Geometrical consistent 3D tracing of neuronal processes in ssTEM data

Authors:
Verena Kaynig;Thomas J. Fuchs;Joachim M. Buhmann
Affiliations:
Department of Computer Science, ETH Zurich, Switzerland and Electron Microscopy ETH Zurich, Switzerland;Department of Computer Science, ETH Zurich, Switzerland;Department of Computer Science, ETH Zurich, Switzerland
Venue:
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
Year:
2010

Citing 2
Cited 4

Random Forests

Machine Learning
Convolutional networks can learn to generate affinity graphs for image segmentation

Neural Computation

Multiple structure tracing in 3d electron micrographs

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Neural process reconstruction from sparse user scribbles

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Anisotropic ssTEM image segmentation using dense correspondence across sections

MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
The open connectome project data cluster: scalable analysis and vision for high-throughput neuroscience

Proceedings of the 25th International Conference on Scientific and Statistical Database Management

Quantified Score

Hi-index	0.00

Visualization

Abstract

In neuroanatomy, automatic geometry extraction of neurons from electron microscopy images is becoming one of the main limiting factors in getting new insights into the functional structure of the brain. We propose a novel framework for tracing neuronal processes over serial sections for 3d reconstructions. The automatic processing pipeline combines the probabilistic output of a random forest classifier with geometrical consistency constraints which take the geometry of whole sections into account. Our experiments demonstrate significant improvement over grouping by Euclidean distance, reducing the split and merge error per object by a factor of two.