Geometric and biomechanical modeling aided by machine learning improves the prediction of growth and rupture of small abdominal aortic aneurysms

A Comprehensive Review on Computational Analysis, Research Advances, and Major Findings on Abdominal Aortic Aneurysms for the Years 2021 to 2023

BACKGROUND

Abdominal aortic aneurysm (AAA) is a pathological condition characterized by the dilation of the lower part of the aorta, where significant hemodynamic forces are present. The prevalence and high mortality risk associated with AAA remain major concerns within the scientific community. There is a critical need for extensive research to understand the underlying mechanisms, pathophysiological characteristics, and effective detection methods for abdominal aortic abnormalities. Additionally, it is imperative to develop and refine both medical and surgical management strategies. This review aims to indicate the role of computational analysis in the comprehension and management of AAAs and covers recent research studies regarding the computational analysis approach conducted between 2021 and 2023. Computational analysis methods have emerged as sophisticated and noninvasive approaches, providing detailed insights into the complex dynamics of AAA and enhancing our ability to study and manage this condition effectively.

METHODS

Computational analysis relies on fluid mechanics principles applied to arterial flow, using the Navier-Stokes equations to model blood flow dynamics. Key hemodynamic indicators relevant to AAAs include Time-Average Wall Shear Stress, Oscillatory Shear Index, Endothelial Cell Activation Potential, and Relative Residence Time. The primary methods employed for simulating the abdominal aorta and studying its biomechanical environment are computational fluid dynamics and Finite Element Methods. This review article encompasses a thorough examination of recent literature, focusing on studies conducted between 2021 and 2023.

RESULTS

The latest studies have elucidated crucial insights into the blood flow characteristics and geometric attributes of AAAs. Notably, blood flow patterns within AAAs are associated with increased rupture risk, along with elevated intraluminal thrombus volume and specific calcification thresholds. Asymmetric AAAs exhibit heightened risks of rupture and thrombus formation due to low and oscillating wall shear stresses. Moreover, larger aneurysms demonstrate increased wall stress, pressure, and energy loss. Advanced modeling techniques have augmented predictive capabilities concerning growth rates and surgical thresholds. Additionally, the influence of material properties and thrombus volume on wall stress levels is noteworthy, while inlet velocity profiles significantly modulate blood flow dynamics within AAAs.

CONCLUSIONS

This review highlights the potential utility of computational modeling. However, the clinical applicability of computational modeling has been limited by methodological variability despite the ongoing accumulation of evidence supporting the prognostic significance of biomechanical and hemodynamic indices in this field. The establishment of standardized reporting is critical for clinical implementation.

New Trends of Personalized Medicine in the Management of Abdominal Aortic Aneurysm: A Review

Abdominal aortic aneurysm (AAA) is a significant vascular condition characterized by the dilation of the abdominal aorta, presenting a substantial risk of rupture and associated high mortality rates. Current management strategies primarily rely on aneurysm diameter and growth rates to predict rupture risk and determine the timing of surgical intervention. However, this approach has limitations, as ruptures can occur in smaller AAAs below surgical thresholds, and many large AAAs remain stable without intervention. This review highlights the need for more precise and individualized assessment tools that integrate biomechanical parameters such as wall stress, wall strength, and hemodynamic factors. Advancements in imaging modalities like ultrasound elastography, computed tomography (CT) angiography, and magnetic resonance imaging (MRI), combined with artificial intelligence, offer enhanced capabilities to assess biomechanical indices and predict rupture risk more accurately. Incorporating these technologies can lead to personalized medicine approaches, improving decision-making regarding the timing of interventions. Additionally, emerging treatments focusing on targeted delivery of therapeutics to weakened areas of the aortic wall, such as nanoparticle-based drug delivery, stem cell therapy, and gene editing techniques like CRISPR-Cas9, show promise in strengthening the aortic wall and halting aneurysm progression. By validating advanced screening modalities and developing targeted treatments, the future management of AAA aims to reduce unnecessary surgeries, prevent ruptures, and significantly improve patient outcomes.

Persistence diagrams for exploring the shape variability of abdominal aortic aneurysms

Abdominal aortic aneurysm consists of a permanent dilation in the abdominal portion of the aorta and, along with its associated pathologies like calcifications and intraluminal thrombi, is one of the most important pathologies of the circulatory system. The shape of the aorta is among the primary drivers for these health issues, with particular reference to all the characteristics which affect the hemodynamics. Starting from the computed tomography angiography of a patient, we propose to summarize such information using tools derived from Topological Data Analysis, obtaining persistence diagrams which describe the irregularities of the lumen of the aorta. We showcase the effectiveness of such shape-related descriptors with a series of supervised and unsupervised case studies.

