The 10-year outcomes of a regional abdominal aortic aneurysm screening program

Screening Men and Women above the Age of 50 Years for Abdominal Aortic Aneurysm: A Pilot Study in an Upper Middle Income Country

OBJECTIVE

Screening for abdominal aortic aneurysm (AAA) is recommended in high risk populations based on local conditions. Differences in lifestyle and risk factors between countries with different income status make risk stratification based on geographic location necessary. The majority of epidemiological studies on AAA have reported data from high income countries. The aim of this study was to explore the prevalence and risk factors for AAA in an upper middle income country in Eastern Europe.

METHODS

A pilot screening project for AAA, supported by a mass media campaign, was conducted in 2023 in seven cities in Serbia. Ultrasound evaluation of the abdominal aorta was performed by a registered vascular surgeon on individuals who agreed to participate. Participants who attended screening completed a questionnaire on demographic and clinical information. To assess risk factors for AAA, univariable logistic regression analysis was performed to compute the odds ratio (OR) with 95% confidence interval (CI). Multivariable logistic regression was subsequently performed with adjustments for sex, age, family history of AAA, and other relevant factors.

RESULTS

A total of 4 046 participants (51.2% male and 48.8% female; mean age 68.8 ± 7.6 years) responded to the campaign. An aneurysm was found in 195 (4.8%) screened individuals (8.2% of men and 1.3% of women). In males aged 50 - 64 years, the prevalence of AAA was 5.4%. Male sex, older age, family history of AAA, being a smoker or ex-smoker, being overweight, and alcohol consumption were predictors of AAA in the univariable analysis. After adjustments in the multivariable analysis, male sex (OR 8.04, 95% CI 4.87 - 13.28), older age (OR 1.04, 95% CI 1.02 - 1.07), positive family history (OR 2.47, 95% CI 1.61 - 3.78), smoker status (OR 3.10, 95% CI 2.10 - 4.59), ex-smoker status (OR 2.13, 95% CI 1.39 - 3.27), and being overweight (OR 1.85, 95% CI 1.25 - 2.74) were independent risk factors for AAA.

CONCLUSION

The prevalence of AAA has not been reduced in all countries, and screening strategies might be changed based on local epidemiological data. The results of this pilot study underline the importance of exploring the prevalence of AAA in populations with a high prevalence of smoking.

Eleven-Year Outcomes of a Screening Project for Abdominal Aortic Aneurysm (AAA) in 65-Year-Old Men

Objective

Since 2011, the Department of Vascular Surgery at Oslo University Hospital has offered screening for abdominal aortic aneurysm (AAA) to 65-year-old men living in Oslo, Norway. The aim of this study was to evaluate the effect of the screening project on AAA-related mortality and rupture and repair rates in the screened population.

Methods

This cohort study included men that participated in AAA screening at the Department of Vascular Surgery at Oslo University Hospital in the period May 2011 to September 2019. All men with screen-detected AAA (aortic diameter ≥30 mm) and subaneurysmal aortic dilatation (aortic diameter 25-29 mm) were included. A stratified (1:1 with the subaneurysm group), randomized selection of men with normal aortic diameter (<25 mm) upon screening was also included. The follow-up data on events (ruptures, repairs, and deaths) after screening were collected retrospectively from patient electronic medical records at Oslo University Hospital, the National Population Register and the Norwegian Cause of Death Registry (CoDR).

Results

In total, 2048 men were included, with a median follow-up time of 7.1 years (IQR 3.8). Among men with screen-detected AAA, 0.6% died of AAA-related causes (0.9 AAA-related deaths per 1000 person-years). The rupture rate was 0.3% among men with screen-detected AAA or subaneurysmal aortic dilatation, giving an incidence of 0.5 ruptures per 1000 person-years. The overall repair rate in the AAA group was 20.6% (36.1 repairs per 1000 person-years) and 0.6% (0.9 repairs per 1000 person-years) in the subaneurysm group.

Conclusion

In a population screened for AAA, the incidence of rupture and the AAA-related mortality was very low. Almost one-fifth of the participants with screen-detected AAA underwent elective repair, representing a group that might have presented with rupture if untreated. These results indicate that screening is valuable in preventing AAA rupture and AAA-related mortality.

