Automatic Segmentation of Abdominal Aortic Aneurysms From Time-Resolved 3-D Ultrasound Images Using Deep Learning

Abdominal aortic aneurysms (AAAs) are rupture-prone dilatations of the aorta. In current clinical practice, the maximal diameter of AAAs is monitored with 2-D ultrasound to estimate their rupture risk. Recent studies have shown that 3-D and mechanical AAA parameters might be better predictors for aneurysm growth and rupture than the diameter. These parameters can be obtained with time-resolved 3-D ultrasound (3-D + t US), which requires robust and automatic segmentation of AAAs from 3-D + t US. This study proposes and validates a deep learning (DL) approach for the automatic segmentation of AAAs. A group of 500 patients was included for follow-up 3-D + t US imaging, resulting in 2495 3-D + t US images. Segmentation masks for model training were obtained using a conventional automatic segmentation algorithm (nonDL). Four different DL models were trained and validated by 1) comparison to CT and 2) reader scoring. Performance of the nonDL and different DL segmentation strategies were evaluated by comparing Hausdorff distance, Dice scores, accuracy, sensitivity, and specificity with a sign test. All DL models had higher median Dice scores, accuracy, and sensitivity (all ${p} \lt 0.003$ ) compared to nonDL segmentation. The full image-resolution model without data augmentation showed the highest median Dice score and sensitivity ( ${p} \lt 0.001$ ). Applying the DL model on an independent test group produced fewer poor segmentation scores of 1 to 2 on a five-point scale (8% for DL, 18% for nonDL). This demonstrates that a robust and automatic segmentation algorithm for segmenting AAAs from 3-D + t US images was developed, showing improved performance compared to conventional segmentation.