Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using deep convolutional neural networks

TL;DR

This paper introduces a fully automatic deep learning-based method for detecting and segmenting abdominal aortic thrombus in post-operative CTA images, achieving high accuracy and reproducibility without human intervention.

Contribution

The study presents a novel deep convolutional neural network architecture for automatic thrombus detection and segmentation in CTA images, improving robustness and reproducibility over existing methods.

Findings

Achieved Dice score > 82% for thrombus segmentation

Automatic volume measurements within human observer variance

Validated robustness with 4-fold cross-validation

Abstract

Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases.