Correlation between transversal and orthogonal maximal diameters of abdominal aortic aneurysms and alternative rupture risk predictors

Artificial Intelligence-Assisted Sac Diameter Assessment for Complex Endovascular Aortic Repair

PURPOSE

Artificial intelligence (AI) using an automated, deep learning-based method, Augmented Radiology for Vascular Aneurysm (ARVA), has been verified as a viable aide in aneurysm morphology assessment. The aim of this study was to evaluate the accuracy of ARVA when analyzing preoperative and postoperative computed tomography angiography (CTA) in patients managed with fenestrated endovascular repair (FEVAR) for complex aortic aneurysms (cAAs).

MATERIALS AND METHODS

Preoperative and postoperative CTAs from 50 patients (n=100 CTAs) who underwent FEVAR for cAAs were extracted from the picture archiving and communication system (PACS) of a single aortic center equipped with ARVA. All studies underwent automated AI aneurysm morphology assessment by ARVA. Appropriate identification of the outer wall of the aorta was verified by manual review of the AI-generated overlays for each patient. Maximum outer-wall aortic diameters were measured by 2 clinicians using multiplanar reconstruction (MPR) and curved planar reformatting (CPR), and among studies where the aortic wall was appropriately identified by ARVA, they were compared with ARVA automated measurements.

RESULTS

Identification of the outer wall of the aorta was accurate in 89% of CTA studies. Among these, diameter measurements by ARVA were comparable to clinician measurements by MPR or CPR, with a median absolute difference of 2.4 mm on the preoperative CTAs and 1.6 mm on the postoperative CTAs. Of note, no significant difference was detected between clinician measurements using MPR or CPR on preoperative and postoperative scans (range 0.5-0.9 mm).

CONCLUSION

For patients with cAAs managed with FEVAR, ARVA provides accurate preoperative and postoperative assessment of aortic diameter in 89% of studies. This technology may provide an opportunity to automate cAA morphology assessment in most cases where time-intensive, manual clinician measurements are currently required.

CLINICAL IMPACT

In this retrospective analysis of preoperative and postoperative imaging from 50 patients managed with FEVAR, AI provided accurate aortic diameter measurements in 89% of the CTAs reviewed, despite the complexity of the aortic anatomies, and in post-operative CTAs despite metal artifact from stent grafts, markers and embolization materials. Outliers with imprecise automated aortic overlays were easily identified by scrolling through the axial AI-generated segmentation MPR cuts of the entire aorta.This study supports the notion that such emerging AI technologies can improve efficiency of routine clinician workflows while maintaining excellent measurement accuracy when analyzing complex aortic anatomies by CTA.

Automatic measurement of maximal diameter of abdominal aortic aneurysm on computed tomography angiography using artificial intelligence

INTRODUCTION

The treatment of abdominal aortic aneurysm (AAA) relies on surgical repair and the indication mainly depends on its size evaluated by the maximal diameter (Dmax). The aim of this study was to evaluate a new automatic method based on artificial intelligence (AI) to measure the Dmax on computed tomography angiography (CTA).

METHODS

A fully automatic segmentation of the vascular system was performed using a hybrid method combining expert system with supervised deep learning (DL). The aorta centreline was extracted from the segmented aorta and the aortic diameters were automatically calculated. Results were compared to manual segmentation performed by two human operators.

RESULTS

The median absolute error between the two human operators was 1.2 mm (IQR 0.5- 1.9). The automatic method using the DL algorithm demonstrated correlation with the human segmentation, with a median absolute error of 0.8 (0.5- 4.2) mm and a coefficient correlation of 0.91 (p<0.001).

CONCLUSION

Although validation in larger cohorts is required, this method brings perspectives to develop new tools to standardize and automate the measurement of AAA Dmax in order to help clinicians in the decision-making process.

Defining a master curve of abdominal aortic aneurysm growth and its potential utility of clinical management

OBJECTIVE

The maximum diameter measurement of an abdominal aortic aneurysm (AAA), which depends on orthogonal and axial cross-sections or maximally inscribed spheres within the AAA, plays a significant role in the clinical decision making process. This study aims to build a total of 21 morphological parameters from longitudinal CT scans and analyze their correlations. Furthermore, this work explores the existence of a "master curve" of AAA growth, and tests which parameters serve to enhance its predictability for clinical use.

METHODS

106 CT scan images from 25 Korean AAA patients were retrospectively obtained. We subsequently computed morphological parameters, growth rates, and pair-wise correlations, and attempted to enhance the predictability of the growth for high-risk aneurysms using non-linear curve fitting and least-square minimization.

RESULTS

An exponential AAA growth model was fitted to the maximum spherical diameter, as the best representative of the growth among all parameters (r-square: 0.94) and correctly predicted to 15 of 16 validation scans based on a 95% confidence interval. AAA volume expansion rates were highly correlated (r=0.75) with thrombus accumulation rates.

CONCLUSIONS

The exponential growth model using spherical diameter provides useful information about progression of aneurysm size and enables AAA growth rate extrapolation during a given surveillance period.

