Title
Minimum Spanning Trees (MST) as a Tool for Describing Tissue Architecture when Grading Bladder Carcinoma
Abstract
In this pilot study we have investigated the possible use of minimum spanning trees, MST, as a way of quantitatively describing the tissue architecture when developing a computer program for malignancy grading of transitional cell bladder carcinoma. The MST was created by connecting the centre points of the nuclei in the tissue section image. These nuclei were found by thresholding the image at an automatically determined threshold followed by a connected component labeling and a watershed algorithm for separation of overlapping nuclei. Clusters were defined in the MST by thresholding the edge lengths. For these clusters geometric and densitometric features were measures. These features were compared by multivariate statistical methods to the subjective grading by the pathologists and the resulting correspondence was 85% on a material of 40 samples.
Year
DOI
Venue
1995
10.1007/3-540-60298-4_322
ICIAP
Keywords
Field
DocType
grading bladder carcinoma,tissue architecture,minimum spanning trees,multivariate statistics,minimum spanning tree,connected component
Grading (education),Pattern recognition,Multivariate statistics,Computer science,Tissue section,Artificial intelligence,Transitional cell bladder carcinoma,Spanning tree,Thresholding,Linear discriminant analysis,Connected-component labeling
Conference
ISBN
Citations 
PageRank 
3-540-60298-4
0
0.34
References 
Authors
4
7
Name
Order
Citations
PageRank
Heung-Kook Choi1285.32
ewert bengtsson213525.36
Torsten Jarkrans331.07
Janos Vasko400.34
Kenneth Wester500.34
Per-Uno Malmström600.34
Christer Busch700.34