Automated left ventricular border determination in cineangiograms based on a dynamic spider model

Author

Fan, N. ; Denys, B.G. ; Li, C.C. ; Reddy, P.S.

Author_Institution

Pittsburgh Univ., PA, USA

fYear

1990

fDate

23-26 Sep 1990

Firstpage

439

Lastpage

442

Abstract

A dynamic spider model is presented to automatically extract the left ventricular border in a sequence of cineangiograms. The spider legs correspond to the medical involution chords of a confined region which resembles the shape of the left ventricle and encompasses its deformations in expansion and contraction of the heart. The recognition task is to find a congruence transformation of the spider by adaptively minimizing a deformity measure. The left ventricular border is then determined via the dynamic programming within the confined region of the registered spider. The method has been tested on cineangiograms of 30 subjects with reasonable success

Keywords

cardiology; computerised picture processing; diagnostic radiography; medical diagnostic computing; modelling; adaptive minimization; automated left ventricular border determination; cineangiograms; congruence transformation; deformity measure; dynamic programming; dynamic spider model; medical involution chords; recognition task; spider legs; Cardiology; Computer vision; Deformable models; Dynamic programming; Heart; Humans; Image edge detection; Image segmentation; Leg; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers in Cardiology 1990, Proceedings.

Conference_Location

Chicago, IL

Print_ISBN

0-8186-2225-3

Type

conf

DOI

10.1109/CIC.1990.144252

Filename

144252