Volume Measurements for Surveillance after Endovascular Aneurysm Repair using Artificial Intelligence.

OBJECTIVE: Surveillance after endovascular aneurysm repair (EVAR) is suboptimal due to limited compliance and relatively large variability in measurement methods of abdominal aortic aneurysm (AAA) sac size after treatment. Measuring volume offers a more sensitive early indicator of aneurysm sac growth or regression/stability, but is more time consuming and thus less practical than measuring maximum diameter. This study evaluated the accuracy and consistency of the artificial intelligence (AI) driven software PRAEVAorta 2 and compared it with an established semi-automated segmentation method. METHODS: Post-EVAR aneurysm sac volumes measured by AI were compared with a semi-automated segmentation method (3mensio software) in patients with infrarenal AAA, focusing on absolute aneurysm volume and volume evolution over time. The clinical impact of both methods was evaluated by categorising patients as showing either AAA sac regression, stabilisation, or growth comparing the 30 day and one year post-EVAR computed tomography angiography (CTA) images. Intermethod and intramethod agreement were assessed using Bland-Altman analysis, the intraclass correlation coefficient (ICC) and Cohen's κ statistic. RESULTS: Forty nine patients (98 CTA images) were analysed, after excluding 15 patients due to segmentation errors by AI owing to low quality CT scans. Aneurysm sac volume measurements showed excellent correlation (ICC = 0.94, 95% confidence interval [CI] 0.88 - 0.99) with good to excellent correlation for volume evolution over time (ICC = 0.85, 95% CI 0.75 - 0.91). Categorisation of AAA sac evolution showed fair correlation (Cohen's κ = 0.33), with 12 discrepancies (24%) between methods. The intramethod agreement for the AI software demonstrated perfect consistency (bias = -0.01 cc), indicating that it is more reliable compared with the semi-automated method. CONCLUSION: Despite some differences in AAA sac volume measurements, the highly consistent AI driven software accurately measured AAA sac volume evolution. AAA sac evolution classification appears to be more reliable than existing methods and may therefore improve risk stratification post-EVAR. It could facilitate AI driven personalised surveillance programmes. While high quality CTA images are crucial, considering radiation exposure is important, validating the software with non-contrast CT scans might reduce the radiation burden.

Targeted proteomics and metabolomics for biomarker discovery in abdominal aortic aneurysm and post-EVAR sac volume.

BACKGROUND AND AIMS: Abdominal aortic aneurysm (AAA) patients undergo uniform surveillance programs both leading up to, and following surgery. Circulating biomarkers could play a pivotal role in individualizing surveillance. We applied a multi-omics approach to identify relevant biomarkers and gain pathophysiological insights. MATERIALS AND METHODS: In this cross-sectional study, 108 AAA patients and 200 post-endovascular aneurysm repair (post-EVAR) patients were separately investigated. We performed partial least squares regression and ingenuity pathway analysis on circulating concentrations of 96 proteins (92 Olink Cardiovascular-III panel, 4 ELISA-assays) and 199 metabolites (measured by LC-TQMS), and their associations with CT-based AAA/sac volume. RESULTS: The median (25th-75th percentile) maximal diameter was 50.0 mm (46.0, 53.0) in the AAA group, and 55.4 mm (45.0, 64.2) in the post-EVAR group. Correcting for clinical characteristics in AAA patients, the aneurysm volume Z-score differed 0.068 (95 %CI: (0.042, 0.093)), 0.066 (0.047, 0.085) and -0.051 (-0.064, -0.038) per Z-score valine, leucine and uPA, respectively. After correcting for clinical characteristics and orthogonalization in the post-EVAR group, the sac volume Z-score differed 0.049 (0.034, 0.063) per Z-score TIMP-4, -0.050 (-0.064, -0.037) per Z-score LDL-receptor, -0.051 (-0.062, -0.040) per Z-score 1-OG/2-OG and -0.056 (-0.066, -0.045) per Z-score 1-LG/2-LG. CONCLUSIONS: The branched-chain amino acids and uPA were related to AAA volume. For post-EVAR patients, LDL-receptor, monoacylglycerols and TIMP-4 are potential biomarkers for sac volume. Additionally, distinct markers for sac change were identified.