Computational Hemodynamics-Based Growth Prediction for Small Abdominal Aortic Aneurysms: Laminar Simulations Versus Large Eddy Simulations

Prior studies have shown that computational fluid dynamics (CFD) simulations help assess patient-specific hemodynamics in abdominal aortic aneurysms (AAAs); patient-specific hemodynamic stressors are frequently used to predict an AAA's growth. Previous studies have utilized both laminar and turbulent simulation models to simulate hemodynamics. However, the impact of different CFD simulation models on the predictive modeling of AAA growth remains unknown and is thus the knowledge gap that motivates this study. Specifically, CFD simulations were performed for 70 AAA models derived from 70 patients' computed tomography angiography (CTA) data with known growth status (i.e., fast-growing [> 5 mm/yr] or slowly growing [< 5 mm/yr]). We used laminar and large eddy simulation (LES) models to obtain hemodynamic parameters to predict AAAs' growth status. Predicting the growth status of AAAs was based on morphological, hemodynamic, and patient health parameters in conjunction with three classical machine learning (ML) classifiers, namely, support vector machine (SVM), K-nearest neighbor (KNN), and generalized linear model (GLM). Our preliminary results estimated aneurysmal flow stability and wall shear stress (WSS) were comparable in both laminar and LES flow simulations. Moreover, computed WSS and velocity-related hemodynamic variables obtained from the laminar and LES simulations showed comparable abilities in differentiating the growth status of AAAs. More importantly, the predictive modeling performance of the three ML classifiers mentioned above was similar, with less than a 2% difference observed (p-value > 0.05). In closing, our findings suggest that two different flow simulations investigated did not significantly affect outcomes of computational hemodynamics and predictive modeling of AAAs' growth status, given the data investigated.

Peak wall rupture index is associated with risk of rupture of abdominal aortic aneurysms, independent of size and sex

BACKGROUND

Information on the predictive determinants of abdominal aortic aneurysm rupture from CT angiography are scarce. The aim of this study was to investigate biomechanical parameters in abdominal aortic aneurysms and their association with risk of subsequent rupture.

METHODS

In this retrospective study, the digital radiological archive was searched for 363 patients with ruptured abdominal aortic aneurysms. All patients who underwent at least one CT angiography examination before aneurysm rupture were included. CT angiography results were analysed to determine maximum aneurysm diameter, aneurysm volume, and biomechanical parameters (peak wall stress and peak wall rupture index). In the primary survival analysis, patients with abdominal aortic aneurysms less than 70 mm were considered. Sensitivity analyses including control patients and abdominal aortic aneurysms of all sizes were performed.

RESULTS

A total of 67 patients who underwent 109 CT angiography examinations before aneurysm rupture were identified. The majority were men (47, 70%) and the median age at the time of CTA examination was 77 (71-83) years. The median maximum aneurysm diameter was 56 (interquartile range 46-65) mm and the median time to rupture was 2.13 (interquartile range 0.64-4.72) years. In univariable analysis, maximum aneurysm diameter, aneurysm volume, peak wall stress, and peak wall rupture index were all associated with risk of rupture. Women had an increased HR for rupture when adjusted for maximum aneurysm diameter or aneurysm volume (HR 2.16, 95% c.i. 1.23 to 3.78 (P = 0.007) and HR 1.92, 95% c.i. 1.06 to 3.50 (P = 0.033) respectively). In multivariable analysis, the peak wall rupture index was associated with risk of rupture. The HR for peak wall rupture index was 1.05 (95% c.i. 1.03 to 1.08) per % (P < 0.001) when adjusted for maximum aneurysm diameter and 1.05 (95% c.i. 1.02 to 1.08) per % (P < 0.001) when adjusted for aneurysm volume.

CONCLUSION

Biomechanical factors appear to be important in the prediction of abdominal aortic aneurysm rupture. Women are at increased risk of rupture when adjustments are made for maximum aneurysm diameter alone.

Radiation therapy for cancer is potentially associated with reduced growth of concomitant abdominal aortic aneurysm

PURPOSE

Co-prevalence of abdominal aortic aneurysm (AAA) and cancer poses a unique challenge in medical care since both diseases and their respective therapies might interact. Recently, reduced AAA growth rates were observed in cancer patients that received radiation therapy (RT). The purpose of this study was to perform a fine-grained analysis of the effects of RT on AAA growth with respect to direct (infield) and out-of-field (outfield) radiation exposure, and radiation dose-dependency.

