Multi-atlas based neointima segmentation in intravascular coronary OCT

Neointima thickening plays a decisive role in coronary restenosis after stenting. The aim of this study is to detect neointima tissue in intravascular optical coherence tomography (IVOCT) sequences. We developed a multi-atlas based segmentation method to detect neointima without stent struts locations. The atlases are selected by measurements of stenosis and a similarity metric. The probability map is then used to estimate neointima label in the unseen image. To account for the registration errors, a patch-based label fusion approach is applied. Validation is performed using 18 typical in-vivo IVOCT sequences. The comparison against manual expert segmentation and other fusion approaches demonstrates that the proposed neointima identification is robust and accurate.

[1]  Daniel Rueckert,et al.  Nonrigid registration using free-form deformations: application to breast MR images , 1999, IEEE Transactions on Medical Imaging.

[2]  Daniel Rueckert,et al.  Automatical vessel wall detection in intravascular coronary OCT , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[3]  D. G. Vince,et al.  Atherosclerotic plaque characterization by acoustic impedance analysis of intravascular ultrasound data , 2003, IEEE Symposium on Ultrasonics, 2003.

[4]  Daniel Rueckert,et al.  Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy , 2009, NeuroImage.

[5]  Haim Levkowitz,et al.  Characterization of Atherosclerosis Plaque in OCT Images Using Texture Analysis and Parametric Equations , 2011, 2011 15th International Conference on Information Visualisation.

[6]  Juan Luis Gutiérrez-Chico,et al.  Optical coherence tomography: from research to practice , 2012, European heart journal cardiovascular Imaging.

[7]  Masanori Yamamoto,et al.  Evaluation by optical coherence tomography of neointimal coverage of sirolimus-eluting stent three months after implantation. , 2007, The American journal of cardiology.

[8]  Dimitrios I. Fotiadis,et al.  Atherosclerotic plaque characterization in Optical Coherence Tomography images , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  D. Louis Collins,et al.  Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation , 2011, NeuroImage.

[10]  Mert R. Sabuncu,et al.  A Generative Model for Image Segmentation Based on Label Fusion , 2010, IEEE Transactions on Medical Imaging.

[11]  Y. Yuzawa,et al.  Neointima formation in a restenosis model is suppressed in midkine-deficient mice. , 2000, The Journal of clinical investigation.

[12]  O. Rodriguez,et al.  Near real-time plaque segmentation of IVUS , 2003, Computers in Cardiology, 2003.

[13]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..