Active learning based segmentation of Crohn's disease using principles of visual saliency

@article{Mahapatra2014ActiveLB,
  title={Active learning based segmentation of Crohn's disease using principles of visual saliency},
  author={Dwarikanath Mahapatra and Peter J. Sch{\"u}ffler and Jeroen A. W. Tielbeek and Jesica Makanyanga and Jaap Stoker and Stuart A. Taylor and Frans Vos and Joachim M. Buhmann},
  journal={2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)},
  year={2014},
  pages={226-229}
}
We propose a active learning (AL) approach to segment Crohn's disease (CD) affected regions in abdominal magnetic resonance (MR) images. Our label query strategy is inspired from the principles of visual saliency which has similar considerations for choosing the most salient region. These similarities are encoded in a graph using classification maps and low… CONTINUE READING