Gebiss: an ImageJ plugin for the specification of ground truth and the performance evaluation of 3D segmentation algorithms
1 Bioinformatics Institute, Agency for Science, Technology and Research (A*STAR), 30 Biopolis Street 07-01 Matrix, 138671, Singapore
2 School of Biological Sciences, Nanyang Technological University, Singapore
3 Department of Biological Sciences, National University of Singapore, Singapore
4 Translational Research Resource Centre, Laboratory for Molecular Cell Biology, Medical Research Council, University College London, London, UK
BMC Bioinformatics 2011, 12:232 doi:10.1186/1471-2105-12-232Published: 13 June 2011
Image segmentation is a crucial step in quantitative microscopy that helps to define regions of tissues, cells or subcellular compartments. Depending on the degree of user interactions, segmentation methods can be divided into manual, automated or semi-automated approaches. 3D image stacks usually require automated methods due to their large number of optical sections. However, certain applications benefit from manual or semi-automated approaches. Scenarios include the quantification of 3D images with poor signal-to-noise ratios or the generation of so-called ground truth segmentations that are used to evaluate the accuracy of automated segmentation methods.
We have developed Gebiss; an ImageJ plugin for the interactive segmentation, visualisation and quantification of 3D microscopic image stacks. We integrated a variety of existing plugins for threshold-based segmentation and volume visualisation.
We demonstrate the application of Gebiss to the segmentation of nuclei in live Drosophila embryos and the quantification of neurodegeneration in Drosophila larval brains. Gebiss was developed as a cross-platform ImageJ plugin and is freely available on the web at http://imaging.bii.a-star.edu.sg/projects/gebiss/ webcite.