Increased aortic repair in Germany correlates with reduction of death caused by aortic aneurysms but not aortic dissections

INTRODUCTION

We asked if there is a significant correlation between the increasing trend in aortic repair (AR) and decreasing aortic aneurysm (AA) and aortic dissection (AD) mortality? Therefore, we retrospectively analyzed all aortic repairs in patients with AA and AD and its correlation with disease-specific death rates and hospitalizations for ruptured AA and AD in Germany.

METHODS

We retrieved the number of cases hospitalized for AA and AD as well as the procedures in these cases from the Federal Bureau of Statistics (DRG statistics) and death rates from the national mortality statistic published by the Federal Statistical Office in Germany for the years 2006-2017.

RESULTS

From 2006 to 2017, the total number of hospitalized cases admitted with principal diagnosis of AA increased by 25.8% and that of AD by 56.7%. That of cases with the principal diagnosis of ruptured AA (rAA) remained unchanged (-2.5%) and that with rAD increased by 54.6%. The number of (open and endovascular) procedures in cases hospitalized for AA increased by 39.4% and for AD by 126.4%. The age-adjusted death rates in Germany for AA decreased from 4.0 to 2.9 per 100,000 inhabitants and that for AD increased from 1.0 to 1.4. The decrease in death attributed to AA cases can be described by linear regression as y = -0.0003*y + 6.7076 (p < 0.0001). Accepting this association between increased elective procedures and reduced AA mortality, each/all 1000 procedures save 0.3 lives per 100,000 inhabitants.

CONCLUSION

Despite increasing numbers of AR for AA and AD, only the mortality rate for all AAs decreased, while we did not observe a decrease in overall mortality of AD in Germany.

High prevalence of abdominal aortic aneurysm in older men with cerebrovascular disease: Evaluation of a local screening program

Introduction

Patients with cerebrovascular disease may suffer from other vascular morbidities, such as abdominal aortic aneurysm (AAA). Previously, a high prevalence of AAA has been demonstrated in men 60 years of age and older who have experienced TIA or stroke. This report evaluates the results of a decade's operation of a local screening program for AAA in this selected neurologic population.

Methods

Men aged ≥60 years and admitted to the neurology ward of a community-based hospital in the Netherlands from 2006 to 2017 with a diagnosis of TIA or stroke were selected for screening. The diameter of the abdominal aorta was assessed by abdominal ultrasonography. Patients with detected AAA were referred for evaluation by a vascular surgeon.

Results

AAA was detected in 72 of 1,035 screened patients (6.9%). AAAs with a diameter of 3.0-3.9 cm accounted for 61.1% of the total aneurysms found; AAAs with a diameter of 4.0-5.4 cm accounted for 20.8% of the total; and large aneurysms with a diameter of ≥5.5 cm accounted for 18.1% of all aneurysms discovered. A total of 18 patients (1.7%) underwent elective aneurysm repair.

Discussion

The detection rate of AAA in older men with cerebrovascular disease was roughly 5-fold the detection rate in known European screening programs in older men from the general population. The proportion of large AAAs (≥5.5 cm) was also substantially higher. These findings reveal a previously unknown co-morbidity in patients with cerebrovascular disease and may be helpful for cardiovascular management of this large group of neurologic patients. Current and future AAA screening programs may also benefit from this knowledge.

Accuracy of Point-of-Care Ultrasound in Follow Up Abdominal Aortic Aneurysm Imaging

BACKGROUND

Point-of-care ultrasound (POCUS) has been reported as a valuable tool for bedside diagnoses of abdominal Aortic Aneurysms (AAA). However, no data exist regarding POCUS in measuring follow-up AAA diameter studies in patients with existing AAAs. The purpose of this study was to determine the variability of aortic measurements performed by a non-physician using POCUS vs standard of care (SOC) measurements by a registered vascular technologist or an abdominal/pelvic CT scan.

METHODS

A prospective observational ultrasound study was performed from 1/1/2019 to 3/31/2021 on patients with a diagnosis of an AAA (≥3.0 cm). A research coordinator (non-physician) underwent a 3-hour training session in ultrasound operation and basic human anatomy to measure AAA diameter. The maximum aortic diameter was documented and compared to measurements obtained by SOC ultrasonography or CT scan. The POCUS and SOC ultrasounds were separated by no more than 90 days. Clinical risk factors including age, race, body mass index, coronary artery disease, hypertension, peripheral vascular disease, cerebrovascular disease, diabetes, and current smoking were also collected.