Circulating biomarkers of cardiovascular disease are related to aneurysm volume in abdominal aortic aneurysm.

BACKGROUND: Surveillance programs in abdominal aortic aneurysms (AAA) are mainly based on imaging and leave room for improvement to timely identify patients at risk for AAA growth. Many biomarkers are dysregulated in patients with AAA, which fuels interest in biomarkers as indicators of disease progression. We examined associations of 92 cardiovascular disease (CVD)-related circulating biomarkers with AAA and sac volume. METHODS: In a cross-sectional analysis, we separately investigated (1) 110 watchful waiting (WW) patients (undergoing periodic surveillance imaging without planned intervention) and (2) 203 patients after endovascular aneurysm repair (EVAR). The Cardiovascular Panel III (Olink Proteomics AB, Sweden) was used to measure 92 CVD-related circulating biomarkers. We used cluster analyses to investigate protein-based subphenotypes, and linear regression to examine associations of biomarkers with AAA and sac volume on CT scans. RESULTS: Cluster analyses revealed two biomarker-based subgroups in both WW and EVAR patients, with higher levels of 76 and 74 proteins, respectively, in one subgroup versus the other. In WW patients, uPA showed a borderline significant association with AAA volume. Adjusting for clinical characteristics, there was a difference of -0.092 (-0.148, -0.036) loge mL in AAA volume per SD uPA. In EVAR patients, after multivariable adjustment, four biomarkers remained significantly associated with sac volume. The mean effects on sac volume per SD difference were: LDLR: -0.128 (-0.212, -0.044), TFPI: 0.139 (0.049, 0.229), TIMP4: 0.110 (0.023, 0.197), IGFBP-2: 0.103 (0.012, 0.194). CONCLUSION: LDLR, TFPI, TIMP4, and IGFBP-2 were independently associated with sac volume after EVAR. Subgroups of patients with high levels of the majority of CVD-related biomarkers emphasize the intertwined relationship between AAA and CVD.ClinicalTrials.gov Identifier: NCT03703947.

Prevalence and clinical correlates of ascending aortic dilatation in patients with noncompaction cardiomyopathy.

Ascending aortic (AoAsc) dilatation can lead to acute aortic syndromes and has been described in various familial cardiac diseases. Its prevalence and clinical significance in patients with noncompaction cardiomyopathy (NCCM) are however unknown. Establishing the prevalence can facilitate recommendations on routine screening in NCCM. In this cross-sectional cohort study based on the Rijnmond Heart Failure/Cardiomyopathy Registry, the patient were enrolment between 2014 and 2021. All NCCM patients (n = 109) were age and sex matched with 109 dilated cardiomyopathy (DCM) patients as controls. The aortic diameters were measured through the parasternal long-axis transthoracic echocardiographic view at the sinuses of valsalva (SoV-Ao), sinotubular junction (STJ) and ascending aorta (AscAo). Dilatation was defined using published criteria adjusted for body surface area (BSA), sex, and age. Median age of age-sex matched NCCM and DCM patients was 45[31-56] vs. 45 [31-55] years with 53% males in both groups. NCCM patients had more familial hereditary patterns and genetic variants (55% vs. 24%, p < 0.001). DCM patients had more heart failure and left ventricular dysfunction (ejection fraction 34 ± 11 vs. 41 ± 12, p = 0.001). Ascending aortic dilatation was present in 8(7%) patients with NCCM and 5(5%) patients with DCM (p = 0.46). All dilatations were classified as mild. In conclusion, in this cross-sectional cohort study the prevalence of ascending aortic dilatation in NCCM patients was 7%, which were only mild dilatations and not significantly different from an age-sex matched cohort of DCM patients. Routine aortic dilatation screening therefore does not seem warranted in patients with NCCM.