RESUMO
OBJECTIVES: To develop and validate a deep learning model for detecting post-endovascular aortic repair (EVAR) endoleak from non-contrast CT. METHODS: This retrospective study involved 245 patients who underwent EVAR between September 2016 and December 2022. All patients underwent both non-enhanced and enhanced follow-up CT. The presence of endoleak was evaluated based on computed tomography angiography (CTA) and radiology reports. First, the aneurysm sac was segmented, and radiomic features were extracted on non-contrast CT. Statistical analysis was conducted to investigate differences in shape and density characteristics between aneurysm sacs with and without endoleak. Subsequently, a deep learning model was trained to generate predicted segmentation of the endoleak. A binary decision was made based on whether the model produced a segmentation to detect the presence of endoleak. The absence of a predicted segmentation indicated no endoleak, while the presence of a predicted segmentation indicated endoleak. Finally, the performance of the model was evaluated by comparing the predicted segmentation with the reference segmentation obtained from CTA. Model performance was assessed using metrics such as dice similarity coefficient, sensitivity, specificity, and the area under the curve (AUC). RESULTS: This study finally included 85 patients with endoleak and 82 patients without endoleak. Compared to patients without endoleak, patients with endoleak had higher CT values and greater dispersion. The AUC in validation group was 0.951, dice similarity coefficient was 0.814, sensitivity was 0.877, and specificity was 0.884. CONCLUSION: This deep learning model based on non-contrast CT can detect endoleak after EVAR with high sensitivity.
