Segmentation of thrombus in abdominal aortic aneurysms from CTA with nonparametric statistical grey level appearance modeling

Machine learning and image analysis in vascular surgery

Deep learning, a subset of machine learning within artificial intelligence, has been successful in medical image analysis in vascular surgery. Unlike traditional computer-based segmentation methods that manually extract features from input images, deep learning methods learn image features and classify data without making prior assumptions. Convolutional neural networks, the main type of deep learning for computer vision processing, are neural networks with multilevel architecture and weighted connections between nodes that can "auto-learn" through repeated exposure to training data without manual input or supervision. These networks have numerous applications in vascular surgery imaging analysis, particularly in disease classification, object identification, semantic segmentation, and instance segmentation. The purpose of this review article was to review the relevant concepts of machine learning image analysis and its application to the field of vascular surgery.

Automatic segmentation of abdominal aortic aneurysms from CT angiography using a context-aware cascaded U-Net

We delineate abdominal aortic aneurysms, including lumen and intraluminal thrombosis (ILT), from contrast-enhanced computed tomography angiography (CTA) data in 70 patients with complete automation. A novel context-aware cascaded U-Net configuration enables automated image segmentation. Notably, auto-context structure, in conjunction with dilated convolutions, anisotropic context module, hierarchical supervision, and a multi-class loss function, are proposed to improve the delineation of ILT in an unbalanced, low-contrast multi-class labeling problem. A quantitative analysis shows that the automated image segmentation produces comparable results with trained human users (e.g., DICE scores of 0.945 and 0.804 for lumen and ILT, respectively). Resultant morphological metrics (e.g., volume, surface area, etc.) are highly correlated to those parameters generated by trained human users. In conclusion, the proposed automated multi-class image segmentation tool has the potential to be further developed as a translational software tool that can be used to improve the clinical management of AAAs.

Space-time-regulated imaging analyzer for smart coagulation diagnosis

The development of intelligent blood coagulation diagnoses is awaited to meet the current need for large clinical time-sensitive caseloads due to its efficient and automated diagnoses. Herein, a method is reported and validated to realize it through artificial intelligence (AI)-assisted optical clotting biophysics (OCB) properties identification. The image differential calculation is used for precise acquisition of OCB properties with elimination of initial differences, and the strategy of space-time regulation allows on-demand space time OCB properties identification and enables diverse blood function diagnoses. The integrated applications of smartphones and cloud computing offer a user-friendly automated analysis for accurate and convenient diagnoses. The prospective assays of clinical cases (n = 41) show that the system realizes 97.6%, 95.1%, and 100% accuracy for coagulation factors, fibrinogen function, and comprehensive blood coagulation diagnoses, respectively. This method should enable more low-cost and convenient diagnoses and provide a path for potential diagnostic-markers finding.

•

An ultraportable optofluidic analyzer empowers convenient coagulation diagnoses

•

The system enables optical clotting biophysics (OCB) properties acquisition and process

•

Coagulation function diagnoses uses intelligent OCB properties identification

•

Space-time regulation of OCB properties endow it capability to diverse diagnoses

Fully automatic segmentation of abdominal aortic thrombus in pre-operative CTA images using deep convolutional neural networks

BACKGROUND

Endovascular aortic aneurysm repair (EVAR) is currently established as the first-line treatment for anatomically suitable abdominal aortic aneurysm (AAA).

OBJECTIVE

To establish a deep convolutional neural networks (DCNN) model for fully automatic segmentation intraluminal thrombosis (ILT) of abdominal aortic aneurysm (AAA) in pre-operative computed tomography angiography (CTA) images.

METHODS

We retrospectively reviewed 340 patients of AAA with ILT at our single center. The software ITKSNAP was used to draw AAA and ILT region of interests (ROIs), respectively. Image preprocessing and DCNN model build using MATLAB. Randomly divided, 80% of patients was classified as training set, 20% of patients was classified as test set. Accuracy, intersection over union (IOU), Boundary F1 (BF) Score were used to evaluate the predictive effect of the model.

RESULTS

By training in 34760-35652 CTA images (n= 204) and validation in 6968-7860 CTA images (n=68), the DCNN model achieved encouraging predictive performance in test set (n= 68, 6898 slices): Global accuracy 0.9988 ± 5.7735E-05, mean accuracy 0.9546 ± 0.0054, ILT IOU 0.8650 ± 0.0033, aortic lumen IOU 0.8595 ± 0.0085, ILT weighted IOU 0.9976 ± 0.0001, mean IOU 0.9078 ± 0.0029, mean BF Score 0.9829 ± 0.0011. Our DCNN model achieved a mean IOU of more than 90.78% for segmentation of ILT and aortic lumen. It provides a mean relative volume difference between automatic segmentation and ground truth (P> 0.05).