METHODS

A retrospective single-center analysis identified patients with AAA, cancer, and RT. Clinical data, radiation plans, and aneurysm diameters were analyzed. The total dose of radiation to each aneurysm was computed. AAA growth under infield and outfield exposure was compared to patients with AAA and cancer that did not receive RT (no-RT control) and to an external noncancer AAA reference cohort.

RESULTS

Between 2003 and 2020, a total of 38 AAA patients who had received well-documented RT for their malignancy were identified. AAA growth was considerably reduced for infield patients (n = 18) compared to outfield patients (n = 20), albeit not significantly (0.8 ± 1.0 vs. 1.3 ± 1.6 mm/year, p = 0.28). Overall, annual AAA growth in RT patients was lower compared to no-RT control patients (1.1 ± 1.5 vs. 1.8 ± 2.2 mm/year, p = 0.06) and significantly reduced compared to the reference cohort (1.1 ± 1.5 vs. 2.7 ± 2.1 mm/year, p < 0.001). The pattern of AAA growth reduction due to RT was corroborated in linear regression analyses correcting for initial AAA diameter. A further investigation with respect to dose-dependency of radiation effects on AAA growth, however, revealed no apparent association.

CONCLUSION

In this study, both infield and outfield radiation exposure were associated with reduced AAA growth. This finding warrants further investigation, both in a larger scale clinical cohort and on a molecular level.

Machine learning algorithms for the prognostication of abdominal aortic aneurysm progression: a systematic review

INTRODUCTION

Abdominal aortic aneurysm (AAA), often characterized by an abdominal aortic diameter over 3.0 cm, is managed through screening, surveillance, and surgical intervention. AAA growth can be heterogeneous and rupture carries a high mortality rate, with size and certain risk factors influencing rupture risk. Research is ongoing to accurately predict individual AAA growth rates for personalized management. Machine learning, a subset of artificial intelligence, has shown promise in various medical fields, including endoleak detection post-EVAR. However, its application for predicting AAA growth remains insufficiently explored, thus necessitating further investigation. Subsequently, this paper aims to summarize the current status of machine learning in predicting AAA growth.

EVIDENCE ACQUISITION

A systematic database search of Embase, MEDLINE, Cochrane, PubMed and Google Scholar from inception till December 2022 was conducted of original articles that discussed the use of machine learning in predicting AAA growth using the aforementioned databases.

EVIDENCE SYNTHESIS

Overall, 2742 articles were extracted, of which seven retrospective studies involving 410 patients were included using a predetermined criteria. Six out of seven studies applied a supervised learning approach for their machine learning (ML) models, with considerable diversity observed within specific ML models. The majority of the studies concluded that machine learning models perform better in predicting AAA growth in comparison to reference models. All studies focused on predicting AAA growth over specified durations. Maximal luminal diameter was the most frequently used indicator, with alternative predictors being AAA volume, ILT (intraluminal thrombus) and flow-medicated diameter (FMD).

CONCLUSIONS

The nascent field of applying machine learning (ML) for Abdominal Aortic Aneurysm (AAA) expansion prediction exhibits potential to enhance predictive accuracy across diverse parameters. Future studies must emphasize evidencing clinical utility in a healthcare system context, thereby ensuring patient outcome improvement. This will necessitate addressing key ethical implications in establishing prospective studies related to this topic and collaboration among pivotal stakeholders within the AI field.

Identification of abdominal aortic aneurysm subtypes based on mechanosensitive genes

BACKGROUND

Rupture of abdominal aortic aneurysm (rAAA) is a fatal event in the elderly. Elevated blood pressure and weakening of vessel wall strength are major risk factors for this devastating event. This present study examined whether the expression profile of mechanosensitive genes correlates with the phenotype and outcome, thus, serving as a biomarker for AAA development.

METHODS

In this study, we identified mechanosensitive genes involved in AAA development using general bioinformatics methods and machine learning with six human datasets publicly available from the GEO database. Differentially expressed mechanosensitive genes (DEMGs) in AAAs were identified by differential expression analysis. Molecular biological functions of genes were explored using functional clustering, Protein-protein interaction (PPI), and weighted gene co-expression network analysis (WGCNA). According to the datasets (GSE98278, GSE205071 and GSE165470), the changes of diameter and aortic wall strength of AAA induced by DEMGs were verified by consensus clustering analysis, machine learning models, and statistical analysis. In addition, a model for identifying AAA subtypes was built using machine learning methods.

RESULTS

38 DEMGs clustered in pathways regulating 'Smooth muscle cell biology' and 'Cell or Tissue connectivity'. By analyzing the GSE205071 and GSE165470 datasets, DEMGs were found to respond to differences in aneurysm diameter and vessel wall strength. Thus, in the merged datasets, we formally created subgroups of AAAs and found differences in immune characteristics between the subgroups. Finally, a model that accurately predicts the AAA subtype that is more likely to rupture was successfully developed.

