The effect of Endovascular Aneurysm Repair on Renal Function in Patients Treated for Abdominal Aortic Aneurysm

A radiomics model for predicting the outcome of endovascular abdominal aortic aneurysm repair based on machine learning

OBJECTIVE

This study aimed to develop a radiomics model to predict the outcome of endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA), based on machine learning (ML) algorithms.

METHODS

We retrospectively reviewed 711 patients with infra-renal AAA who underwent elective EVAR procedures between January 2016 and December 2019 at our single center. The radiomics features of AAA were extracted using Pyradiomics. Pearson correlation analysis, analysis of variance (ANOVA), least absolute shrinkage, and selection operator (LASSO) regression were applied to determine the predictors for EVAR-related severe adverse events (SAEs). Eighty percent of patients were classified as the training set and the remaining 20 percent of patients were classified as the test set. The selected features were used to build a radiomics model in training set using different ML algorithms. The performance of each model was assessed using the area under the curve (AUC) from the receiver operating characteristic (ROC) curve in the test set.

RESULTS

A total of 493 patients were enrolled in this study, the mean follow-up time was 32 months. During the follow-up, 156 (31.6%) patients experienced EVAR-related SAEs. A total of 1223 radiomics features were extracted from each patient, of which 30 radiomics features were finally identified. The quantitative performance assessment and the ROC curves indicated that the logistics regression (LR) model had better predictive value than others, with accuracy, 0.86; AUC, 0.93; and F1 score, 0.91. The Rad-score waterfall plot showed that the overall amount of error was small both in the training set and in the test set. Calibration curve showed that the calibration degree of the training set and the test set were good (p > 0.05). Decision curve analysis (threshold 0.32) demonstrated that the model had good clinical applicability.

CONCLUSION

Our radiomics model could be used as an efficient and adjunctive tool to predict the outcome after EVAR.

Intravascular Ultrasound Versus Computed Tomography Angiography in Sizing and Operative Management of Endovascular Aortic Aneurysm Repair

OBJECTIVES

An abdominal aortic aneurysm (AAA) is a potentially life-threatening condition, the management of which has dramatically evolved over the past 2 decades with an increasing tendency toward endovascular repair (EVAR) rather than open surgical repair. Classically, contrast-enhanced multislice computed tomography (CT) angiography (CTA) is performed preoperatively for procedure sizing and EVAR planning. This entails voluminous contrast injection with risk of allergic reaction, nephropathy, and radiation exposure. Intra-vascular ultrasound (IVUS) has been increasingly used to guide EVAR procedures intraoperatively. The aim of this study is to investigate the accuracy of IVUS in sizing AAAs, device selection, and EVAR planning compared to the gold standard CTA.

DESIGN

This is a prospective observational study enrolling 10 patients who underwent standard infrarenal EVAR procedures performed for unruptured infrarenal AAAs over the course of 1 year. All patients had a preoperative CTA done upon which aneurysm sizing and device planning were performed, and the measurements obtained were compared to those obtained from intraoperative IVUS.

METHODS

All participating patients had unruptured infrarenal AAA, had no renal impairment, and had anatomical suitability for EVAR according to the instructions for use (IFU) of the device manufacturer. Primary endpoint was comparing anatomical measurements recorded by IVUS with those obtained from the preoperative CTA.

RESULTS

Mean age was 65.6 (±6.19), all patients were males and hypertensives and 4 (40%) had a positive family history for AAA. On comparing mean measurements taken by CTA and IVUS, there was no statistically significant differences with exception of maximal aortic diameter and aortic diameter at site of bifurcation (both p-values <.001). There were no statistically significant differences in length measurements between the 2 imaging modalities. Computed tomography angiography was more associated with neck thrombus detection, and IVUS was more associated with calcification detection.

CONCLUSION

Although CT angiography is still the gold standard imaging modality for AAA, IVUS use is very beneficial in EVAR sizing and planning, in addition to intra-operative guidance of the procedure, saving the patient significant time, contrast administration, and radiation exposure, especially in patients with renal impairment and contrast allergy.

CLINICAL IMPACT

A preoperative CT angiogram is the gold standard required investigation for planning and sizing EVARs, with subsequent contrast injection entailing a risk of contrast induced nephropathy and allergic reactions. IVUS has been used as an adjuvant technique to guide EVAR stent graft deployment. However, our study concluded that it can also be reliably used in sizing and planning of the EVAR stent graft along with complementary non contrast imaging, especially in patients with high risk for contrast induced nephropathy and contrast allergy.

Development and Comparison of Multimodal Models for Preoperative Prediction of Outcomes After Endovascular Aneurysm Repair

Objective

The aim of this study was to develop and compare multimodal models for predicting outcomes after endovascular abdominal aortic aneurysm repair (EVAR) based on morphological, deep learning (DL), and radiomic features.