CONCLUSION

An end-to-end DCNN model could be used as an efficient and adjunctive tool for fully automatic segmentation of abdominal aortic thrombus in pre-operative CTA image.

Automated Segmentation of the Human Abdominal Vascular System Using a Hybrid Approach Combining Expert System and Supervised Deep Learning

Background: Computed tomography angiography (CTA) is one of the most commonly used imaging technique for the management of vascular diseases. Here, we aimed to develop a hybrid method combining a feature-based expert system with a supervised deep learning (DL) algorithm to enable a fully automatic segmentation of the abdominal vascular tree. Methods: We proposed an algorithm based on the hybridization of a data-driven convolutional neural network and a knowledge-based model dedicated to vascular system segmentation. By using two distinct datasets of CTA from patients to evaluate independence to training dataset, the accuracy of the hybrid method for lumen and thrombus segmentation was evaluated compared to the feature-based expert system alone and to the ground truth provided by a human expert. Results: The hybrid approach demonstrated a better accuracy for lumen segmentation compared to the expert system alone (volume similarity: 0.8128 vs. 0.7912, p = 0.0006 and Dice similarity coefficient: 0.8266 vs. 0.7942, p < 0.0001). The accuracy for thrombus segmentation was also enhanced using the hybrid approach (volume similarity: 0.9404 vs. 0.9185, p = 0.0027 and Dice similarity coefficient: 0.8918 vs. 0.8654, p < 0.0001). Conclusions: By enabling a robust and fully automatic segmentation, the method could be used to develop real-time decision support to help in the management of vascular diseases.

Artificial intelligence in abdominal aortic aneurysm

OBJECTIVE

Abdominal aortic aneurysm (AAA) is a life-threatening disease, and the only curative treatment relies on open or endovascular repair. The decision to treat relies on the evaluation of the risk of AAA growth and rupture, which can be difficult to assess in practice. Artificial intelligence (AI) has revealed new insights into the management of cardiovascular diseases, but its application in AAA has so far been poorly described. The aim of this review was to summarize the current knowledge on the potential applications of AI in patients with AAA.

METHODS

A comprehensive literature review was performed. The MEDLINE database was searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The search strategy used a combination of keywords and included studies using AI in patients with AAA published between May 2019 and January 2000. Two authors independently screened titles and abstracts and performed data extraction. The search of published literature identified 34 studies with distinct methodologies, aims, and study designs.

RESULTS

AI was used in patients with AAA to improve image segmentation and for quantitative analysis and characterization of AAA morphology, geometry, and fluid dynamics. AI allowed computation of large data sets to identify patterns that may be predictive of AAA growth and rupture. Several predictive and prognostic programs were also developed to assess patients' postoperative outcomes, including mortality and complications after endovascular aneurysm repair.

CONCLUSIONS

AI represents a useful tool in the interpretation and analysis of AAA imaging by enabling automatic quantitative measurements and morphologic characterization. It could be used to help surgeons in preoperative planning. AI-driven data management may lead to the development of computational programs for the prediction of AAA evolution and risk of rupture as well as postoperative outcomes. AI could also be used to better evaluate the indications and types of surgical treatment and to plan the postoperative follow-up. AI represents an attractive tool for decision-making and may facilitate development of personalized therapeutic approaches for patients with AAA.

Segmentation of carotid arterial walls using neural networks

BACKGROUND

Automated, accurate, objective, and quantitative medical image segmentation has remained a challenging goal in computer science since its inception. This study applies the technique of convolutional neural networks (CNNs) to the task of segmenting carotid arteries to aid in the assessment of pathology.

AIM

To investigate CNN's utility as an ancillary tool for researchers who require accurate segmentation of carotid vessels.

METHODS

An expert reader delineated vessel wall boundaries on 4422 axial T2-weighted magnetic resonance images of bilateral carotid arteries from 189 subjects with clinically evident atherosclerotic disease. A portion of this dataset was used to train two CNNs (one to segment the vessel lumen and the other to segment the vessel wall) with the remaining portion used to test the algorithm's efficacy by comparing CNN segmented images with those of an expert reader.

RESULTS

Overall quantitative assessment between automated and manual segmentations was determined by computing the DICE coefficient for each pair of segmented images in the test dataset for each CNN applied. The average DICE coefficient for the test dataset (CNN segmentations compared to expert's segmentations) was 0.96 for the lumen and 0.87 for the vessel wall. Pearson correlation values and the intra-class correlation coefficient (ICC) were computed for the lumen (Pearson = 0.98, ICC = 0.98) and vessel wall (Pearson = 0.88, ICC = 0.86) segmentations. Bland-Altman plots of area measurements for the CNN and expert readers indicate good agreement with a mean bias of 1%-8%.

CONCLUSION

Although the technique produces reasonable results that are on par with expert human assessments, our application requires human supervision and monitoring to ensure consistent results. We intend to deploy this algorithm as part of a software platform to lessen researchers' workload to more quickly obtain reliable results.

Automatic aorta and left ventricle segmentation for TAVI procedure planning using convolutional neural networks

Transcatheter aortic valve implantation (TAVI) is a minimally invasive procedure which is performed on patients with aortic valve defects that are posing a high-risk for conducting a surgical treatment. Preoperative surgical planning and valve sizing play a crucial role in reducing surgery complications and adverse effects such as paravalvular leakage or stroke. Planning process incorporates performing measurements, detecting landmarks and visualizing relevant structures in 3D. To automatize this process, a segmentation is required. Due to the lack of methods enabling parallel aorta and left ventricle segmentation we propose a fully automatic neural network approach based on 2D U-Net architecture. Convolutional neural network architecture was trained on 44 studies (22 raw CTA datasets and 22 elastic deformed scans) and tested on another 18 stacks of data. During every epoch of network learning process cross validation was performed on 8 stacks. As a result, we achieve 0.95 mean Dice coefficient score with standard deviation 0.02 determining high precision of predicted aorta and left ventricle label maps.

Outer Wall Segmentation of Abdominal Aortic Aneurysm by Variable Neighborhood Search Through Intensity and Gradient Spaces

Aortic aneurysm segmentation remains a challenge. Manual segmentation is a time-consuming process which is not practical for routine use. To address this limitation, several automated segmentation techniques for aortic aneurysm have been developed, such as edge detection-based methods, partial differential equation methods, and graph partitioning methods. However, automatic segmentation of aortic aneurysm is difficult due to high pixel similarity to adjacent tissue and a lack of color information in the medical image, preventing previous work from being applicable to difficult cases. This paper uses uses a variable neighborhood search that alternates between intensity-based and gradient-based segmentation techniques. By alternating between intensity and gradient spaces, the search can escape from local optima of each space. The experimental results demonstrate that the proposed method outperforms the other existing segmentation methods in the literature, based on measurements of dice similarity coefficient and jaccard similarity coefficient at the pixel level. In addition, it is shown to perform well for cases that are difficult to segment.

A fully automated pipeline for mining abdominal aortic aneurysm using image segmentation

Imaging software have become critical tools in the diagnosis and the treatment of abdominal aortic aneurysms (AAA). The aim of this study was to develop a fully automated software system to enable a fast and robust detection of the vascular system and the AAA. The software was designed from a dataset of injected CT-scans images obtained from 40 patients with AAA. Pre-processing steps were performed to reduce the noise of the images using image filters. The border propagation based method was used to localize the aortic lumen. An online error detection was implemented to correct errors due to the propagation in anatomic structures with similar pixel value located close to the aorta. A morphological snake was used to segment 2D or 3D regions. The software allowed an automatic detection of the aortic lumen and the AAA characteristics including the presence of thrombus and calcifications. 2D and 3D reconstructions visualization were available to ease evaluation of both algorithm precision and AAA properties. By enabling a fast and automated detailed analysis of the anatomic characteristics of the AAA, this software could be useful in clinical practice and research and be applied in a large dataset of patients.

Automatic Segmentation, Detection, and Diagnosis of Abdominal Aortic Aneurysm (AAA) Using Convolutional Neural Networks and Hough Circles Algorithm

PURPOSE

An abdominal aortic aneurysm (AAA) is known as a cardiovascular disease involving localized deformation (swelling or enlargement) of aorta occurring between the renal and iliac arteries. AAA would jeopardize patients' lives due to its rupturing risk, so prompt recognition and diagnosis of this disorder is vital. Although computed tomography angiography (CTA) is the preferred imaging modality used by radiologist for diagnosing AAA, computed tomography (CT) images can be used too. In the recent decade, there has been several methods suggested by experts in order to find a precise automated way to diagnose AAA without human intervention base on CT and CTA images. Despite great approaches in some methods, most of them need human intervention and they are not fully automated. Also, the error rate needs to decrease in other methods. Therefore, finding a novel fully automated with lower error rate algorithm using CTA and CT images for Abdominal region segmentation, AAA detection, and disease severity classification is the main goal of this paper.

