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

HIGHLIGHTSA DCNN‐based fully automatic thrombus detection and segmentation pipeline that is easily translatable to clinical practice is proposed.A new DCNN architecture adapted to post‐operative thrombus segmentation from CTA images is presented, which combines low level features with coarser representations.The well‐known Detectnet computer vision network is translated into the clinical domain, specifically for thrombus region of interest detection in CTA images.Automatic segmentation exceeds previous state of the art results, with a mean Dice similarity coefficient of 82%.In terms of clinical applicability, the obtained segmentation results lay within the experienced human observer variance without the need of human intervention in most common cases. 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.