Methods

We retrospectively reviewed 979 patients (January 2010—December 2019) with infrarenal abdominal aortic aneurysms (AAAs) who underwent elective EVAR procedures. A total of 486 patients (January 2010–December 2015) were used for morphological feature model development and optimization. Univariable and multivariable analyses were conducted to determine significant morphological features of EVAR-related severe adverse events (SAEs) and to build a morphological feature model based on different machine learning algorithms. Subsequently, to develop the morphological feature model more easily and better compare with other modal models, 340 patients of AAA with intraluminal thrombosis (ILT) were used for automatic segmentation of ILT based on deep convolutional neural networks (DCNNs). Notably, 493 patients (January 2016–December 2019) were used for the development and comparison of multimodal models (optimized morphological feature, DL, and radiomic models). Of note, 80% of patients were classified as the training set and 20% of patients were classified as the test set. The area under the curve (AUC) was used to evaluate the predictive abilities of different modal models.

Results

The mean age of the patients was 69.9 years, the mean follow-up was 54 months, and 307 (31.4%) patients experienced SAEs. Statistical analysis revealed that short neck, angulated neck, conical neck, ILT, ILT percentage ≥51.6%, luminal calcification, double iliac sign, and common iliac artery index ≥1.255 were associated with SAEs. The morphological feature model based on the support vector machine had a better predictive performance with an AUC of 0.76, an accuracy of 0.76, and an F1 score of 0.82. Our DCNN model achieved a mean intersection over union score of more than 90.78% for the segmentation of ILT and AAA aortic lumen. The multimodal model result showed that the radiomic model based on logistics regression had better predictive performance (AUC 0.93, accuracy 0.86, and F1 score 0.91) than the optimized morphological feature model (AUC 0.62, accuracy 0.69, and F1 score 0.81) and the DL model (AUC 0.82, accuracy 0.85, and F1 score 0.89).

Conclusion

The radiomic model has better predictive performance for patient status after EVAR. The morphological feature model and DL model have their own advantages and could also be used to predict outcomes after EVAR.

Clinical effect of accessory renal artery coverage after endovascular repair of aneurysms in abdominal and thoracoabdominal aorta

BACKGROUND

The aim of our systematic review and meta-analysis was to assess the effect of accessory renal artery (ARA) coverage on renal function in terms of acute kidney injury (AKI), renal infarction, chronic renal failure (CRF), and mortality in patients undergoing standard endovascular aortic aneurysm repair (EVAR) or endovascular repair of complex aneurysms.

METHODS

An electronic search of the English language medical literature from 2000 to September 2020 was conducted using the MEDLINE, EMBASE, and Cochrane databases with the PRISMA (preferred reporting items for systematic reviews and meta-analyses) method for studies reporting on ARA management in patients undergoing endovascular repair of aneurysms in the abdominal and thoracoabdominal aorta. The patients were divided into two groups: group 1, patients with ARA coverage; and group 2, patients without an ARA or without coverage of the ARA. Each group included two arms, one of patients who had undergone standard EVAR and one of patients who had undergone endovascular treatment of a complex aortic aneurysm. The GRADE (grading of recommendations assessment, development, evaluation) approach was used to evaluate the quality of evidence and summary of the findings. The primary outcomes included the incidence of AKI, renal infarction, CRF, and mortality.

RESULTS

Ten retrospective, nonrandomized, control studies were included in the systematic review reporting on 1014 patients (302 with a covered ARA vs 712 without an ARA or without ARA coverage). In six studies, the mean diameter of the covered ARA was <4 mm (range, 2.7-3.4 mm). The mean follow-up was 22.74 months (range, 1-42 months). In the standard EVAR subgroup, the risk of AKI (odds ratio [OR], 0.72; 95% confidence interval [CI], 0.21-2.51; I² = 0%] in the early period, and CRF (OR, 4.44; 95% CI, 0.46-42.61; I² = 87%) and death (OR, 0.91; 95% CI, 0.36-2.31; I² = 0%) during follow-up were similar between groups 1 and 2. Only the risk of renal infarction was greater in group 1 than in group 2 (OR, 93.3; 95% CI, 1.48-5869; I² = 92%). In the complex aneurysm repair subgroup, the risk of AKI (OR, 1.85; 95% CI, 0.61-5.64; I² = 42%) in early period and CRF (OR, 1.64; 95% CI, 0.88-3.07; I² = not applicable) and death (OR, 3.63; 95% CI, 0.14-96.29; I² = 56%) during follow-up were similar between groups 1 and 2. Only the risk of renal infarction was greater for group 1 compared with group 2 (OR, 8.58; 95% CI, 4.59-16.04; I² = 0%).

CONCLUSIONS

ARA (<4 mm) coverage in patients undergoing standard EVAR or endovascular repair of complex aneurysms is associated with an increased risk of renal infarction. However, we found no clinical effects of ARA coverage on renal function or mortality in early postoperative and follow-up period. Preservation of an ARA >4 mm should be considered.