METHODS

The proposed method in this article will be performed in three steps: (1) designing a classifier based on Convolutional Neural Network (CNN) for classifying different parts of abdominal into four different classes such as: abdominal inside region, aorta, body border, and bone. (2) After correct aorta detection, defining its edge and measuring its diameter with the use of Hough Circle Algorithm (which is an algorithm for finding an arbitrary shape in images and measuring its diameter in pixel) is the second step. (3) Ultimately, the detected aorta, depending on its diameter, will be categorized in one of these groups: (a) there is no risk of AAA, (b) there is a medium risk of AAA, and (c) there is a high risk of AAA.

RESULTS

The designed CNN classifier classifies different parts of abdominal into four different classes such as: abdominal inside region, aorta, body border, and bone with the accuracy, precision, and sensitivity of 97.93, 97.94, and 97.93% respectively. The accuracy of the proposed classifier for aorta region detection is 98.62% and Hough Circles algorithm can classify 120 aorta patches according to their diameter with accuracy of 98.33%.

CONCLUSIONS

As a whole, a classifier using Convolutional Neural Network is designed and applied in order to detect AAA region among other abdominal regions. Then Hough Circles algorithm is applied to aorta patches for finding aorta border and measuring its diameter. Ultimately, the detected aortas will be categorized according to their diameters. All steps meet the expected results.

Segmentation of lumen and outer wall of abdominal aortic aneurysms from 3D black-blood MRI with a registration based geodesic active contour model

Segmentation of the geometric morphology of abdominal aortic aneurysm is important for interventional planning. However, the segmentation of both the lumen and the outer wall of aneurysm in magnetic resonance (MR) image remains challenging. This study proposes a registration based segmentation methodology for efficiently segmenting MR images of abdominal aortic aneurysms. The proposed methodology first registers the contrast enhanced MR angiography (CE-MRA) and black-blood MR images, and then uses the Hough transform and geometric active contours to extract the vessel lumen by delineating the inner vessel wall directly from the CE-MRA. The proposed registration based geometric active contour is applied to black-blood MR images to generate the outer wall contour. The inner and outer vessel wall are then fused presenting the complete vessel lumen and wall segmentation. The results obtained from 19 cases showed that the proposed registration based geometric active contour model was efficient and comparable to manual segmentation and provided a high segmentation accuracy with an average Dice value reaching 89.79%.

Generic thrombus segmentation from pre- and post-operative CTA

PURPOSE

Abdominal aortic aneurysm (AAA) is a localized, permanent and irreversible enlargement of the artery, with the formation of thrombus into the inner wall of the aneurysm. A precise patient-specific segmentation of the thrombus is useful for both the pre-operative planning to estimate the rupture risk, and for post-operative assessment to monitor the disease evolution. This paper presents a generic approach for 3D segmentation of thrombus from patients suffering from AAA using computed tomography angiography (CTA) scans.

METHODS

A fast and versatile thrombus segmentation approach has been developed. It is composed of initial centerline detection and aorta lumen segmentation, an optimized pre-processing stage and the use of a 3D deformable model. The approach has been designed to be very generic and requires minimal user interaction. The proposed method was tested on different datasets with 145 patients overall, including pre- and post-operative CTAs, abdominal aorta and iliac artery sections, different calcification degrees, aneurysm sizes and contrast enhancement qualities.

RESULTS

The thrombus segmentation approach showed very accurate results with respect to manual delineations for all datasets ([Formula: see text] and [Formula: see text] for abdominal aorta sections on pre-operative CTA, iliac artery sections on pre-operative CTAs and aorta sections on post-operative CTA, respectively). Experiments on the different patient and image conditions showed that the method was highly versatile, with no significant differences in term of precision. Comparison with the level-set algorithm also demonstrated the superiority of the 3D deformable model. Average processing time was [Formula: see text].

CONCLUSION

We presented a near-automatic and generic thrombus segmentation algorithm applicable to a large variability of patient and imaging conditions. When integrated in an endovascular planning system, our segmentation algorithm shows its compatibility with clinical routine and could be used for pre-operative planning and post-operative assessment of endovascular procedures.