CONCLUSION

We identified 38 DEMGs that may be involved in AAA. This gene cluster is involved in regulating the maximum vessel diameter, degree of immunoinflammatory infiltration, and strength of the local vessel wall in AAA. The prognostic model we developed can accurately identify the AAA subtypes that tend to rupture.

An artificial intelligence based abdominal aortic aneurysm prognosis classifier to predict patient outcomes

Abdominal aortic aneurysms (AAA) have been rigorously investigated to understand when their clinically-estimated risk of rupture-an event that is the 13th leading cause of death in the US-exceeds the risk associated with repair. Yet the current clinical guideline remains a one-size-fits-all "maximum diameter criterion" whereby AAA exceeding a threshold diameter is thought to make the risk of rupture high enough to warrant intervention. However, between 7 and 23.4% of smaller-sized AAA have been reported to rupture with diameters below the threshold. In this study, we train and assess machine learning models using clinical, biomechanical, and morphological indices from 381 patients to develop an aneurysm prognosis classifier to predict one of three outcomes for a given AAA patient: their AAA will remain stable, their AAA will require repair based as currently indicated from the maximum diameter criterion, or their AAA will rupture. This study represents the largest cohort of AAA patients that utilizes the first available medical image and clinical data to classify patient outcomes. The APC model therefore represents a potential clinical tool to striate specific patient outcomes using machine learning models and patient-specific image-based (biomechanical and morphological) and clinical data as input. Such a tool could greatly assist clinicians in their management decisions for patients with AAA.

S-Net: a multiple cross aggregation convolutional architecture for automatic segmentation of small/thin structures for cardiovascular applications

With the success of U-Net or its variants in automatic medical image segmentation, building a fully convolutional network (FCN) based on an encoder-decoder structure has become an effective end-to-end learning approach. However, the intrinsic property of FCNs is that as the encoder deepens, higher-level features are learned, and the receptive field size of the network increases, which results in unsatisfactory performance for detecting low-level small/thin structures such as atrial walls and small arteries. To address this issue, we propose to keep the different encoding layer features at their original sizes to constrain the receptive field from increasing as the network goes deeper. Accordingly, we develop a novel S-shaped multiple cross-aggregation segmentation architecture named S-Net, which has two branches in the encoding stage, i.e., a resampling branch to capture low-level fine-grained details and thin/small structures and a downsampling branch to learn high-level discriminative knowledge. In particular, these two branches learn complementary features by residual cross-aggregation; the fusion of the complementary features from different decoding layers can be effectively accomplished through lateral connections. Meanwhile, we perform supervised prediction at all decoding layers to incorporate coarse-level features with high semantic meaning and fine-level features with high localization capability to detect multi-scale structures, especially for small/thin volumes fully. To validate the effectiveness of our S-Net, we conducted extensive experiments on the segmentation of cardiac wall and intracranial aneurysm (IA) vasculature, and quantitative and qualitative evaluations demonstrated the superior performance of our method for predicting small/thin structures in medical images.

3D-Ultrasound Based Mechanical and Geometrical Analysis of Abdominal Aortic Aneurysms and Relationship to Growth

The heterogeneity of progression of abdominal aortic aneurysms (AAAs) is not well understood. This study investigates which geometrical and mechanical factors, determined using time-resolved 3D ultrasound (3D + t US), correlate with increased growth of the aneurysm. The AAA diameter, volume, wall curvature, distensibility, and compliance in the maximal diameter region were determined automatically from 3D + t echograms of 167 patients. Due to limitations in the field-of-view and visibility of aortic pulsation, measurements of the volume, compliance of a 60 mm long region and the distensibility were possible for 78, 67, and 122 patients, respectively. Validation of the geometrical parameters with CT showed high similarity, with a median similarity index of 0.92 and root-mean-square error (RMSE) of diameters of 3.5 mm. Investigation of Spearman correlation between parameters showed that the elasticity of the aneurysms decreases slightly with diameter (p = 0.034) and decreases significantly with mean arterial pressure (p < 0.0001). The growth of a AAA is significantly related to its diameter, volume, compliance, and surface curvature (p < 0.002). Investigation of a linear growth model showed that compliance is the best predictor for upcoming AAA growth (RMSE 1.70 mm/year). To conclude, mechanical and geometrical parameters of the maximally dilated region of AAAs can automatically and accurately be determined from 3D + t echograms. With this, a prediction can be made about the upcoming AAA growth. This is a step towards more patient-specific characterization of AAAs, leading to better predictability of the progression of the disease and, eventually, improved clinical decision making about the treatment of AAAs.

