Automatic 2D Segmentation of an Intracardiac Catheter Basedon MSER Blob Detector and Eccentricity

Bibliographic Details
Parent link:Advances in Intelligent Systems Research
Vol. 158 : Critical Infrastructures: Contingency Management, Intelligent, Agent-based, Cloud Computing and Cyber Security (IWCI 2018).— 2018.— [P. 26-30]
Corporate Author: Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Отделение информационных технологий
Other Authors: Danilov V. V. Vyacheslav Vladimirovich, Skirnevsky I. P. Igor Petrovich, Gerget O. M. Olga Mikhailovna, Manakov R. Roman
Summary:Title screen
The present study describes an algorithm for automatic catheter detection and segmentation based onechocardiography data. The catheter area was recognized and then delineated by combination of detection andsegmentation techniques such as the maximally stable extremal regions (MSER) algorithm, feature analysis andKittler-Illingworth thresholding algorithm. Regions processed by MSER detector were restricted by eccentricity.Eccentricity, assessing the shape of the particular region, was chosen as the main feature. Morphological closingwas applied at the pre-processing step. After applying MSER blob detector, detection accuracy of the catheter madeup 86.7±11.5%. After performing an additional restriction based on the shape analysis, the accuracy increased to92.8±6.6%. The proposed algorithm allows performing automatic detection and segmentation of the catheter insidethe heart based on 2D echocardiography data.
Published: 2018
Subjects:
Online Access:https://dx.doi.org/10.2991/iwci-18.2018.5
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=659652