DocumentCode :
3504168
Title :
Automated segmentation of synapses in 3D EM data
Author :
Kreshuk, A. ; Straehle, C.N. ; Sommer, C. ; Koethe, U. ; Knott, G. ; Hamprecht, F.A.
Author_Institution :
Univ. of Heidelberg, Heidelberg, Germany
fYear :
2011
fDate :
March 30 2011-April 2 2011
Firstpage :
220
Lastpage :
223
Abstract :
This contribution presents a method for automatic detection of excitatory, asymmetric synapses and segmentation of synaptic junctional complexes in stacks of serial electron microscopy images with nearly isotropic resolution. The method uses a Random Forest classifier in the space of generic image features, computed directly in the 3D neighborhoods of each pixel, and an additional step of interactive probability maps thresholding. On the test dataset, the algorithm missed considerably less synapses than the human expert during the ground truth creation, while maintaining an equivalent false positive rate. The algorithm is implemented as an extension to the Interactive Learning and Segmentation Toolkit “ilastik” and is freely available on our website (www.ilastik.org/synapse-detection).
Keywords :
electron microscopy; image classification; image resolution; image segmentation; learning (artificial intelligence); medical image processing; neurophysiology; probability; 3D EM data; 3D neighborhoods; automated segmentation; equivalent false positive rate; excitatory asymmetric synapses; generic image features; ground truth creation; ilastik; interactive learning; interactive probability maps thresholding; nearly isotropic resolution; random Forest classifier; segmentation toolkit; serial electron microscopy images; synaptic junctional complexes; Feature extraction; Humans; Image segmentation; Microscopy; Pixel; Three dimensional displays; Training; Synapse detection; neural tissue segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on
Conference_Location :
Chicago, IL
ISSN :
1945-7928
Print_ISBN :
978-1-4244-4127-3
Electronic_ISBN :
1945-7928
Type :
conf
DOI :
10.1109/ISBI.2011.5872392
Filename :
5872392
Link To Document :
بازگشت