Robust Segmentation of the Full Cerebral Vasculature in 4D CT of Suspected Stroke Patients

Midas Meijs,Rashindra Manniesing,Sil C Van De Leemput,Ewoud J Van Dijk,Mathias Prokop,Bram Van Ginneken,Frank-Erik De Leeuw,Frederick J A Meijer,Ajay Patel

doi:10.1038/s41598-017-15617-w

Midas Meijs, Rashindra Manniesing + Show 7 more

Open Access

https://doi.org/10.1038/s41598-017-15617-w

Copy DOI

Abstract

A robust method is presented for the segmentation of the full cerebral vasculature in 4-dimensional (4D) computed tomography (CT). The method consists of candidate vessel selection, feature extraction, random forest classification and postprocessing. Image features include among others the weighted temporal variance image and parameters, including entropy, of an intensity histogram in a local region at different scales. These histogram parameters revealed to be a strong feature in the detection of vessels regardless of shape and size. The method was trained and tested on a large database of 264 patients with suspicion of acute ischemia who underwent 4D CT in our hospital in the period January 2014 to December 2015. Five subvolumes representing different regions of the cerebral vasculature were annotated in each image in the training set by medical assistants. The evaluation was done on 242 patients. A total of 16 (<8%) patients showed severe under or over segmentation and were reported as failures. One out of five subvolumes was randomly annotated in 159 patients and was used for quantitative evaluation. Quantitative evaluation showed a Dice coefficient of 0.91 ± 0.07 and a modified Hausdorff distance of 0.23 ± 0.22 mm. Therefore, robust vessel segmentation in 4D CT is feasible with good accuracy.

Highlights

The task of vessel segmentation has led to a vast amount of literature in the past decades[2,3]
The method scored higher, this difference is only significant in observer 1
In this work we have presented a method for full cerebral vessel segmentation in 4D computed tomography (CT) using a pattern recognition framework with minimal pre- and postprocessing

Summary

Introduction

The task of vessel segmentation has led to a vast amount of literature in the past decades[2,3]. Tracking based approaches will have difficulty achieving the desired level of robustness on full brain vessel segmentation These methods require some form of initialization, as intensity values vary along the vessel. Nonnatural variations caused by pathology, such as vessel occlusions and arteriovenous malformations, or imaging artifacts, resulting from the presence of clips or stents, have a major influence on the continuity of the intensity along the vessels (Fig. 2). This may even pose a challenge for tracking based methods with adaptive properties

Methods

Results

Conclusion