Deep-learning-based image segmentation for image-based computational hemodynamic analysis of abdominal aortic aneurysms: a comparison study

Computational hemodynamics is increasingly being used to quantify hemodynamic characteristics in and around abdominal aortic aneurysms (AAA) in a patient-specific fashion. However, the time-consuming manual annotation hinders the clinical translation of computational hemodynamic analysis. Thus, we investigate the feasibility of using deep-learning-based image segmentation methods to reduce the time required for manual segmentation. Two of the latest deep-learning-based image segmentation methods, ARU-Net and CACU-Net, were used to test the feasibility of automated computer model creation for computational hemodynamic analysis. Morphological features and hemodynamic metrics of 30 computed tomography angiography (CTA) scans were compared between pre-dictions and manual models. The DICE score for both networks was 0.916, and the correlation value was above 0.95, indicating their ability to generate models comparable to human segmentation. The Bland-Altman analysis shows a good agreement between deep learning and manual segmentation results. Compared with manual (computational hemodynamics) model recreation, the time for automated computer model generation was significantly reduced (from ∼2 h to ∼10 min). Automated image segmentation can significantly reduce time expenses on the recreation of patient-specific AAA models. Moreover, our study showed that both CACU-Net and ARU-Net could accomplish AAA segmentation, and CACU-Net outperformed ARU-Net in terms of accuracy and time-saving.

Characterization of small abdominal aortic aneurysms' growth status using spatial pattern analysis of aneurismal hemodynamics

Aneurysm hemodynamics is known for its crucial role in the natural history of abdominal aortic aneurysms (AAA). However, there is a lack of well-developed quantitative assessments for disturbed aneurysmal flow. Therefore, we aimed to develop innovative metrics for quantifying disturbed aneurysm hemodynamics and evaluate their effectiveness in predicting the growth status of AAAs, specifically distinguishing between fast-growing and slowly-growing aneurysms. The growth status of aneurysms was classified as fast (≥ 5 mm/year) or slow (< 5 mm/year) based on serial imaging over time. We conducted computational fluid dynamics (CFD) simulations on 70 patients with computed tomography (CT) angiography findings. By converting hemodynamics data (wall shear stress and velocity) located on unstructured meshes into image-like data, we enabled spatial pattern analysis using Radiomics methods, referred to as "Hemodynamics-informatics" (i.e., using informatics techniques to analyze hemodynamic data). Our best model achieved an AUROC of 0.93 and an accuracy of 87.83%, correctly identifying 82.00% of fast-growing and 90.75% of slowly-growing AAAs. Compared with six classification methods, the models incorporating hemodynamics-informatics exhibited an average improvement of 8.40% in AUROC and 7.95% in total accuracy. These preliminary results indicate that hemodynamics-informatics correlates with AAAs' growth status and aids in assessing their progression.

Computerized Differentiation of Growth Status for Abdominal Aortic Aneurysms: A Feasibility Study

Fast-growing abdominal aortic aneurysms (AAA) have a high rupture risk and poor outcomes if not promptly identified and treated. Our primary objective is to improve the differentiation of small AAAs' growth status (fast versus slow-growing) through a combination of patient health information, computational hemodynamics, geometric analysis, and artificial intelligence. 3D computed tomography angiography (CTA) data available for 70 patients diagnosed with AAAs with known growth status were used to conduct geometric and hemodynamic analyses. Differences among ten metrics (out of ninety metrics) were statistically significant discriminators between fast and slow-growing groups. Using a support vector machine (SVM) classifier, the area under receiving operating curve (AUROC) and total accuracy of our best predictive model for differentiation of AAAs' growth status were 0.86 and 77.50%, respectively. In summary, the proposed analytics has the potential to differentiate fast from slow-growing AAAs, helping guide resource allocation for the management of patients with AAAs.

AI-powered assessment of biomarkers for growth prediction of abdominal aortic aneurysms

Objective

The purpose of this study was to employ biomechanics-based biomarkers to locally characterize abdominal aortic aneurysm (AAA) tissue and investigate their relation to local aortic growth by means of an artificial intelligence model.

