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 V. Kaynig and T. Jones and D. Haehn and J. Lichtman and T. Parag and H. Pfister},
  journal={2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)},
  year={2017},
  pages={327-331}
}
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… Expand

References

SHOWING 1-10 OF 17 REFERENCES
Ilastik: Interactive learning and segmentation toolkit
Efficient Classifier Training to Minimize False Merges in Electron Microscopy Segmentation
Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images
Boundary Learning by Optimization with Topological Constraints
Robust Cell Detection and Segmentation in Histopathological Images Using Sparse Reconstruction and Stacked Denoising Autoencoders
Machine Learning of Hierarchical Clustering to Segment 2D and 3D Images
A benchmark for comparison of cell tracking algorithms
Synaptic circuits and their variations within different columns in the visual system of Drosophila
...
1
2
...