RESULTS

Eighty-one patients (mean age: 73.6 ± 5.8 years, body mass index: 29.5 ± 6.2 kg/m2) were being followed in a vascular clinic and underwent both a POCUS and SOC ultrasounds. One indeterminant study was reported in identifying an AAA diagnosis, due to an overlying colostomy. The average follow-up time from initial screening aortic diameter to POCUS was 4.4 ± 3.7 years. Overall average aortic diameter measurements obtained were 4.1 ± .9 cm for POCUS and 4.0 ± .9 cm for SOC (P = NS). Average difference in aortic measurement for POCUS and SOC was -.1 ± .3 cm.

CONCLUSIONS

POCUS is an accurate method to follow AAA diameter in patients. POCUS could improve patient follow up with AAA diameter measurements, streamline care and reduce overall burden for both patients and Radiology Departments in assessing follow up AAA diameters.

Impact of Implicit Abdominal Aortic Aneurysm Screening in the Veterans Affairs Health Care System Over 10 Years

Background

Abdominal aortic aneurysm (AAA) screening programs have been active in the United States since 2005, but are not the only way AAAs are detected. AAA management and outcomes have not been investigated broadly in the context of “implicit AAA screening,” whereby radiologic examinations not intended for focused screening can identify AAAs.

Methods and Results

We examined the association between imaging‐based AAA screening, both explicit and implicit, and various outcomes for ≈1.6 million veterans in the Veterans Affairs health care system from 2005 to 2015. Screened‐positive, screened‐negative, and unscreened veterans were identified in the overall cohort and within a subgroup of veterans aged 65 years in 2005. The yearly composite screening rate increased over 10 years, from 11.7% to 18.3%, whereas the screened‐positive rate decreased from 7.3% to 4.9%. Only 12.9% of screening examinations were explicit AAA screening ultrasounds. The subgroup’s composite screening rate was 74% within its 10‐year eligibility window, with implicit screening accounting for 91.8% of examinations. In the 2005 subgroup, all‐cause mortality and Charlson comorbidity scores were higher for veterans who underwent screening compared with those unscreened (31.2% versus 23.1% and 0.47 versus 0.25, respectively; P<0.001). AAA rupture rates were similar between those unscreened and screened‐negative individuals.

Conclusions

Accounting for both explicit and implicit screening, AAA screening in the Veterans Affairs population has moderate reach. Efforts to expand explicit AAA screening are not likely to impact either all‐cause mortality or AAA rupture on the population scale as significantly as a careful accounting for and use of implicit screening data.

Costs of abdominal aortic aneurysm care at a regional Veterans Affairs medical center with the implementation of an abdominal aortic aneurysm screening program

BACKGROUND

Abdominal aortic aneurysm (AAA) screening has demonstrated to be cost-effective in reducing AAA-related morbidity and all-cause mortality. However, the downstream care costs of an implemented AAA screening in clinical practice have not been reported. The purpose of this study is to determine direct regional Department of Veterans Affairs (VA) costs in implementing and sustaining an AAA screening program over a 10-year period.

METHODS

A cost data analysis (adjusted to 2021 U.S. dollars) of an AAA screening program was conducted from 2007 to 2016, where 19,649 veteran patients aged 65-75 with a smoking history were screened at a regional VA medical center. A decision support system tracked direct and indirect encounter costs from Medicare billing codes associated with AAA care. Costs from a patient's initial screening, follow-up imaging, to AAA repair or at the end of the analysis period, March 31, 2021, were recorded. Costs for AAA repairs outside the VA system were also tracked.

RESULTS

A total of 1,183 patients screened were identified with an AAA ≥3.0 cm without history of repair. Estimated screening costs were $2.8 million or $280,000 annually ($143/screening) in the care of 19,649 screened patients. There were 221 patients who required repair (143 repairs in VA, 78 repairs outside VA). The average cost of elective endovascular repair was $43,021 and that of open repair was $49,871. The total costs for all elective repairs were $9,692,591. Screening, implementation, maintenance, and surgical repair cost involved in the management of patients with AAA disease was $13.7 million, with $10,686 per life-year lived after repair (5.8 ± 3.5 mean life-years) and $490 per life-year lived after screening (6.9 ± 3.5 mean life-years) for all patients screened. There were 13 deaths of unknown causes and one patient with a ruptured AAA that required emergency repair at a cost of $124,392.

