A surface-based method for detection of coronary vessel boundaries in poor quality X-ray angiogram images

KAYIKCIOGLU T., GANGAL A., TURHAL M., Kose C.

PATTERN RECOGNITION LETTERS, vol.23, no.7, pp.783-802, 2002 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 23 Issue: 7
  • Publication Date: 2002
  • Doi Number: 10.1016/s0167-8655(01)00156-8
  • Journal Name: PATTERN RECOGNITION LETTERS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.783-802
  • Karadeniz Technical University Affiliated: Yes

Abstract

In this paper, we propose a surface-based method for simultaneous detection of left and right coronary borders that is suitable for analysis of poor quality X-ray angiogram images. Coronary artery is modelled with a 3D generalized cylinder (GC) with elliptic cross-sections. Based on this model, we developed a 2D surface function for the projection intensity distribution of a vessel part. The parameters associated with vessel edges are estimated from this model. The model takes into account local background intensity, noise and blurring. In simulation and real experiments over a range of imaging conditions, the proposed method consistently produced lower estimation error and variability in detecting edges than our previously reported 1D profile-based method. The improvement is most significant especially for noisy and low-contrast angiograms. (C) 2002 Elsevier Science B.V. All rights reserved.