and 25 ± 5%; while manual measurements by first observer were 0.95 ± 0.60 cm(3), 14 ± 16%, 63 ± 13% and 21 ± 9%, respectively and manual measurement by second observer were 1.05 ± 0.75 cm(3), 11 ± 12%, 61 ± 11% and 27 ± 10%. In 90 datasets, significant associations were found between age, gender, hypercholesterolemia, diabetes, smoking and previous cerebrovascular disease and plaque features. For both automated and manual measurements, significant associations were found between: age and calcium and fibrous tissue percentage; gender and plaque volume and lipid percentage; diabetes and calcium, smoking and plaque volume; previous cerebrovascular disease and plaque volume. Significant associations found only by the automated method were between age and plaque volume, hypercholesterolemia and plaque volume and diabetes and fibrous tissue percentage. Significant association found only by the manual method was between previous cerebrovascular disease and percentage of fibrous tissue. Automated analysis of plaque composition in the carotid arteries is comparable with the manual analysis and has the potential to replace it.

Robust adaptive 3-D segmentation of vessel laminae from fluorescence confocal microscope images and parallel GPU implementation

This paper presents robust 3-D algorithms to segment vasculature that is imaged by labeling laminae, rather than the lumenal volume. The signal is weak, sparse, noisy, nonuniform, low-contrast, and exhibits gaps and spectral artifacts, so adaptive thresholding and Hessian filtering based methods are not effective. The structure deviates from a tubular geometry, so tracing algorithms are not effective. We propose a four step approach. The first step detects candidate voxels using a robust hypothesis test based on a model that assumes Poisson noise and locally planar geometry. The second step performs an adaptive region growth to extract weakly labeled and fine vessels while rejecting spectral artifacts. To enable interactive visualization and estimation of features such as statistical confidence, local curvature, local thickness, and local normal, we perform the third step. In the third step, we construct an accurate mesh representation using marching tetrahedra, volume-preserving smoothing, and adaptive decimation algorithms. To enable topological analysis and efficient validation, we describe a method to estimate vessel centerlines using a ray casting and vote accumulation algorithm which forms the final step of our algorithm. Our algorithm lends itself to parallel processing, and yielded an 8 x speedup on a graphics processor (GPU). On synthetic data, our meshes had average error per face (EPF) values of (0.1-1.6) voxels per mesh face for peak signal-to-noise ratios from (110-28 dB). Separately, the error from decimating the mesh to less than 1% of its original size, the EPF was less than 1 voxel/face. When validated on real datasets, the average recall and precision values were found to be 94.66% and 94.84%, respectively.

Carotid artery segmentation using an outlier immune 3D active shape models framework

This paper presents an outlier immune 3D active shape models framework for robust volumetric segmentation of the carotid artery required for accurate plaque burden assessment. In the proposed technique, outlier handling is based on a shape metric that is invariant to scaling, rotation and translation by using the ratio of inter-landmark distances as a local shape dissimilarity measure. Tolerance intervals for each descriptor are calculated from the training samples and used to infer the validity of landmarks. The identified outliers are corrected prior to the model fitting using the ratios distributions and appearance information. To improve the feature point search, the method exploits the geometrical knowledge from the outlier analysis at the previous iteration to weight the gray level appearance based fitness measure. A combined intensity-phase feature point search is also introduced which significantly limits the presence of outliers and improves the overall search accuracy. Both numerical and in vivo assessments of the method involving volumetric segmentation of the carotid artery have shown that the outlier handling technique is capable of handling a significant presence of outliers independently of the amplitudes.

Atherosclerotic carotid plaque segmentation

Atherosclerosis is the major cause of heart attack and stroke in the western world. In this paper we present a computerized method for segmenting the athrerosclerotic carotid plaque from ultrasound images. The method uses the blood flow image first to detect the initial contour of the plaque, and then despeckle filtering and snakes to deform the initial contour for best fit of plaque boundaries. The accuracy and reproducibility of this method was tested using 35 longitudinal ultrasound images of carotid arteries and the results were compared with the manual delineations of an expert. The comparison showed that the computerized method gives satisfactory results with no manual correction needed in most of the cases. The true positive fraction, TPF, true negative fraction, TNF, false negative fraction, FNF and false positive fraction, FPF, were 86.44%, 84.03%, 8.5%, and 7% respectively.

