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

Abstract

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.

Keywords: abdominal aortic aneurysm; deep learning; endovascular repair (EVAR); morphologic features; multimodal; radiomics.

FIGURE 1

Preoperative CTA reconstruction (A); AAA sac ROI (B); ILT ROI (C); AAA ROI (D); AAA original ROI CTA slice (F) was the combination between AAA ROI CTA slicer (G) and original ROI CTA slice (E); CTA slicer (I) was the combination between AAA sac ROI CTA slicer (G) and ILT ROI CTA slicer (H). CTA, computed tomography angiography; AAA, abdominal aortic aneurysm; ROI, region of interest; ILT, intraluminal thrombosis.

FIGURE 2

The AUC of CAI and SAEs after EVAR. The red dotted circle represents the optimal cutoff point. AUC, area under the curve; CAI, common iliac artery index; SAEs, severe adverse events.

FIGURE 3

The AUC of the optimized morphological feature model for predicting EVAR-related SAEs in the training set. AUC, area under the curve; SAEs, severe adverse events; EVAR, endovascular aneurysm repair.

FIGURE 4

The AUC of the multimodal models for predicting EVAR-related SAEs in the test set. AUC, area under the curve; SAEs, severe adverse events; EVAR, endovascular aneurysm repair. (A) AdaBoost ROC curve with test dataset. (B) Fold 3 ROC curve with test dataset. (C) LogisticRegression ROC curve with test dataset.

FIGURE 5

The AUC of the DL model for predicting EVAR-related SAEs in the training set. AUC, area under the curve; DL, deep learning; SAEs, severe adverse events; EVAR, endovascular aneurysm repair.

FIGURE 6

Significant radiomic features and feature coefficients.

FIGURE 7

The AUC of the radiomic model for predicting EVAR-related SAEs in the training set. AUC, area under the curve; SAEs, severe adverse events; EVAR, endovascular aneurysm repair.