CONCLUSIONS

Despite known limitations, the implementation of an AAA ultrasound screening program is feasible, cost-effective, and a worthwhile endeavor.

Screening for Abdominal Aortic Aneurysms and Risk Factors in 65-Year-Old Men in Oslo, Norway

Purpose

To investigate the prevalence of and risk factors for abdominal aortic aneurysm (AAA) in 65-year-old men in Oslo, Norway.

Materials and Methods

From May 2011, until September 2019, the annual population of 65-year-old men living in Oslo were invited to an ultrasonographic screening of the abdominal aorta. Candidates received a one-time invitation by mail, including a questionnaire on possible risk factors and comorbidities. Abdominal aortic outer-to-outer diameter and ankle-brachial index were measured by the screening team. Participants were allocated into three groups: non-, sub- and aneurysmal aorta. Written information on recommended follow-up regime was given to participants with an aortic diameter ≥25 mm. Univariate and multivariate analyses of potential risk factors were performed, in addition to descriptive analyses and significance testing.

Results

In total, 19,328 were invited, 13,215 men were screened, of which 12,822 accepted inclusion in the study. Aortic diameter was registered for 12,810 participants and 330 men had aortic diameter ≥30 mm, giving a prevalence of AAA of 2.6% (95% confidence interval (CI) 2.31-2.86). We identified 4 independent risk factors for AAA: smoking (OR = 3.64, 95% CI 2.90-4.58), hypertension (OR = 1.87, 95% CI 1.49-2.35), BMI >30 (OR = 1.02, 95% CI 1.00-1.03), and diabetes mellitus (OR = 0.52, 95% CI 0.35-0.79), the latter showing an inverse association with AAA growth. A subgroup of 862 men with aortic diameters 25-29 mm had a significantly higher prevalence of BMI >25, smoking and family history of AAA, compared to participants with aortic diameter <25 mm.

Conclusion

Among the participants in this study, the prevalence of abdominal aortic aneurysms was 2.6%. Participants with AAA more frequently reported cardiovascular risk factors, and less frequently diabetes mellitus.

The natural history of large abdominal aortic aneurysms in patients without timely repair

OBJECTIVE

Contemporary data on the natural history of large abdominal aortic aneurysms (AAAs) in patients undergoing delayed or no repair are lacking. In this study, we examine the impact of large AAA size on the incidence of rupture and mortality.

METHODS

From a prospectively maintained aneurysm surveillance registry, patients with an unrepaired, large AAA (≥5.5 cm in men and ≥5.0 cm in women) at baseline (ie, index imaging) or who progressed to a large size from 2003 to 2017 were included, with follow-up through March 2020. Outcomes of interest obtained by manual chart review included rupture (confirmed by imaging/autopsy), probable rupture (timing/findings consistent with rupture without more likely cause of death), repair, reasons for either no or delayed (>1 year after diagnosis of large AAA) repair and total mortality. Cumulative incidence of rupture was calculated using a nonparametric cumulative incidence function, accounting for the competing events of death and aneurysm repair and was stratified by patient sex.

RESULTS

Of the 3248 eligible patients (mean age, 83.6 ± 9.1 years; 71.2% male; 78.1% white; and 32.0% current smokers), 1423 (43.8%) had large AAAs at index imaging, and 1825 progressed to large AAAs during the follow-up period, with a mean time to qualifying size of 4.3 ± 3.4 years. In total, 2215 (68%) patients underwent repair, of which 332 were delayed >1 year; 1033 (32%) did not undergo repair. The most common reasons for delayed repair were discrepancy in AAA measurement between surgeon and radiologist (34%) and comorbidity (20%), whereas the most common reasons for no repair were patient preference (48%) and comorbidity (30%). Among patients with delayed repair (mean time to repair, 2.6 ± 1.8 years), nine (2.7%) developed symptomatic aneurysms, and an additional 11 (3.3%) ruptured. Of patients with no repair, 94 (9.1%) ruptured. The 3-year cumulative incidence of rupture was 3.4% for initial AAA size 5.0 to 5.4 cm (women only), 2.2% for 5.5 to 6.0 cm, 6.0% for 6.1 to 7.0 cm, and 18.4% for >7.0 cm. Women with AAA size 6.1 to 7.0 cm had a 3-year cumulative incidence of rupture of 12.8% (95% confidence interval, 7.5%-19.6%) compared with 4.5% (95% confidence interval, 3.0%-6.5%) in men (P = .002).

