Research Article: Automatic segmentation of optical coherence tomography pullbacks of coronary arteries treated with bioresorbable vascular scaffolds: Application to hemodynamics modeling

Date Published: March 14, 2019

Publisher: Public Library of Science

Author(s): Marco Bologna, Susanna Migliori, Eros Montin, Rajiv Rampat, Gabriele Dubini, Francesco Migliavacca, Luca Mainardi, Claudio Chiastra, Laura Gatto.

http://doi.org/10.1371/journal.pone.0213603

Abstract

Automatic algorithms for stent struts segmentation in optical coherence tomography (OCT) images of coronary arteries have been developed over the years, particularly with application on metallic stents. The aim of this study is three-fold: (1) to develop and to validate a segmentation algorithm for the detection of both lumen contours and polymeric bioresorbable scaffold struts from 8-bit OCT images, (2) to develop a method for automatic OCT pullback quality assessment, and (3) to demonstrate the applicability of the segmentation algorithm for the creation of patient-specific stented coronary artery for local hemodynamics analysis.

The proposed OCT segmentation algorithm comprises four steps: (1) image pre-processing, (2) lumen segmentation, (3) stent struts segmentation, (4) strut-based lumen correction. This segmentation process is then followed by an automatic OCT pullback image quality assessment. This method classifies the OCT pullback image quality as ‘good’ or ‘poor’ based on the number of regions detected by the stent segmentation. The segmentation algorithm was validated against manual segmentation of 1150 images obtained from 23 in vivo OCT pullbacks.

When considering the entire set of OCT pullbacks, lumen segmentation showed results comparable with manual segmentation and with previous studies (sensitivity ~97%, specificity ~99%), while stent segmentation showed poorer results compared to manual segmentation (sensitivity ~63%, precision ~83%). The OCT pullback quality assessment algorithm classified 7 pullbacks as ‘poor’ quality cases. When considering only the ‘good’ classified cases, the performance indexes of the scaffold segmentation were higher (sensitivity >76%, precision >86%).

This study proposes a segmentation algorithm for the detection of lumen contours and stent struts in low quality OCT images of patients treated with polymeric bioresorbable scaffolds. The segmentation results were successfully used for the reconstruction of one coronary artery model that included a bioresorbable scaffold geometry for computational fluid dynamics analysis.

Partial Text

Coronary artery disease is the leading cause of death worldwide [1]. Balloon angioplasty followed by stent implantation is the main treatment strategy of diseased coronary arteries [1]. Although in the short-term such treatment is generally effective, in the medium- and long-term stent efficacy can be reduced by adverse clinical events, such as in-stent restenosis and thrombosis [2]. Multiple causes have been associated with those events. Among them, experimental and in vivo evidences suggest that the altered local fluid dynamics induced by the stent plays an important role on promoting in-stent restenosis and thrombosis [3,4].

This section reports the results of the validation by considering both all OCT pullbacks (Subsection 3.1) and only the OCT pullbacks that were classified as ‘good’ by the pullback classification algorithm, which were 16 out of 23 (Subsection 3.2).

In this study, a new automatic segmentation algorithm for the detection of lumen contours and polymeric bioresorbable scaffold struts in intravascular OCT images was proposed and validated. Furthermore, a method for automatic OCT pullback quality assessment was developed to classify the OCT pullbacks as ‘good’ or ‘poor’ quality cases based on the appearance of the stent struts within the OCT images. Specifically, this method classified 7 out of the 23 OCT investigated OCT pullbacks as ‘poor’ quality cases.

This study presents an automatic algorithm for the detection of both lumen contours and polymeric bioresorbable scaffold struts in in vivo OCT images. The algorithm was validated against manual segmentation of two expert image readers using a dataset of 23 OCT pullbacks. Results of validation were good for both the lumen contour segmentation and the stent segmentation, considering the poor quality of some OCT pullbacks. Furthermore, a method for automatic OCT pullback quality assessment was proposed. Finally, one case was successfully used to show the applicability of the segmentation algorithm for the creation of patient-specific coronary artery models including the bioresorbable scaffold geometry for local hemodynamics analysis. In the future, the 3D reconstruction of many patient-specific cases treated with the Absorb BVS will enable the investigation of the role of abnormal hemodynamics on the occurrence of in-stent restenosis and thrombotic events, which limited the use of that bioresorbable scaffold.

 

Source:

http://doi.org/10.1371/journal.pone.0213603

 

Leave a Reply

Your email address will not be published.