Methods

The study focused on a population of 36 patients with AAAs undergoing serial monitoring with electrocardiogram-gated multiphase computed tomography angiography acquisitions. The geometries of the aortic lumen and wall were reconstructed from the baseline scans and used for the baseline assessment of regional aortic weakness with three functional biomarkers, time-averaged wall-shear stress, in vivo principal strain, and intra-luminal thrombus thickness. The biomarkers were encoded as regional averages on axial and circumferential sections perpendicularly to the aortic centerline. Local diametric growth was obtained as difference in diameter between baseline and follow-up at the level of each axial section. An artificial intelligence model was developed to predict accelerated aneurysmal growth with the Extra Trees algorithm used as a binary classifier where the positive class represented regions that grew more than 2.5 mm/year. Additional clinical biomarkers, such as maximum aortic diameter at baseline, were also investigated as predictors of growth.

Results

The area under the curve for the constructed receiver operating characteristic curve for the Extra Trees classifier showed a very good performance in predicting relevant aortic growth (area under the curve = 0.92), with the three biomechanics-based functional biomarkers being objectively selected as the main predictors of growth.

Conclusions

The use of features based on the functional and local characterization of the aortic tissue resulted in a superior performance in terms of growth prediction when compared with models based on geometrical assessments. With rapid growth linked to increasing risk for patients with AAAs, the ability to access functional information related to tissue weakening and disease progression at baseline has the potential to support early clinical decisions and improve disease management.

Three-dimensional growth and biomechanical risk progression of abdominal aortic aneurysms under serial computed tomography assessment

Growth of abdominal aortic aneurysms (AAAs) is often described as erratic and discontinuous. This study aimed at describing growth patterns of AAAs with respect to maximal aneurysm diameter (Dmax) and aneurysm volume, and to characterize changes in the intraluminal thrombus (ILT) and biomechanical indices as AAAs grow. 384 computed tomography angiographies (CTAs) from 100 patients (mean age 70.0, standard deviation, SD = 8.5 years, 22 women), who had undergone at least three CTAs, were included. The mean follow-up was 5.2 (SD = 2.5) years. Growth of Dmax was 2.64 mm/year (SD = 1.18), volume 13.73 cm³/year (SD = 10.24) and PWS 7.3 kPa/year (SD = 4.95). For Dmax and volume, individual patients exhibited linear growth in 87% and 77% of cases. In the tertile of patients with the slowest Dmax-growth (< 2.1 mm/year), only 67% belonged to the slowest tertile for volume-growth, and 52% and 55% to the lowest tertile of PWS- and PWRI-increase, respectively. The ILT-ratio (ILT-volume/aneurysm volume) increased with time (2.6%/year, p < 0.001), but when adjusted for volume, the ILT-ratio was inversely associated with biomechanical stress. In contrast to the notion that AAAs grow in an erratic fashion most AAAs displayed continuous and linear growth. Considering only change in Dmax, however, fails to capture the biomechanical risk progression, and parameters such as volume and the ILT-ratio need to be considered.

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.

A quarter of a century biomechanical rupture risk assessment of abdominal aortic aneurysms. Achievements, clinical relevance, and ongoing developments

Abdominal aortic aneurysm (AAA) disease, the local enlargement of the infrarenal aorta, is a serious condition that causes many deaths, especially in men exceeding 65 years of age. Over the past quarter of a century, computational biomechanical models have been developed towards the assessment of AAA risk of rupture, technology that is now on the verge of being integrated within the clinical decision-making process. The modeling of AAA requires a holistic understanding of the clinical problem, in order to set appropriate modeling assumptions and to draw sound conclusions from the simulation results. In this article we summarize and critically discuss the proposed modeling approaches and report the outcome of clinical validation studies for a number of biomechanics-based rupture risk indices. Whilst most of the aspects concerning computational mechanics have already been settled, it is the exploration of the failure properties of the AAA wall and the acquisition of robust input data for simulations that has the greatest potential for the further improvement of this technology.

Assessment of shape-based features ability to predict the ascending aortic aneurysm growth

The current guidelines for the ascending aortic aneurysm (AsAA) treatment recommend surgery mainly according to the maximum diameter assessment. This criterion has already proven to be often inefficient in identifying patients at high risk of aneurysm growth and rupture. In this study, we propose a method to compute a set of local shape features that, in addition to the maximum diameter D, are intended to improve the classification performances for the ascending aortic aneurysm growth risk assessment. Apart from D, these are the ratio DCR between D and the length of the ascending aorta centerline, the ratio EILR between the length of the external and the internal lines and the tortuosity T. 50 patients with two 3D acquisitions at least 6 months apart were segmented and the growth rate (GR) with the shape features related to the first exam computed. The correlation between them has been investigated. After, the dataset was divided into two classes according to the growth rate value. We used six different classifiers with input data exclusively from the first exam to predict the class to which each patient belonged. A first classification was performed using only D and a second with all the shape features together. The performances have been evaluated by computing accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC) and positive (negative) likelihood ratio LHR+ (LHR-). A positive correlation was observed between growth rate and DCR (r = 0.511, p = 1.3e-4) and between GR and EILR (r = 0.472, p = 2.7e-4). Overall, the classifiers based on the four metrics outperformed the same ones based only on D. Among the diameter-based classifiers, k-nearest neighbours (KNN) reported the best accuracy (86%), sensitivity (55.6%), AUROC (0.74), LHR+ (7.62) and LHR- (0.48). Concerning the classifiers based on the four shape features, we obtained the best accuracy (94%), sensitivity (66.7%), specificity (100%), AUROC (0.94), LHR+ (+∞) and LHR- (0.33) with support vector machine (SVM). This demonstrates how automatic shape features detection combined with risk classification criteria could be crucial in planning the follow-up of patients with ascending aortic aneurysm and in predicting the possible dangerous progression of the disease.

