Academic Journals Database
Disseminating quality controlled scientific knowledge

Assessment of Vascular Network Segmentation

Author(s): Jack Collins, Christopher Kurcz, Curtis Lisle, Yanling Liu, Enrique Zudaire

Journal: International Journal of Image Processing
ISSN 1985-2304

Volume: 4;
Issue: 6;
Start page: 584;
Date: 2011;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Vessel Segmentation | Network Comparison | Quantitative Analysis | Segmentation Quality | Segmentation Accuracy.

We present an analysis framework to assess the quality and accuracy of vesselsegmentation algorithms for three dimensional images. We generate synthetic (insilico) vessel models which act as ground truth and are constructed to embodyvarying morphological features. These models are transformed into imagesconstructed under different levels of contrast, noise, and intensity. Todemonstrate the use of our framework, we implemented two segmentationalgorithms and compare the results to the ground truth model using severalmeasures to quantify the accuracy and quality of segmentation. Furthermore, wecollect metrics which describe the characteristics of the vessels it fails tosegment. Our approach is illustrated with several examples. Funded by NCIContract No.HHSN261200800001E.
Save time & money - Smart Internet Solutions     

Tango Jona
Tangokurs Rapperswil-Jona