Automatic segmentation of Pulmonary Artery (PA) in 3D pulmonary CTA images

Abstract

This paper proposes an efficient algorithm for segmenting the Pulmonary Artery (PA) tree in 3D pulmonary Computed Tomography Angiography (CTA) images. In this algorithm, to reduce the search area the lung regions from the original image are first segmented and the heart region is extracted by selecting the regions between the lungs. A pre-processing algorithm based on Hessian matrix and its eigenvalues is used to remove the connectivity between the pulmonary artery and other nearby pulmonary organs. To extract the pulmonary artery tree, we first use a region growing method initialized by a seed point which is automatically selected within the pulmonary artery trunk in the heart region. In the second step, the segmentation of the pulmonary artery is performed using a 3D level set algorithm, using the output of region grower as the initial contour. We use a new stopping criterion for the used level set algorithm, a consideration often neglected in many level set implementations. To validate and assess the robustness of the method, 20 CT angiography datasets were used (10 free pulmonary embolism scans and 10 CT with pulmonary emboli). A very good agreement with the visual judgment was obtained in both normal and positive pulmonary emboli CT scans.

Considerations for Numerical Modeling of the Pulmonary Circulation—A Review With a Focus on Pulmonary Hypertension

“…This can be overcome with additional processing steps to separate the right and left hemilungs, followed by either automatic or semiautomatic snake-based separation of pulmonary lesions attached to the chest wall, as demonstrated with tumorladen lungs by O'Dell [64]. Many existing partially or fully automated methods can rapidly reconstruct the vascular tree to a large number of generations [65][66][67][68][69], but most are susceptible to discontinuity artifacts present in the volumetric scans and are unable to reveal both distal and proximal vasculature (see Fig. 3).…”

“…The Burrowes et al technique can be solved as a reconstructed patient-specific 3D domain. Nevertheless, it should be noted that this technique is not fully automatic, but if incorporated with other segmentation strategies such as those referenced above [65][66][67][68][69], it holds promise for rapid patient-specific pulmonary vasculature regeneration.…”

3D Pulmonary Artery Segmentation from CTA Scans Using Deep Learning with Realistic Data Augmentation

“…Regarding the segmentation of the PA outside the lung, which is our goal, only a few studies have been proposed. In [2] a Hessian matrix based preprocessing followed by a region growing method is proposed, which relies on a previous extraction of the lungs and the heart. The method in [14] also requires a priori knowledge of the artery morphology followed by a fast-marching algorithm and a registration to a target reference volume, which did not fully address the variability in PA sizes and shapes.…”

Pulmonary arteries segmentation from CT images using PA‐Net with attention module and contour loss

“…proposed a pulmonary artery segmentation and arterial tree slice tracking algorithm based on region growth and slice marching (RGSM) to segment the pulmonary artery. Ebrahimdoost et al 21 . first extracted the heart region and used the 3D level set algorithm to segment the pulmonary artery.…”

“…However, few studies on pulmonary artery segmentation in CT images. [19][20][21][22][23][24] Linguraru et al 19 proposed a semiautomatic tool for analyzing lung CTA, using level sets and geodesic active contours to segment pulmonary arteries. Zhang et al 20 proposed a pulmonary artery segmentation and arterial tree slice tracking algorithm based on region growth and slice marching (RGSM) to segment the pulmonary artery.…”