Rupture risk parameters upon biomechanical analysis independently change from vessel geometry during abdominal aortic aneurysm growth

Objective

The indication for abdominal aortic aneurysm (AAA) repair is based on a diameter threshold. However, mechanical properties, such as peak wall stress (PWS) and peak wall rupture index (PWRI), influence the individual rupture risk. This study aims to correlate biomechanical and geometrical AAA characteristics during aneurysm growth applying a new linear transformation-based comparison of sequential imaging.

Methods

Patients with AAA with two sequential computed tomography angiographies (CTA) were identified from a single-center aortic database. Patient characteristics included age, gender, and comorbidities. Semiautomated segmentation of CTAs was performed using Endosize (Therenva) for geometric variables (diameter, neck configuration, α/β angle, and vessel tortuosity) and for finite element method A4 Clinics Research Edition (Vascops) for additional variables (intraluminal thrombus [ILT]), vessel volume, PWS, PWRI). Maximum point coordinates from at least one CTA 6 to 24 months before their final were predicted for the final preoperative CTA using linear transformation along fix and validation points to estimate spatial motion. Pearson's correlation and the t test were used for comparison.

Results

Thirty-two eligible patients (median age, 70 years) were included. The annual AAA growth rate was 3.7 mm (interquartile range [IQR], 2.25-5.44; P < .001) between CTs. AAA (+17%; P < .001) and ILT (+43%; P < .001) volume, maximum ILT thickness (+35%; P < .001), β angle (+1.96°; P = .017) and iliac tortuosity (+0.009; P = .012) increased significantly. PWS (+12%; P = .0029) and PWRI (+16%; P < .001) differed significantly between both CTAs. Both mechanical parameters correlated most significantly with the AAA volume increase (r = 0.68 [P < .001] and r = 0.6 [P < .001]). Changes in PWS correlated best with the aneurysm neck configuration. The spatial motion of maximum ILT thickness was 14.4 mm (IQR, 7.3-37.2), for PWS 8.4 mm (IQR, 3.8-17.3), and 11.5 mm (IQR, 5.9-31.9) for PWRI. Here, no significant correlation with any of the aforementioned parameters, patient age, or time interval between CTs were observed.

Conclusions

PWS correlates highly significant with vessel volume and aneurysm neck configuration. Spatial motion of maximum ILT thickness, PWS, and PWRI is detectable and predictable and might expose different aneurysm wall segments to maximum stress throughout aneurysm growth. Linear transformation could thus add to patient-specific rupture risk analysis.

Clinical Relevance

Abdominal aortic aneurysm rupture risk assessment is a key feature in future individualized therapy approaches for patients, since more and more data are obtained concluding a heterogeneous disease entity that might not be addressed ideally looking only at diameter enlargement. The approach presented in this pilot study demonstrates the feasibility and importance of measuring peak wall stress and rupture risk indices based on predicted and actual position of maximum stress points including intraluminal thrombus.

Neural operator learning of heterogeneous mechanobiological insults contributing to aortic aneurysms

Thoracic aortic aneurysm (TAA) is a localized dilatation of the aorta that can lead to life-threatening dissection or rupture. In vivo assessments of TAA progression are largely limited to measurements of aneurysm size and growth rate. There is promise, however, that computational modelling of the evolving biomechanics of the aorta could predict future geometry and properties from initiating mechanobiological insults. We present an integrated framework to train a deep operator network (DeepONet)-based surrogate model to identify TAA contributing factors using synthetic finite-element-based datasets. For training, we employ a constrained mixture model of aortic growth and remodelling to generate maps of local aortic dilatation and distensibility for multiple TAA risk factors. We evaluate the performance of the surrogate model for insult distributions varying from fusiform (analytically defined) to complex (randomly generated). We propose two frameworks, one trained on sparse information and one on full-field greyscale images, to gain insight into a preferred neural operator-based approach. We show that this continuous learning approach can predict the patient-specific insult profile associated with any given dilatation and distensibility map with high accuracy, particularly when based on full-field images. Our findings demonstrate the feasibility of applying DeepONet to support transfer learning of patient-specific inputs to predict TAA progression.