CONCLUSIONS

In this large cohort of AAA registry patients over 17 years, annual rupture rates for large AAAs were lower than previously reported, with possible increased risk in women. Further analyses are ongoing to identify those at increased risk for aneurysm rupture and may provide targeted surveillance regimens and improve patient counseling.

Screening Older Adult Men for Abdominal Aortic Aneurysm: A Scoping Review

Abdominal aortic aneurysm (AAA) is a potentially fatal condition predominantly affecting older adult men (60 years or over). Based on evidence, preventative health-care guidelines recommend screening older males for AAA using ultrasound. In attempts to reduce AAA mortality among men, screening has been utilized for early detection in some Western countries including the UK and Sweden. The current scoping review includes 19 empirical studies focusing on AAA screening in men. The findings from these studies highlight benefits and potential harms of male AAA screening. The benefits of AAA screening for men include decreased incidence of AAA rupture, decreased AAA mortality, increased effectiveness of elective AAA repair surgery, and cost-effectiveness. The potential harms of AAA screening included lack of AAA mortality reduction, negative impacts on quality of life, and inconsistent screening eligibility criteria being applied by primary care practitioners. The current scoping review findings are discussed to suggest changes to AAA screening guidelines and improve policy and practice.

Aneurysms and dissections - What is new in the literature of 2019/2020 - a European Society of Vascular Medicine annual review

More than 6,000 publications were found in PubMed concerning aneurysms and dissections, including those Epub ahead of print in 2019, printed in 2020. Among those publications 327 were selected and considered of particular interest.

Association Between the Atherosclerotic Disease Risk Score and Carotid Artery Stenosis

BACKGROUND

Carotid artery stenosis (CAS) is the most frequently detected treatable cause of ischemic stroke. However, there are no recommendations to screen asymptomatic patients. The atherosclerotic cardiovascular disease (ASCVD) risk score estimates individuals' 10-year risk for developing cardiovascular disease. The objective of this study is to identify a relationship between the ASCVD risk score and moderate/severe CAS based on ultrasound findings.

MATERIALS AND METHODS

We performed a single-institution retrospective review of patients who underwent a surveillance ultrasound for CAS between 2015 and 2018. We used Strandness velocity criteria to separate patients into two cohorts: none to mild CAS (<50%) and moderate/severe CAS (≥50%). We performed Student's t-test, multivariate analysis, and receiver operator characteristic (ROC) curve analysis to determine a relationship between the ASCVD risk score and degree of CAS. We evaluated a new risk score model based on stepwise logistic regression of significant variables on univariate analysis.

RESULTS

Two thousand eight hundred and fifty-six patients with carotid ultrasounds (1623 with none to mild, 1161 with moderate, and 72 with severe disease) were included in the study. The ASCVD risk score significantly predicted moderate/severe CAS in an adjusted multivariate analysis. Each 10% increase in the ASCVD risk score corresponded to an additional 11% likelihood of moderate/severe stenosis (OR: 1.11 [1.04-1.20], P = 0.004). The ROC area under the curve for predicting moderate/severe CAS based on the ASCVD risk score was 0.59 (Youden index (J) = 0.14); the optimized ASCVD cutoff point was 28.4%. Our new atherosclerotic disease model demonstrated increased odds of moderate/severe CAS with scores greater than zero (ROC area under the curve = 0.57).

CONCLUSIONS

This is the first study to demonstrate an association between atherosclerotic disease risk factors as measured by the ASCVD risk score and moderate/severe CAS. However, this tool is not sensitive or specific for using the ASCVD risk score as a screening mechanism for moderate/severe CAS.