Efficient parallel simulation of hemodynamics in patient-specific abdominal aorta with aneurysm

Surgical planning for aortic aneurysm repair is a difficult task. In addition to the morphological features obtained from medical imaging, alternative features obtained with computational modeling may provide additional useful information. Though numerical studies are noninvasive, they are often time-consuming, especially when we need to study and compare multiple repair scenarios, because of the high computational complexity. In this paper, we present a highly parallel algorithm for the numerical simulation of unsteady blood flows in the patient-specific abdominal aorta before and after the aneurysmic repair. We model the blood flow with the unsteady incompressible Navier-Stokes equations with different outlet boundary conditions, and solve the discretized system with a highly scalable domain decomposition method. With this approach, a high resolution simulation of a full-size adult aorta can be obtained in less than an hour, instead of days with older methods and software. In addition, we show that the parallel efficiency of the proposed method is near 70% on a parallel computer with 2, 880 processor cores.

Predicting abdominal aortic aneurysm growth using patient-oriented growth models with two-step Bayesian inference

OBJECTIVE

For small abdominal aortic aneurysms (AAAs), a regular follow-up examination is recommended every 12 months for AAAs of 30-39 mm and every six months for AAAs of 40-55 mm. Follow-up diameters can determine if a patient follows the common growth model of the population. However, the rapid expansion of an AAA, often associated with higher rupture risk, may be overlooked even though it requires surgical intervention. Therefore, the prognosis of abdominal aortic aneurysm growth is clinically important for planning treatment. This study aims to build enhanced Bayesian inference methods to predict maximum aneurysm diameter.

METHODS

106 CT scans from 25 Korean AAA patients were retrospectively obtained. A two-step approach based on Bayesian calibration was used, and an exponential abdominal aortic aneurysm growth model (population-based) was specified according to each individual patient's growth (patient-specific) and morphologic characteristics of the aneurysm sac (enhanced). The distribution estimates were obtained using a Markov Chain Monte Carlo (MCMC) sampler.

RESULTS

The follow-up diameters were predicted satisfactorily (i.e. the true follow-up diameter was in the 95% prediction interval) for 79% of the scans using the population-based growth model, and 83% of the scans using the patient-specific growth model. Among the evaluated geometric measurements, centerline tortuosity was a significant (p = 0.0002) predictor of growth for AAAs with accelerated and stable expansion rates. Using the enhanced prediction model, 86% of follow-up scans were predicted satisfactorily. The average prediction errors of population-based, patient-specific, and enhanced models were ±2.67, ±2.61 and ± 2.79 mm, respectively.

CONCLUSION

A computational framework using patient-oriented growth models provides useful tools for per-patient basis treatment and enables better prediction of AAA growth.

Decision Tree Based Classification of Abdominal Aortic Aneurysms Using Geometry Quantification Measures

Abdominal aortic aneurysm (AAA) is an asymptomatic aortic disease with a survival rate of 20% after rupture. It is a vascular degenerative condition different from occlusive arterial diseases. The size of the aneurysm is the most important determining factor in its clinical management. However, other measures of the AAA geometry that are currently not used clinically may also influence its rupture risk. With this in mind, the objectives of this work are to develop an algorithm to calculate the AAA wall thickness and abdominal aortic diameter at planes orthogonal to the vessel centerline, and to quantify the effect of geometric indices derived from this algorithm on the overall classification accuracy of AAA based on whether they were electively or emergently repaired. Such quantification was performed based on a retrospective review of existing medical records of 150 AAA patients (75 electively repaired and 75 emergently repaired). Using an algorithm implemented within the MATLAB computing environment, 10 diameter- and wall thickness-related indices had a significant difference in their means when calculated relative to the AAA centerline compared to calculating them relative to the medial axis. Of these 10 indices, nine were wall thickness-related while the remaining one was the maximum diameter (D_max). D_max calculated with respect to the medial axis is over-estimated for both electively and emergently repaired AAA compared to its counterpart with respect to the centerline. C5.0 decision trees, a machine learning classification algorithm implemented in the R environment, were used to construct a statistical classifier. The decision trees were built by splitting the data into 70% for training and 30% for testing, and the properties of the classifier were estimated based on 1000 random combinations of the 70/30 data split. The ensuing model had average and maximum classification accuracies of 81.0 and 95.6%, respectively, and revealed that the three most significant indices in classifying AAA are, in order of importance: AAA centerline length, L2-norm of the Gaussian curvature, and AAA wall surface area. Therefore, we infer that the aforementioned three geometric indices could be used in a clinical setting to assess the risk of AAA rupture by means of a decision tree classifier. This work provides support for calculating cross-sectional diameters and wall thicknesses relative to the AAA centerline and using size and surface curvature based indices in classification studies of AAA.

Applicability of simplified computational models in prediction of peak wall stress in abdominal aortic aneurysms

In the paper impact of different material models on the calculated peak wall stress (PWS) and peak wall rupture risk (PWRR) in abdominal aortic aneurysms (AAAs) is assessed. Computational finite element models of 70 patient-specific AAAs were created using two different material models - a realistic one based on mean population results of uniaxial tests of AAA wall considered as reference, and a 100 times stiffer artificial model. The calculated results of PWS and PWRR were tested to evaluate statistical significance of differences caused by the non-realistic material model. It was shown that for majority of AAAs the differences are insignificant but for some 10% of them their relative differences exceed 20% which may lead to incorrect decisions on their surgical treatment. This percentage of failures favours application of realistic material models in clinical practise although they are much more time-consuming.