Influence of limited field-of-view on wall stress analysis in abdominal aortic aneurysms

Abdominal aortic aneurysms (AAAs) are local dilations of the aorta which can lead to a fatal hemorrhage when ruptured. Wall stress analysis of AAAs has been widely reported in literature to predict the risk of rupture. Usually, the complete AAA geometry including the aortic bifurcation is obtained by computed tomography (CT). However, performing wall stress analysis based on 3D ultrasound (3D US) has many advantages over CT, although, the field-of-view (FOV) of 3D US is limited and the aortic bifurcation is not easily imaged. In this study, the influence of a limited FOV is examined by performing wall stress analysis on CT-based (total) AAA geometries in 10 patients, and observing the changes in 99th percentile stresses and median stresses while systematically limiting the FOV. Results reveal that changes in the 99th percentile wall stresses are less than 10% when the proximal and distal shoulders of the aneurysm are in the shortened FOV. Wall stress results show that the presence of the aortic bifurcation in the FOV does not influence the wall stresses in high stress regions. Hence, the necessity of assessing the complete FOV, including the aortic bifurcation, is of minor importance. When the proximal and distal shoulders of the AAA are in the FOV, peak wall stresses can be detected adequately.

Implementation and use of 3D pairwise geodesic distance fields for seeding abdominal aortic vessels

PURPOSE

Precise extraction of aorta and the vessels departing from it (i.e. coeliac, renal, and iliac) is vital for correct positioning of a graft prior to abdominal aortic surgery. To perform this task, most of the segmentation algorithms rely on seed points, and better-located seed points provide better initial positions for cross-sectional methods. Under non-optimal acquisition characteristics of daily clinical routine and complex morphology of these vessels, inserting seed points to all these small, but critically important vessels is a tedious, time-consuming, and error-prone task. Thus, in this paper, a novel strategy is developed to generate pathways between user-inserted seed points in order to initialize segmentation methods effectively.

METHOD

The proposed method requires only a single user-inserted seed for each vessel of interest for initializations. Starting from these initial seeds, it automatically generates pathways that span all vessels in between. To accomplish this, first, a geodesic mask is generated by adaptive thresholding, which reinforces the initial seeds to be kept in the vascular tree. Then, a novel implementation of 3D pairwise geodesic distance field (3D-PGDF) is utilized. It is shown that the minimal-valued geodesic of 3D-PGDF successfully defines a path linking the initial seeds as being the shortest geodesic. Moreover, the robustness of the minimum level set of the 3D-PGDF to local variations and regions of high curvature is increased by a region classification strategy, which adds partial geodesics to these critical regions.

RESULTS

The proposed method was applied to 19 challenging CT data sets obtained from four different scanners and compared to two benchmark methods. The first method is a high-precision technique with very long processing time (subvoxel precise multi-stencil fast marching-MSFM), while the second is a very fast method with lower accuracy (3D fast marching). The results, which are obtained using various measures, show that the pathways generated by the developed technique enable significantly higher segmentation performance than 3D fast marching and require much less computational power and time than MSFM.

CONCLUSION

The developed technique offers a useful tool for generating pathways between seed points with minimal user interaction. It guarantees to include all important vessels in a computationally effective manner and thus, it can be used to initialize segmentation methods for abdominal aortic tree.

Automated Delineation of Vessel Wall and Thrombus Boundaries of Abdominal Aortic Aneurysms Using Multispectral MR Images

A correct patient-specific identification of the abdominal aortic aneurysm is useful for both diagnosis and treatment stages, as it locates the disease and represents its geometry. The actual thickness and shape of the arterial wall and the intraluminal thrombus are of great importance when predicting the rupture of the abdominal aortic aneurysms. The authors describe a novel method for delineating both the internal and external contours of the aortic wall, which allows distinguishing between vessel wall and intraluminal thrombus. The method is based on active shape model and texture statistical information. The method was validated with eight MR patient studies. There was high correspondence between automatic and manual measurements for the vessel wall area. Resulting segmented images presented a mean Dice coefficient with respect to manual segmentations of 0.88 and a mean modified Hausdorff distance of 1.14 mm for the internal face and 0.86 and 1.33 mm for the external face of the arterial wall. Preliminary results of the segmentation show high correspondence between automatic and manual measurements for the vessel wall and thrombus areas. However, since the dataset is small the conclusions cannot be generalized.