Intraluminal Thrombus Predicts Rapid Growth of Abdominal Aortic Aneurysms

Background Intraluminal thrombus (ILT) within abdominal aortic aneurysms (AAAs) may be a potential marker for subsequent aneurysm growth. Purpose To investigate the role of ILT in AAA progression as assessed with CT and MRI. Materials and Methods This was a retrospective study, with patient data included from January 2004 to December 2018 at a Veteran Affairs medical center. Male patients with AAA who underwent contrast material-enhanced CT at baseline and CT or black-blood MRI at follow-up (minimal follow-up duration of 6 months) were included. The maximal AAA diameter was measured with multiplanar reconstruction, and the annual growth rate of aneurysms was calculated. Uni- and multivariable linear regression analyses were used to determine the relationship between demographic and imaging factors and aneurysm growth. Results A total of 225 patients (mean age, 72 years ± 9 [standard deviation]) were followed for a mean of 3.3 years ± 2.5. A total of 207 patients were followed up with CT, and 18 were followed up with MRI. At baseline, the median size of the AAA was 3.8 cm (interquartile range [IQR], 3.3-4.3 cm); 127 of 225 patients (54.7%) had ILT. When compared with AAAs without ILT, AAAs with ILT had larger baseline diameters (median, 4.1 cm [IQR, 3.6-4.8 cm] vs 3.4 cm [IQR, 3.2-3.9 cm]; P < .001) and faster growth rates (median, 2.0 mm/y [IQR, 1.3-3.2 mm/y] vs 1.0 mm/y [IQR, 0.4-1.8 mm/y]; P < .001). Small AAAs (size range, 3-4 cm) with ILT grew 1.9-fold faster than did those without ILT (median, 1.5 mm/y [IQR, 0.9-2.7 mm/y] vs 0.8 mm/y [IQR, 0.3-1.5 mm/y]; P < .001). Medium AAAs (size range, 4-5 cm) with ILT had 1.2-fold faster growth than did those without ILT (median growth, 2.1 mm/y [IQR, 1.4, 3.7 mm/y] vs 1.8 mm/y [IQR, 0.9, 2.0 mm/y]; P = .06). In multivariable analysis, baseline diameter and ILT were independently positively related to aneurysm growth rate (standardized regression coefficient, 0.43 [P < .001] and 0.15 [P = .02], respectively). Conclusion Both maximal cross-sectional aneurysm diameter and the presence of intraluminal thrombus are independent predictors of abdominal aortic aneurysm growth. © RSNA, 2020 Online supplemental material is available for this article.

Risk of developing an abdominal aortic aneurysm after ectatic aorta detection from initial screening

OBJECTIVE

Current abdominal aortic aneurysm (AAA) surveillance guidelines lack any follow-up recommendations after initial abdominal aortic screening diameter of less than 3.0 cm. Some reports have demonstrated patients with late AAA formation and late ruptures after initial ultrasound screening detection of patients with an aortic diameter of 2.5 to 2.9 cm (ectatic aorta). The purpose of this study was to determine ectatic aorta prevalence, AAA development, rupture risk, and risk factor profile in patients with detected ectatic aortas in a AAA screening program.

METHODS

A retrospective chart review of all patients screened for AAA from January 1, 2007, to December 31, 2016, within a regional health care system was conducted. Screening criteria were men 65 to 75 years of age that smoked a minimum of 100 cigarettes in their lifetime. An ectatic aorta was defined as a maximum aortic diameter from 2.5 to 2.9 cm. An AAA was defined as an aortic diameter of 3 cm or greater. Patients screened with ectatic aortas who had subsequent follow-up imaging of the aorta with a minimum of 1-year follow-up were analyzed for associated clinical and cardiovascular risk factors. All data were collected through December 3,/2018. A logistic regression of statistically significant variables from univariate and χ² analyses were performed to identify risks associated with the development of AAA from an initially diagnosed ectatic aorta. A Cox proportional hazard model was used to assess survival data. A P value of less than .05 was considered statistically significant.

RESULTS

From a screening pool of 19,649 patients, 3205 (16.3%) with a mean age of 72.1 ± 5.3 years were identified to have an ectatic aorta from January 1, 2007, to December 31, 2016. The average screening ectatic aortic diameter was 2.6 ± 0.1 cm. There were 672 patients (21.0%) with a mean age of 73.0 ± 5.7 years who received subsequent imaging for other clinical indications and 193 of these patients (28.7%) with ectatic aortas developed an AAA from the last follow-up scan (4.2 ± 2.5 years). The average observation length of all patients was 6.4 ± 2.9 years. No ruptures were reported, but 27.8% of deaths were of unknown cause. One patient had aortic growth to 5.5 cm or greater (0.15%). Larger initial screening diameter (P < .01), presence of chronic obstructive pulmonary disease (P < .01), and active smoking (P = .01) were associated with AAA development.

CONCLUSIONS

Patients with diagnosed ectatic aortas from screening who are active smokers or have chronic obstructive pulmonary disease are likely to develop an AAA.

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.