Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access Methodology article

Semi-Automatic segmentation of multiple mouse embryos in MR images

Leila Baghdadi1*, Mojdeh Zamyadi1, John G Sled12, Jürgen E Schneider3, Shuomo Bhattacharya3, R Mark Henkelman12 and Jason P Lerch12

Author Affiliations

1 Mouse Imaging Centre, The Hospital for Sick Children, Toronto, Canada

2 Department of Medical Biophysics, University of Toronto, Toronto, Canada

3 Department of Cardiovascular Medicine, University of Oxford, Oxford, UK

For all author emails, please log on.

BMC Bioinformatics 2011, 12:237  doi:10.1186/1471-2105-12-237

Published: 16 June 2011

Abstract

Background

The motivation behind this paper is to aid the automatic phenotyping of mouse embryos, wherein multiple embryos embedded within a single tube were scanned using Magnetic Resonance Imaging (MRI).

Results

Our algorithm, a modified version of the simplex deformable model of Delingette, addresses various issues with deformable models including initialization and inability to adapt to boundary concavities. In addition, it proposes a novel technique for automatic collision detection of multiple objects which are being segmented simultaneously, hence avoiding major leaks into adjacent neighbouring structures. We address the initialization problem by introducing balloon forces which expand the initial spherical models close to the true boundaries of the embryos. This results in models which are less sensitive to initial minimum of two fold after each stage of deformation. To determine collision during segmentation, our unique collision detection algorithm finds the intersection between binary masks created from the deformed models after every few iterations of the deformation and modifies the segmentation parameters accordingly hence avoiding collision.

We have segmented six tubes of three dimensional MR images of multiple mouse embryos using our modified deformable model algorithm. We have then validated the results of the our semi-automatic segmentation versus manual segmentation of the same embryos. Our Validation shows that except paws and tails we have been able to segment the mouse embryos with minor error.

Conclusions

This paper describes our novel multiple object segmentation technique with collision detection using a modified deformable model algorithm. Further, it presents the results of segmenting magnetic resonance images of up to 32 mouse embryos stacked in one gel filled test tube and creating 32 individual masks.