A texture-based 3D region growing approach for segmentation of ICA through the skull base in CTA

  • PDF / 4,947,284 Bytes
  • 26 Pages / 439.37 x 666.142 pts Page_size
  • 5 Downloads / 197 Views

DOWNLOAD

REPORT


A texture-based 3D region growing approach for segmentation of ICA through the skull base in CTA Ferhat Bozkurt 1

2

& Cemal Köse & Ahmet Sarı

3

Received: 6 November 2019 / Revised: 12 July 2020 / Accepted: 21 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020

Abstract

The internal carotid artery (ICA) segmentation is a complicated task at skull base in computed tomography angiography (CTA) images. The ICA enters into from skull cavity and shows close proximity to bone and surrounding soft tissues. For this reason, there exists a robust intensity overlap between vessels, bone and other surrounding tissues. Thus, these similar objects are not separated properly in images only according to the intensity level. In this paper, a texture-based 3D region growing approach is proposed and applied to the ICA through the skull base. The main contribution of this study is that the method does not ask for an extra computed tomography scan for bone masking. Moreover, the method dynamically sets the segmentation parameters according to texture knowledge. The proposed method was evaluated by the experiments on 15 actual clinical data. The performance evaluations were performed by comparing the automatic outputs with manual segmentations which are done by two radiologist observers. As a result, dice similarity rate of 89% was achieved together with 99% accuracy and 0.32 mm mean surface distance (Msd) for ICA segmentation through the skull base. The results show that the average overlap for the observers are similar. The proposed texture-based approach decreases significantly explosions, over-segmentations and increases rate of area overlap, sensitivity, precision at skull base. Therefore, the method is clinically useful and has potential to segment carotid arteries at skull base efficiently. Keywords 3Dvessel segmentation . Carotidartery segmentation . Texture-based region growing . Skull base . Computed tomography angiography

* Ferhat Bozkurt [email protected] Cemal Köse [email protected] Ahmet Sarı [email protected] Extended author information available on the last page of the article

Multimedia Tools and Applications

1 Introduction Medical imaging has been becoming most popular tool for last decade years [3, 60]. The 3D representation of body from 2D X-ray images has significantly facilitated the detection of diseases [22]. At the present time, the vascular diseases are the most cause of death in the world as stroke or heart attack [45]. Both of them occur very suddenly and it can be difficult to predict. Angiography makes it possible to observe vessels without the need for any surgical operation. CTA is minimally invasive medical test for radiologists to utilize the diagnosis of related diseases over the last years [69]. The body can be scanned by CT scanner, and then can be viewed in 3D for disease diagnosis. The displaying of the body tissues differs with their intensities because of their density variations. The blood vessels cannot be distinguished from surrounding tissue. So, the