Automatic Lumen Segmentation in Intravascular Optical Coherence Tomography Using Morphological Features

Authors:

Abstract
Lumen segmentation in intravascular optical coherence tomography (IVOCT) images is a fundamental work for more advanced plaque analysis, stent recognition, fractional flow reserve (FFR) assessment etc. However, the catheter, guide-wire, inadequate blood clearance and other factors will impact on the accuracy of lumen segmentation. We present a simple and effective method for automatic lumen segmentation method in IVOCT based on morphological features. We use image enhancement, median filtering, image binarization and morphological closing operation to reduce speckle noise, minimize the effect of blood artifacts and fill in small holes inside vascular walls. We extract the orientation and area-size of connected regions as morphological features in images and remove the catheter and guide-wire completely by morphological corrosion operation, small area-size region removal and orientation morphological feature comparison. And then the contour of the lumen can be discriminated. The evaluation metrics of this method, Dice index, Hausdorff distance, Jaccard index and Accuracy of 99.32%, 0.06 mm, 99.4% and 99.66%, respectively are obtained from comparing with expert annotations on 268 IVOCT images. Compared with other morphology based lumen segmentation methods’ the presented method can remove the catheter and guide-wire completely, even if the catheter and guide-wire cling to the lumen or the shape of catheter is irregular. Since only morphological operations are used to complete all processes, the calculation burden is reduced greatly.
Funding Information
  • National Natural Science Foundation of China (61505138, 61635008, 61735011)
  • Tianjin Science and Technology Support Plan Program Funding (16JCQNJC01800)
  • China Postdoctoral Science Foundation (2015M580199, 2016T90205)
  • National Instrumentation Program (2013YQ030915)
  • National key research and development program (2016YFC0100500)
  • Tianjin University (2019KFKT004)

This publication has 28 references indexed in Scilit: