Presentation 2015-03-19
Angle Based Segmentation in Cardiovascular OCT Image
Yutaka KOKAWA, Haiyuan WU, Kazumasa SUZUKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Cardiovascular optical coherence tomography (OCT) is a catheter-based invasive imaging system. Using light rather than ultrasound, OCT produces high-resolution in vivo images of coronary arteries and deployed stents. In this paper, we propose an angle based segmentation method in cardiovascular OCT image. To make use of the characteristic of cardiovascular OCT image, and achieve its segmentation, we suggest polar-angle-brightness distribution vector (PABDV) to express the tissue in the blood vessel. Because the number of the tissue is unknown, we adopt AP (Affinity Propagation) and MSC (Mean Shift Clustering). We evaluate segmentation results using NMI (Normalized Mutual Information).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) OCT / PABDV / AP / MSC / Segmentation
Paper # BioX2014-52,PRMU2014-172
Date of Issue

Conference Information
Committee PRMU
Conference Date 2015/3/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Angle Based Segmentation in Cardiovascular OCT Image
Sub Title (in English)
Keyword(1) OCT
Keyword(2) PABDV
Keyword(3) AP
Keyword(4) MSC
Keyword(5) Segmentation
1st Author's Name Yutaka KOKAWA
1st Author's Affiliation Graduate School of Systems Engineering, Wakayama University()
2nd Author's Name Haiyuan WU
2nd Author's Affiliation Faculty of Systems Engineering, Wakayama University
3rd Author's Name Kazumasa SUZUKI
3rd Author's Affiliation Graduate School of Systems Engineering, Wakayama University
Date 2015-03-19
Paper # BioX2014-52,PRMU2014-172
Volume (vol) vol.114
Number (no) 521
Page pp.pp.-
#Pages 6
Date of Issue