Abstract

We present an automatic segmentation method for delineation and quantitative thickness measurement of multiple layers in endoscopic airway optical coherence tomography (OCT) images. The boundaries of the mucosa and the sub-mucosa layers were extracted using a graph-theory-based dynamic programming algorithm. The algorithm was tested with pig airway OCT images acquired with a custom built long range endoscopic OCT system. The performance of the algorithm was demonstrated by cross-validation between auto and manual segmentation experiments. Quantitative thicknesses changes in the mucosal layers are obtained automatically for smoke inhalation injury experiments.

Highlights

  • Imaging the sub-surface structure of the airway wall is of great significance to detect abnormalities during airway injuries

  • 3.1 optical coherence tomography (OCT) system setup and animal preparation To verify the flexibility of our algorithm, the images acquired by the LR-SSOCT system reported by our group previously [10, 11] were used as the test set

  • OCT image data sets of a pig airway acquired by this LR-SSOCT system were used

Read more

Summary

INTRODUCTION

Imaging the sub-surface structure of the airway wall is of great significance to detect abnormalities during airway injuries. We have already obtained high resolution airway wall OCT images, the classification of the airway wall structures are mainly based on manual labeling of the boundaries [13], which is time-consuming and subjected to inter-observer errors. In order to robustly segment different airway wall structures and provide quantitative information of these structures automatically, we present a graph-theory-based segmentation algorithm using Cartesian airway OCT images as input. The quantification of the average layer thicknesses can be obtained after the precise localization of different layer boundaries. This algorithm was tested with pig airway images acquired by our LR-SSOCT system [11]. The results show that our algorithm can achieve accurate, robust, and fully automatic delineation of multiple structures in airway OCT images

METHOD
RESULTS
CONCLUSION

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.