Automatic mining of fruit fly embryo images

Jia-Yu Pan, André G. R. Balan, Eric P. Xing, Agma J. M. Traina, Christos Faloutsos

Abstract

We present FEMine, an automatic system for image-based gene expression analysis. We perform experiments on the largest publicly available collection of Drosophila ISH (in situ hybridization) images, showing that our FEMine system achieves excellent performance in classification, clustering, and content-based image retrieval. The major innovation of FEMine is the use of automatically discovered latent spatial "themes" of gene expressions, LGEs, in the whole-embryo context, as opposed to patterns in nearly disjoint portions of an embryo proposed in previous methods.
BibTeX
@inproceedings{pan2006automatic,
  author = {Jia-Yu Pan and André G. R. Balan and Eric P. Xing and Agma J. M. Traina and Christos Faloutsos},
  title = {{Automatic mining of fruit fly embryo images}},
  booktitle = {ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  year = {2006},
  doi = {10.1145/1150402.1150489},
}

Loading related content...

Figure