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


Verena Kaynig; Amelio Vazquez-Reina; Seymour Knowles-Barley; Mike Roberts; Thouis R. Jones; Narayanan Kasthuri; Eric Miller; Je ff Lichtman; Hanspeter Pfister


Automated sample preparation and electron microscopy enables acquisition of very large image data sets. These technical advances are of special importance to the field of neuroanatomy, as 3D reconstructions of neuronal processes at the nm scale can provide new insight into the fine grained structure of the brain. Segmentation of large-scale electron microscopy data is the main bottleneck in the analysis of these data sets. In this paper we present a pipeline that provides state-of-the art reconstruction performance while scaling to data sets in the GB-TB range. First, we train a random forest classifier on interactive sparse user annotations. The classifier output is combined with an anisotropic smoothing prior in a Conditional Random Field framework to generate multiple segmentation hypotheses per image. These segmentations are then combined into geometrically consistent 3D objects by segmentation fusion. We provide qualitative and quantitative evaluation of the automatic segmentation and demonstrate large-scale 3D reconstructions of neuronal processes from a 27; 000 m3 volume of brain tissue over a cube of 30 m in each dimension corresponding to 1,000 consecutive image sections. We also introduce Mojo, a proofreading tool including semi-automated correction of merge errors based on sparse user scribbles.
Automatic reconstruction of a 27000 cubic micrometer volume.

BibTex entry

@article { 345, title = {Large-Scale Automatic Reconstruction of Neuronal Processes from Electron Microscopy Images}, journal = {Medical Image Analysis}, year = {2015}, author = {Verena Kaynig and Amelio Vazquez-Reina and Seymour Knowles-Barley and Mike Roberts and Thouis R. Jones and Narayanan Kasthuri and Eric Miller and Je ff Lichtman and Hanspeter Pfister} }