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. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-15745-5_26 | MICCAI (2) |
Keywords | Field | DocType |
probabilistic output,euclidean distance,automatic processing pipeline,sstem data,new insight,electron microscopy image,automatic geometry extraction,functional structure,geometrical consistency constraint,novel framework,neuronal process | Computer vision,Pattern recognition,Computer science,Euclidean distance,Artificial intelligence,Probabilistic logic,Automatic processing,Neuroanatomy,Random forest,Merge (version control),Tracing,Limiting | Conference |
Volume | Issue | ISSN |
13 | Pt 2 | 0302-9743 |
ISBN | Citations | PageRank |
3-642-15744-0 | 15 | 2.20 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Verena Kaynig | 1 | 78 | 8.86 |
Thomas J. Fuchs | 2 | 343 | 22.48 |
joachim m buhmann | 3 | 4363 | 730.34 |