A new strategy to obtain robust markers for blood vessels segmentation by using the watersheds method

Authors:
Roberto Rodríguez;Teresa E. Alarcón;Oriana Pacheco
Affiliations:
Institute of Cybernetics, Mathematics and Physics (ICIMAF), Group of Digital Signal Processing, Calle 15 No. 551 e/ C y D CP 10400, La Habana, Cuba;Institute of Cybernetics, Mathematics and Physics (ICIMAF), Group of Digital Signal Processing, Calle 15 No. 551 e/ C y D CP 10400, La Habana, Cuba;Institute of Cybernetics, Mathematics and Physics (ICIMAF), Group of Digital Signal Processing, Calle 15 No. 551 e/ C y D CP 10400, La Habana, Cuba
Venue:
Computers in Biology and Medicine
Year:
2005

Citing 8
Cited 2

Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations

IEEE Transactions on Pattern Analysis and Machine Intelligence
An overview of morphological filtering

Circuits, Systems, and Signal Processing - Special issue: median and morphological filters
Digital Image Processing

Digital Image Processing
Color Segmentation Applied to Study of the Angiogenesis. Part I

Journal of Intelligent and Robotic Systems
A Strategy for Reduction of Noise in Segmented Images. Its Use in the Study of Angiogenesis

Journal of Intelligent and Robotic Systems
Image Analysis and Mathematical Morphology

Image Analysis and Mathematical Morphology
Color image segmentation for Bladder Cancer Diagnosis

Mathematical and Computer Modelling: An International Journal
Morphological grayscale reconstruction in image analysis: applications and efficient algorithms

IEEE Transactions on Image Processing

Masseter segmentation using an improved watershed algorithm with unsupervised classification

Computers in Biology and Medicine
A marker-based watershed method for X-ray image segmentation

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

The watersheds method is a powerful segmentation tool developed in mathematical morphology. In order to prevent its over-segmentation, in this paper, we present a new strategy to obtain robust markers for segmentation of blood vessels from malignant tumors. For this purpose, we introduced a new algorithm. We propose a two-stage segmentation strategy which involves: (1) extracting an approximate region containing the blood vessel and part of the background near the blood vessel, and (2) segmenting the blood vessel from the background within this region. The approach effectively reduces the influence of peripheral background intensities on the extraction of a blood vessel region. In this application the important information to be extracted from images is only the number of blood vessels present in the images. The proposed strategy was tested on manual segmentation, where segmentation errors less than 10% for false positives and 0% for false negatives are observed. It is demonstrated by extensive experimentation, by using real images, that the proposed strategy was suitable for our application in the environment of a personal computer.