Automated classification of atherosclerotic plaque from magnetic resonance images using predictive models

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.

Experimental evaluation of the detectability of submillimeter atherosclerotic lesions in ex vivo human iliac arteries with ultrahigh-field (7.0 T) magnetic resonance imaging

BACKGROUND

To evaluate the ability of ultrahigh-field magnetic resonance imaging (MRI) to accurately depict the composition of the human arterial vessel wall ex vivo and to detect early atherosclerotic lesion formation in comparison to histology.

METHODS

Eight iliac artery specimens with low-grade atherosclerotic lesions obtained from human organ donors were studied. Three-dimensional, high-resolution MRI (spatial resolution: 79 x 79 x 109 microm) was performed using T1-, T2- and proton density (PD)-weightings (7.0 Tesla MR system, Bruker Pharmascan). A total of 36 MR slices and corresponding histological sections were matched for comparative evaluation of area measurements of lumen, media and adventitia and--if present--plaque size. Statistical correlation between histology and MR measurements was tested and a ROC-analysis was performed to determine the plaque size being predictive of correctly identifying atherosclerotic lesions with MRI.

RESULTS

The areas of vessel lumen and media as measured on T1-, T2- and PD-weighted MR images showed a strong correlation with the corresponding histological measurements (r = 0.84 to r = 0.89; P < 0.01), however, a systematic overestimation of 34-41% was found. For the area of adventitia, only a moderate, though significant, correlation (r = 0.55 to r = 0.62; P < 0.01) could be demonstrated with a similar overestimation by MRI (38-43%). With T1-weighted MRI, sensitivity and specificity for the detection of plaques > 4.0 mm(2) were 79% and 91%, respectively. With T2- and PD-weighted MRI, however, sensitivity and specificity for the detection of plaques > 0.4 mm2 were 93% and 89%.

CONCLUSIONS

In an experimental ex vivo setting, ultrahigh-field MRI of the human arterial vessel wall resulted in an accurate visualization of vessel wall composition when compared to histology and, thus, allowed for a quantitative assessment. T2- and PD-weighted MRI proved capable of reliably detecting submillimeter atherosclerotic lesions.

3D geometric reconstruction of thoracic aortic aneurysms

Background

The thoracic aortic aneurysm (TAA) is a pathology that involves an expansion of the aortic diameter in the thoracic aorta, leading to risk of rupture. Recent studies have suggested that internal wall stress, which is affected by TAA geometry and the presence or absence of thrombus, is a more reliable predictor of rupture than the maximum diameter, the current clinical criterion. Accurate reconstruction of TAA geometry is a crucial step in patient-specific stress calculations.

Methods

In this work, a novel methodology was developed, which combines data from several sets of magnetic resonance (MR) images with different levels of detail and different resolutions. Two sets of images were employed to create the final model, which has the highest level of detail for each component of the aneurysm (lumen, thrombus, and wall). A reference model was built by using a single set of images for comparison. This approach was applied to two patient-specific TAAs in the descending thoracic aorta.

Results

The results of finite element simulations showed differences in stress pattern between the coarse and fine models: higher stress values were found with the coarse model and the differences in predicted maximum wall stress were 30% for patient A and 11% for patient B.

Conclusion

This paper presents a new approach to the reconstruction of an aneurysm model based on the use of several sets of MR images. This enables more accurate representation of not only the lumen but also the wall surface of a TAA taking account of intraluminal thrombus.

Optimal surface segmentation in volumetric images--a graph-theoretic approach

Efficient segmentation of globally optimal surfaces representing object boundaries in volumetric data sets is important and challenging in many medical image analysis applications. We have developed an optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The method solves the surface segmentation problem by transforming it into computing a minimum s-t cut in a derived arc-weighted directed graph. The proposed algorithm has a low-order polynomial time complexity and is computationally efficient. It has been extensively validated on more than 300 computer-synthetic volumetric images, 72 CT-scanned data sets of different-sized plexiglas tubes, and tens of medical images spanning various imaging modalities. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional image segmentation.