ICON: An interactive approach to train deep neural networks for segmentation of neuronal structures

@article{Gonda2017ICONAI,
  title={ICON: An interactive approach to train deep neural networks for segmentation of neuronal structures},
  author={Felix Gonda and Verena Kaynig and Thouis Ray Jones and Daniel Haehn and Jeff W. Lichtman and Toufiq Parag and Hanspeter Pfister},
  journal={2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)},
  year={2017},
  pages={327-331}
}
  • Felix Gonda, Verena Kaynig, +4 authors Hanspeter Pfister
  • Published 2017
  • Computer Science
  • 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
  • We present an interactive approach to train a deep neural network pixel classifier for the segmentation of neuronal structures. An interactive training scheme reduces the extremely tedious manual annotation task that is typically required for deep networks to perform well on image segmentation problems. Our proposed method employs a feedback loop that captures sparse annotations using a graphical user interface, trains a deep neural network based on recent and past annotations, and displays the… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES

    Ilastik: Interactive learning and segmentation toolkit

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images

    VIEW 4 EXCERPTS

    Boundary Learning by Optimization with Topological Constraints

    VIEW 1 EXCERPT

    Robust Cell Detection and Segmentation in Histopathological Images Using Sparse Reconstruction and Stacked Denoising Autoencoders

    • Hai Su, Fuyong Xing, +3 authors Lin Yang
    • Computer Science, Medicine
    • Deep Learning and Convolutional Neural Networks for Medical Image Computing
    • 2015
    VIEW 1 EXCERPT

    Synaptic circuits and their variations within different columns in the visual system of Drosophila

    VIEW 1 EXCERPT