Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach

In this paper, a fully automatic method for luminal contour segmentation in intracoronary ultrasound imaging is introduced. Its principle is based on a contour with a priori properties that evolves according to the statistics of the ultrasound texture brightness, which is generally Rayleigh distribu...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on medical imaging Ročník 23; číslo 5; s. 554 - 566
Hlavní autoři:	Brusseau, E., de Korte, C.L., Mastik, F., Schaar, J., van der Steen, A.F.W.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.05.2004 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Témata:	Algorithms Anatomy, Cross-Sectional - methods Area measurement Arteries Arteries - diagnostic imaging Biomedical engineering Biomedical imaging Biomedical measurements Computer Science Coronary Vessels - diagnostic imaging Humans Image Interpretation, Computer-Assisted - methods Image Processing Image segmentation Medical Imaging Models, Cardiovascular Models, Statistical Pattern Recognition, Automated Reproducibility of Results Sensitivity and Specificity Statistical distributions Thorax Ultrasonic imaging Ultrasonic variables measurement Ultrasonography, Interventional - methods
ISSN:	0278-0062, 1558-254X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	In this paper, a fully automatic method for luminal contour segmentation in intracoronary ultrasound imaging is introduced. Its principle is based on a contour with a priori properties that evolves according to the statistics of the ultrasound texture brightness, which is generally Rayleigh distributed. The main interest of the technique is its fully automatic character. This is insured by an initial contour that is not set by the user, like in classical snake-based algorithms, but estimated and, thus, adapted to each image. Its estimation combines two pieces of information extracted from the a posteriori probability function of the contour position: the function maximum location (or maximum a posteriori estimator) and the first zero-crossing of its derivative. Then, starting from the initial contour, a region of interest is automatically selected and the process iterated until the contour evolution can be ignored. In vivo coronary images from 15 patients, acquired with the 20-MHz central frequency Jomed Invision ultrasound scanner, were segmented with the developed method. Automatic contours were compared to those manually drawn by two physicians in terms of mean absolute difference. The results demonstrate that the error between automatic contours and the average of manual ones is of small amplitude, and only very slightly higher (0.099/spl plusmn/0.032 mm) than the interexpert error (0.097/spl plusmn/0.027 mm).
Bibliografie:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 content type line 23 ObjectType-Undefined-3 ObjectType-Article-1 ObjectType-Feature-2
ISSN:	0278-0062 1558-254X
DOI:	10.1109/TMI.2004.825602