Segmentation of arterial walls in intravascular ultrasound cross-sectional images using extremal region selection

Abstract

Intravascular Ultrasound (IVUS) is an intra-operative imaging modality that facilitates observing and appraising the vessel wall structure of the human coronary arteries. Segmentation of arterial wall boundaries from the IVUS images is not only crucial for quantitative analysis of the vessel walls and plaque characteristics, but is also necessary for generating 3D reconstructed models of the artery. The aim of this study is twofold. Firstly, we investigate the feasibility of using a recently proposed region detector, namely Extremal Region of Extremum Level (EREL) to delineate the luminal and media-adventitia borders in IVUS frames acquired by 20 MHz probes. Secondly, we propose a region selection strategy to label two ERELs as lumen and media based on the stability of their textural information. We extensively evaluated our selection strategy on the test set of a standard publicly available dataset containing 326 IVUS B-mode images. We showed that in the best case, the average Hausdorff Distances (HD) between the extracted ERELs and the actual lumen and media were 0.22 mm and 0.45 mm, respectively. The results of our experiments revealed that our selection strategy was able to segment the lumen with ⩽0.3 mm HD to the gold standard even though the images contained major artifacts such as bifurcations, shadows, and side branches. Moreover, when there was no artifact, our proposed method was able to delineate media-adventitia boundaries with 0.31 mm HD to the gold standard. Furthermore, our proposed segmentation method runs in time that is linear in the number of pixels in each frame. Based on the results of this work, by using a 20 MHz IVUS probe with controlled pullback, not only can we now analyze the internal structure of human arteries more accurately, but also segment each frame during the pullback procedure because of the low run time of our proposed segmentation method.

IVUS-Net: An Intravascular Ultrasound Segmentation Network

“…The evaluation is based on a publicly available IVUS Bmode dataset [3], which has been widely used in the IVUS segmentation literature [8,6,17,30,26]. There are 109 images in the training set, 326 images in the test set and no official validation set is provided.…”

“…The Hausdorff Distance between the automatic (C pred ) and manual (C true ) curves is the "greatest distance of all points belonging to C pred to the closest point" [8] in C true and is defined as follows:…”

“…The segmentation of IVUS images has been a well-investigated problem from a conventional perspective where numerous ideas and approaches of computer vision and image processing such as in [17,18,25,30,26] have been employed. One of the best segmentation results have been achieved in a very recent work [8] where authors proposed a twofold IVUS segmentation pipeline based on traditional computer vision methods [10,9]. Although no learning method was used, it outperforms existing methods from both the accuracy and efficiency perspective.…”

EREL Selection Using Morphological Relation

“…Another state-of-the-art method is known as Extremal Regions of Extremum Level (EREL) [6,5], a region detector that is capable of extracting repeatable regions from an image. This work is a derivation of [4] in the context of Intravascular Ultrasound (IVUS) image segmentation in which the EREL detector is applied to each IVUS frame and extracts several regions. Each EREL is fitted by a closest ellipsoid since the intrinsic shape of coronary artery is similar to a conic section [4].…”

“…This work is a derivation of [4] in the context of Intravascular Ultrasound (IVUS) image segmentation in which the EREL detector is applied to each IVUS frame and extracts several regions. Each EREL is fitted by a closest ellipsoid since the intrinsic shape of coronary artery is similar to a conic section [4]. Among these fitted ellipsoids, we expect one of them to have the smallest Hausdorff Distance (HD) [1] to the ground truth luminal border labeled by clinical experts and the goal is to find and represent this ellipse as a segmentation of the luminal region.…”