Automatic aorta segmentation and valve landmark detection in C-arm CT for transcatheter aortic valve implantation

Transcatheter aortic valve implantation (TAVI) is a minimally invasive procedure to treat severe aortic valve stenosis. As an emerging imaging technique, C-arm computed tomography (CT) plays a more and more important role in TAVI on both pre-operative surgical planning (e.g., providing 3-D valve measurements) and intra-operative guidance (e.g., determining a proper C-arm angulation). Automatic aorta segmentation and aortic valve landmark detection in a C-arm CT volume facilitate the seamless integration of C-arm CT into the TAVI workflow and improve the patient care. In this paper, we present a part-based aorta segmentation approach, which can handle structural variation of the aorta in case that the aortic arch and descending aorta are missing in the volume. The whole aorta model is split into four parts: aortic root, ascending aorta, aortic arch, and descending aorta. Discriminative learning is applied to train a detector for each part separately to exploit the rich domain knowledge embedded in an expert-annotated dataset. Eight important aortic valve landmarks (three hinges, three commissures, and two coronary ostia) are also detected automatically with an efficient hierarchical approach. Our approach is robust under all kinds of variations observed in a real clinical setting, including changes in the field-of-view, contrast agent injection, scan timing, and aortic valve regurgitation. Taking about 1.1 s to process a volume, it is also computationally efficient. Under the guidance of the automatically extracted patient-specific aorta model, the physicians can properly determine the C-arm angulation and deploy the prosthetic valve. Promising outcomes have been achieved in real clinical applications.

Geometrical methods for level set based abdominal aortic aneurysm thrombus and outer wall 2D image segmentation

Abdominal aortic aneurysm (AAA) is a localized dilatation of the aortic wall. Accurate measurements of its geometric characteristics are critical for a reliable estimate of AAA rupture risk. However, current imaging modalities do not provide sufficient contrast to distinguish thrombus from surrounding tissue thus making the task of segmentation quite challenging. The main objective of this paper is to address this problem and accurately extract the thrombus and outer wall boundaries from cross sections of a 3D AAA image data set (CTA). This is achieved by new geometrical methods applied to the boundary curves obtained by a Level Set Method (LSM). Such methods address the problem of leakage of a moving front into sectors of similar intensity and that of the presence of calcifications. The versatility of the methods is tested by creating artificial images which simulate the real cases. Segmentation quality is quantified by comparing the results with a manual segmentation of the slices of ten patient data sets. Sensitivity to the parameter settings and reproducibility are analyzed. This is the first work to our knowledge that utilizes the level set framework to extract both the thrombus and external AAA wall boundaries.

Reconstruction and finite element mesh generation of abdominal aortic aneurysms from computerized tomography angiography data with minimal user interactions

Evaluating rupture risk of abdominal aortic aneurysms is critically important in reducing related mortality without unnecessarily increasing the rate of elective repair. According to the current clinical practice aneurysm rupture risk is (mainly) estimated from its maximum diameter and/or expansion rate; an approach motivated from statistics but known to fail often in individuals. In contrast, recent research demonstrated that patient specific biomechanical simulations can provide more reliable diagnostic parameters, however current structural model development is cumbersome and time consuming. This paper used 2D and 3D deformable models to reconstruct aneurysms from computerized tomography angiography data with minimal user interactions. In particular, formulations of frames and shells, as known from structural mechanics, were used to define deformable modes, which in turn allowed a direct mechanical interpretation of the applied set of reconstruction parameters. Likewise, a parallel finite element implementation of the models allows the segmentation of clinical cases on standard personal computers within a few minutes. The particular topology of the applied 3D deformable models supports a fast and simple hexahedral-dominated meshing of the arising generally polyhedral domain. The variability of the derived segmentations (luminal: 0.50(SD 0.19) mm; exterior 0.89(SD 0.45) mm) with respect to large variations in elastic properties of the deformable models was in the range of the differences between manual segmentations as performed by experts (luminal: 0.57(SD 0.24) mm; exterior: 0.77(SD 0.58) mm), and was particularly independent from the algorithm's initialization. The proposed interaction of deformable models and mesh generation defines finite element meshes suitable to perform accurate and efficient structural analysis of the aneurysm using mixed finite element formulations.

Three-dimensional thrombus segmentation in abdominal aortic aneurysms using graph search based on a triangular mesh

An abdominal aortic aneurysm (AAA) is the area of a localized widening of the abdominal aorta, with a frequent presence of thrombus. Segmentation and quantitative analysis of the thrombus in AAA are of paramount importance for diagnosis, risk assessment and determination of treatment options. The proposed thrombus segmentation method utilizes the power and flexibility of the 3-D graph search approach based on a triangular mesh. The method was tested in 9 3-D MDCT angiography data sets (9 patients with AAA, 1300 image slices), and the mean unsigned errors for the luminal and thrombotic surfaces were 0.99+/-0.18 mm and 1.90+/-0.72 mm. To achieve these results, 9.9+/-10.3 control points needed to be interactively entered on 2.1+/-2.2 image slices per 3-D CTA data set.

