An artificial vision system for coronary angiography

Author

Poli, R. ; Coppini, G. ; Demi, M. ; Valli, G.

Author_Institution

Firenze Univ., Florence, Italy

fYear

1990

fDate

23-26 Sep 1990

Firstpage

17

Lastpage

20

Abstract

The coronary tree expert analyzer (CORTEX), a computer vision system for the description of the bidimensional shape and position of coronary vessels in standard nonsubtracted radiographic images, is described. The basic ideas used in developing the system are given, and the modules of CORTEX and their algorithmic implementation are described. According to a bottom-up approach, grouping criteria are utilized to produce intermediate image representations of increasing scale in a hierarchical manner (from edge points to curves, segments, bars, and finally to vessels and bifurcations). The evaluation of CORTEX performances according to a signal-detection-theory-like approach is also discussed

Keywords

cardiology; computer vision; diagnostic radiography; expert systems; medical diagnostic computing; CORTEX; algorithmic implementation; artificial vision system; bars; bidimensional shape; bifurcations; coronary angiography; coronary tree expert analyzer; coronary vessels position; curves; edge points; grouping criteria; medical diagnostic imaging; segments; signal-detection-theory-like approach; standard nonsubtracted radiographic images; Angiography; Bars; Bifurcation; Computer vision; Image analysis; Image representation; Image segmentation; Machine vision; Radiography; 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.1990.144156

Filename

144156