Learning Context Cues for Synapse Segmentation in EM Volumes
Embed of video is only possible from Mediaspace, Vimeo or Youtube
We present a new approach for the automated segmentation of excitatory synapses in image stacks acquired by electron microscopy. We rely on a large set of image features specifically designed to take spatial context into account and train a classifier that can effectively utilize cues such as the presence of a nearby post-synaptic region. As a result, our algorithm successfully distinguishes synapses from the numerous other organelles that appear within an EM volume, including those whose local textural properties are relatively similar. This enables us to achieve very high detection rates with very few false positives.
C. Becker, K. Ali, G. Knott, P. Fua
Results
Embed of video is only possible from Mediaspace, Vimeo or Youtube
Automatic segmentation of synapses. Comparison between our method and [1].
This video shows 2D cuts at different Z-planes. Voxels detected as synapses labeled in red.
[1] Kreshuk, A., Straehle, C., Sommer, C., Koethe, U., Knott, G., Hamprecht, F.: Automated segmentation of synapses in 3D EM data. ISBI 2012
Embed of video is only possible from Mediaspace, Vimeo or Youtube
3D reconstruction of the detected synaptic voxels after removing connected regions with less than 2000 voxels on a somatosensory cortex EM cube.
References
Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.
Learning Context Cues for Synapse Segmentation
IEEE Transactions on Medical Imaging. 2013. Vol. 32, num. 10, p. 1864–1877. DOI : 10.1109/Tmi.2013.2267747.Contacts
| Carlos Becker | [e-mail] |
| [e-mail] | |
| Pascal Fua | [e-mail] |