Segmentation of the outer vessel wall of the common carotid artery in CTA

A novel method is presented for carotid artery vessel wall segmentation in computed tomography angiography (CTA) data. First the carotid lumen is semi-automatically segmented using a level set approach initialized with three seed points. Subsequently, calcium regions located within the vessel wall are automatically detected and classified using multiple features in a GentleBoost framework. Calcium regions segmentation is used to improve localization of the outer vessel wall because it is an easier task than direct outer vessel wall segmentation. In a third step, pixels outside the lumen area are classified as vessel wall or background, using the same GentleBoost framework with a different set of image features. Finally, a 2-D ellipse shape deformable model is fitted to a cost image derived from both the calcium and vessel wall classifications. The method has been validated on a dataset of 60 CTA images. The experimental results show that the accuracy of the method is comparable to the interobserver variability.

Clinical validation of a software for quantitative follow-up of abdominal aortic aneurysm maximal diameter and growth by CT angiography

PURPOSE

To compare the reproducibility and accuracy of abdominal aortic aneurysm (AAA) maximal diameter (D-max) measurements using segmentation software, with manual measurement on double-oblique MPR as a reference standard.

MATERIALS AND METHODS

The local Ethics Committee approved this study and waived informed consent. Forty patients (33 men, 7 women; mean age, 72 years, range, 49-86 years) had previously undergone two CT angiography (CTA) studies within 16 ± 8 months for follow-up of AAA ≥ 35 mm without previous treatment. The 80 studies were segmented twice using the software to calculate reproducibility of automatic D-max calculation on 3D models. Three radiologists reviewed the 80 studies and manually measured D-max on double-oblique MPR projections. Intra-observer and inter-observer reproducibility were calculated by intraclass correlation coefficient (ICC). Systematic errors were evaluated by linear regression and Bland-Altman analyses. Differences in D-max growth were analyzed with a paired Student's t-test.

RESULTS

The ICC for intra-observer reproducibility of D-max measurement was 0.992 (≥ 0.987) for the software and 0.985 (≥ 0.974) and 0.969 (≥ 0.948) for two radiologists. Inter-observer reproducibility was 0.979 (0.954-0.984) for the three radiologists. Mean absolute difference between semi-automated and manual D-max measurements was estimated at 1.1 ± 0.9 mm and never exceeded 5mm.

CONCLUSION

Semi-automated software measurement of AAA D-max is reproducible, accurate, and requires minimal operator intervention.

Initial stress and nonlinear material behavior in patient-specific AAA wall stress analysis

Rupture risk estimation of abdominal aortic aneurysms (AAA) is currently based on the maximum diameter of the AAA. A more critical approach is based on AAA wall stress analysis. For that, in most cases, the AAA geometry is obtained from CT-data and treated as a stress free geometry. However, during CT imaging, the AAA is subjected to a time-averaged blood pressure and is therefore not stress free. The aim of this study is to evaluate the effect of neglecting these initial stresses (IS) on the patient-specific AAA wall stress as computed by finite element analysis. Additionally, the contribution of the nonlinear material behavior of the AAA wall is evaluated. Thirty patients with maximum AAA diameters below the current surgery criterion were scanned with contrast-enhanced CT and the AAA's were segmented from the image data. The mean arterial blood pressure (MAP) was measured immediately after the CT-scan and used to compute the IS corresponding with the CT geometry and MAP. Comparisons were made between wall stress obtained with and without IS and with linear and nonlinear material properties. On average, AAA wall stresses as computed with IS were higher than without IS. This was also the case for the stresses computed with the nonlinear material model compared to the linear material model. However, omitting initial stress and material nonlinearity in AAA wall stress computations leads to different effects in the resulting wall stress for each AAA. Therefore, provided that other assumptions made are not predominant, IS cannot be discarded and a nonlinear material model should be used in future patient-specific AAA wall stress analyses.

Three-dimensional blood vessel quantification via centerline deformation

It is clinically important to quantify the geometric parameters of an abnormal vessel, as this information can aid radiologists in choosing appropriate treatments or apparatuses. Centerline and cross-sectional diameters are commonly used to characterize the morphology of vessel in various clinical applications. Due to the existence of stenosis or aneurysm, the associated vessel centerline is unable to truly portray the original, healthy vessel shape and may result in inaccurate quantitative measurement. To remedy such a problem, a novel method using an active tube model is proposed. In the method, a smoothened centerline is determined as the axis of a deformable tube model that is registered onto the vessel lumen. Three types of regions, normal, stenotic, and aneurysmal regions, are defined to classify the vessel segment under-analyzed by use of the algorithm of a cross-sectional-based distance field. The registration process used on the tube model is governed by different region-adaptive energy functionals associated with the classified vessel regions. The proposed algorithm is validated on the 3-D computer-generated phantoms and 3-D rotational digital subtraction angiography (DSA) datasets. Experimental results show that the deformed centerline provides better vessel quantification results compared with the original centerline. It is also shown that the registered model is useful for measuring the volume of aneurysmal regions.

