Automated 3D region growing algorithm based on an assessment function

Authors:
Chantal Revol-Muller;Francoise Peyrin;Yannick Carrillon;Christophe Odet
Affiliations:
CREATIS, UMR CNRS 5515, INSA, Bat. Blaise Pascal, 7 avenue Jean Capelle, 69621 Villeurbanne Cedex, France;CREATIS, UMR CNRS 5515, INSA, Bat. Blaise Pascal, 7 avenue Jean Capelle, 69621 Villeurbanne Cedex, France and ESRF, BP 220, 38043 Grenoble Cedex, France;Labo RMN, UMR CNRS 5012, 69622 Villeurbanne Cedex, France;CREATIS, UMR CNRS 5515, INSA, Bat. Blaise Pascal, 7 avenue Jean Capelle, 69621 Villeurbanne Cedex, France
Venue:
Pattern Recognition Letters
Year:
2002

Citing 3
Cited 3

A new minimum variance region growing algorithm for image segmentation

Pattern Recognition Letters
Seeded Region Growing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Analysis and Mathematical Morphology

Image Analysis and Mathematical Morphology

A constrained region growing approach based on watershed for the segmentation of low contrast structures in bone micro-CT images

Pattern Recognition
Ligand Electron Density Shape Recognition Using 3D Zernike Descriptors

PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
Analysis of skeletal microstructure with clinical multislice CT

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II

Quantified Score

Hi-index	0.10

Visualization

Abstract

A new region growing algorithm is proposed for the automated segmentation of three-dimensional images. No initial parameters such as the homogeneity threshold or the seeds location have to be adjusted. The principle of our method is to build a region growing sequence by increasing the maximal homogeneity threshold from a very small value to a large one. On each segmented region, a 3D parameter that has been validated on a test image assesses the segmentation quality. This set of values called assessment function is used to determine of the optimal homogeneity criterion. Our algorithm was tested on 3D MR images for the segmentation of trabecular bone samples in order to quantify osteoporosis. A comparison to automated and manual thresholding showed that our algorithm performs better. Its main advantages are to eliminate isolated points due to the noise and to preserve connectivity of the bone structure.