Multi-Task Deep Convolutional Neural Network for the Segmentation of Type B Aortic Dissection

TL;DR

This paper presents a fully automated 3-D multi-task deep learning model that accurately segments the entire aorta and true-false lumen in CTA images, aiding diagnosis and treatment planning for type B aortic dissection.

Contribution

It introduces a novel multi-task deep convolutional neural network that simultaneously segments the entire aorta and lumens from CTA images, outperforming existing methods.

Findings

Achieved a mean DSC of 0.910 for the entire aorta.

Achieved a mean DSC of 0.849 for the true lumen.

Achieved a mean DSC of 0.821 for the false lumen.

Abstract

Segmentation of the entire aorta and true-false lumen is crucial to inform plan and follow-up for endovascular repair of the rare yet life threatening type B aortic dissection. Manual segmentation by slice is time-consuming and requires expertise, while current computer-aided methods focus on the segmentation of the entire aorta, are unable to concurrently segment true-false lumen, and some require human interaction. We here report a fully automated approach based on a 3-D multi-task deep convolutional neural network that segments the entire aorta and true-false lumen from CTA images in a unified framework. For training, we built a database containing 254 CTA images (210 preoperative and 44 postoperative) obtained using various systems from 254 unique patients with type B aortic dissection. Slice-wise manual segmentation of the entire aorta and the true-false lumen for each 3-D CTA image was provided. Upon evaluation of another 16 CTA images (11 preoperative and 5 postoperative) with ground truth segmentation provided by experienced vascular surgeons, our method achieves a mean dice similarity score(DSC) of 0.910,0.849 and 0.821 for the entire aorta,true lumen and false lumen respectively.