Radiation and chemotherapeutics are associated with altered aortic aneurysm growth in cancer patients

INTRODUCTION

Co-prevalence of aorto-iliac aneurysm (i.e. AAA) and cancer confronts patients and physicians with two life-threatening diseases. Modern chemotherapeutics and target therapies might impact the aneurysm wall integrity and subsequently affect growth. The purpose of this study was to assess associations between malignancy, therapeutic regimens and the growth rates of aorto-iliac aneurysms.

PATIENTS AND METHODS

A retrospective single-center analysis identified patients with aneurysm + cancer. Patients with ≥2 CT angiograms over ≥6 months and additional malignancy were included. Clinical data and aneurysm diameters were analyzed. AAA growth under cancer therapy (chemotherapy/radiation) was compared to a non-cancer AAA control cohort and to meta-analysis data. Statistics included t-tests and a linear regression model with correction for initial aortic diameter and type of treatment.

RESULTS

From 2003 - 2020, 217 patients (median age 70 years; 92% male) with 246 aneurysms (58.8% AAA) and 238 malignancies were identified. Prostate (27%) and lung (16%) cancer were most frequently seen, 157 patients (72%) received chemotherapy and 105 patients (48%) radiation, thereof 79 (36.4%) both. Annual AAA growth was not significantly different for cancer and non-cancer patients (2.0±2.3 vs. 2.8±2.1mm/y, p=0.20). However, subgroup analyses revealed that radiation was associated with a significantly reduced aneurysm growth rate compared to cancer patients without radiation (1.1±1.3 vs. 1.6±2.1 mm/y, p=0.046) and to the non-cancer control cohort (1.7±1.9 vs. 2.8±2.1 mm/y, p=0.007). Administration of antimetabolites showed significantly increased AAA growth (+0.9mm/year, p=0.011), while e.g. topoisomerase inhibitors (-0.8mm/year, p=0.17) and anti-androgens (-0.5mm/year, p=0.27) showed a possible trend for reduced growth. Similar was observed for iliac aneurysms (n=85). Additionally, effects were persistent in combinations of chemotherapies (2.6±1.4 substances/patient).

CONCLUSION

Cancer patients with concomitant aortic aneurysms may require intensified monitoring when undergoing specific therapies, such as antimetabolites, since they may experience an increased aneurysm growth rate. Radiation may be associated with reduced aneurysm growth.

Low Shear Stress at Baseline Predicts Expansion and Aneurysm-Related Events in Patients With Abdominal Aortic Aneurysm

BACKGROUND

Low shear stress has been implicated in abdominal aortic aneurysm (AAA) expansion and clinical events. We tested the hypothesis that low shear stress in AAA at baseline is a marker of expansion rate and future aneurysm-related events.

METHODS

Patients were imaged with computed tomography angiography at baseline and followed up every 6 months >24 months with ultrasound measurements of maximum diameter. From baseline computed tomography angiography, we reconstructed 3-dimensional models for automated computational fluid dynamics simulations and computed luminal shear stress. The primary composite end point was aneurysm repair and/or rupture, and the secondary end point was aneurysm expansion rate.

RESULTS

We included 295 patients with median AAA diameter of 49 mm (interquartile range, 43-54 mm) and median follow-up of 914 (interquartile range, 670-1112) days. There were 114 (39%) aneurysm-related events, with 13 AAA ruptures and 98 repairs (one rupture was repaired). Patients with low shear stress (<0.4 Pa) experienced a higher number of aneurysm-related events (44%) compared with medium (0.4-0.6 Pa; 27%) and high (>0.6 Pa; 29%) shear stress groups (P=0.010). This association was independent of known risk factors (adjusted hazard ratio, 1.72 [95% CI, 1.08-2.73]; P=0.023). Low shear stress was also independently associated with AAA expansion rate (β=+0.28 mm/y [95% CI, 0.02-0.53]; P=0.037).

CONCLUSIONS

We show for the first time that low shear stress (<0.4 Pa) at baseline is associated with both AAA expansion and future aneurysm-related events. Aneurysms within the lowest tertile of shear stress, versus those with higher shear stress, were more likely to rupture or reach thresholds for elective repair. Larger prospective validation trials are needed to confirm these findings and translate them into clinical management.