Towards patient-specific risk assessment of abdominal aortic aneurysm

Diagnosis of vascular disease and selection and planning of therapy are to a large extent based on the geometry of the diseased vessel. Treatment of a particular vascular disease is usually considered if the geometrical parameter that characterizes the severity of the disease, e.g. % vessel narrowing, exceeds a threshold. The thresholds that are used in clinical practice are based on epidemiological knowledge, which has been obtained by clinical studies including large numbers of patients. They may apply "on average", but they can be sub-optimal for individual patients. To realize more patient-specific treatment decision criteria, more detailed knowledge may be required about the vascular hemodynamics, i.e. the blood flow and pressure in the diseased vessel and the biomechanical reaction of the vessel wall to this flow and pressure. Over the last decade, a substantial number of publications have appeared on hemodynamic modeling. Some studies have provided first evidence that this modeling may indeed be used to support therapeutic decisions. The goal of the research reported in this paper is to go one step further, namely to investigate the feasibility of a patient-specific hemodynamic modeling methodology that is not only effective (improves therapeutic decisions), but that is also efficient (easy to use, fast, as much as possible automatic) and robust (insensitive to variation in the quality of the input data, same outcome for different users). A review is presented of our research performed during the last 5 years and the results that were achieved. This research focused on the risk assessment for one particular disease, namely abdominal aortic aneurysm, a life-threatening dilatation of the abdominal aorta.

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

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

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.

An abdominal aortic aneurysm segmentation method: level set with region and statistical information

We present a system for segmenting the human aortic aneurysm in CT angiograms (CTA), which, in turn, allows measurements of volume and morphological aspects useful for treatment planning. The system estimates a rough "initial surface," and then refines it using a level set segmentation scheme augmented with two external analyzers: The global region analyzer, which incorporates a priori knowledge of the intensity, volume, and shape of the aorta and other structures, and the local feature analyzer, which uses voxel location, intensity, and texture features to train and drive a support vector machine classifier. Each analyzer outputs a value that corresponds to the likelihood that a given voxel is part of the aneurysm, which is used during level set iteration to control the evolution of the surface. We tested our system using a database of 20 CTA scans of patients with aortic aneurysms. The mean and worst case values of volume overlap, volume error, mean distance error, and maximum distance error relative to human tracing were 95.3% +/- 1.4% (s.d.); worst case = 92.9%, 3.5% +/- 2.5% (s.d.); worst case = 7.0%, 0.6 +/- 0.2 mm (s.d.); worst case = 1.0 mm, and 5.2 +/- 2.3 mm (s.d.); worst case = 9.6 mm, respectively. When implemented on a 2.8 GHz Pentium IV personal computer, the mean time required for segmentation was 7.4 +/- 3.6 min (s.d.). We also performed experiments that suggest that our method is insensitive to parameter changes within 10% of their experimentally determined values. This preliminary study proves feasibility for an accurate, precise, and robust system for segmentation of the abdominal aneurysm from CTA data, and may be of benefit to patients with aortic aneurysms.

Aortic thrombus segmentation using narrow band active contour model

This paper proposes 2D active contour approach for segmenting thrombus volume from 3D CT images of abdominal aortic aneurysm (AAA). The major challenges in segmenting thrombus are in part because of lack of delineating contrast at anatomical boundaries due to overlap of other soft tissues and artifacts arising from stents and calcium deposits. In the present approach first the bone structures are removed from the image so that these nearby high intensity regions do not interfere in the segmentation process. Next morphological operation is done on the bone-removed image to reduce the effect of streak artifacts. The order of these two operations can be inter-changed. Then, a manual contour is initialized on an axial slice of the pre-processed image and deformed and subsequently propagated to the consecutive slices for deformation. The snake process is governed by force field defined by intensity-based object-ness measure within a band defined by local image properties. The proposed algorithm has been tested on 7 CT images and compared with the ground truth obtained from manual segmentation by radiologist and accuracy between the range 93.16% to 85.08% is observed.