Automatic segmentation and skeletonization of neurons from confocal microscopy images based on the 3-D wavelet transform

We focus on methods for the preprocessing of neurons from three-dimensional (3-D) confocal microscopy images, which are needed for a subsequent detailed morphologic analysis. Due to the specific image properties of confocal microscopy scans, we had to include several heuristic approaches which are b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2002-07, Vol.11 (7), p.790-801
Main Authors: Dima, A., Scholz, M., Obermayer, K.
Format: Article
Language:English
Subjects:
Applied sciences
Confocal
Exact sciences and technology
Image analysis
Image contrast
Image edge detection
Image segmentation
Information geometry
Information, signal and communications theory
Microscopy
Neurons
Object detection
Pattern recognition
Preprocessing
Segmentation
Signal processing
Skeleton
Surface morphology
Telecommunications and information theory
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We focus on methods for the preprocessing of neurons from three-dimensional (3-D) confocal microscopy images, which are needed for a subsequent detailed morphologic analysis. Due to the specific image properties of confocal microscopy scans, we had to include several heuristic approaches which are based on multiscale edges to guarantee meaningful results: (1) a reliable segmentation of objects of different sizes independent of image contrast, and, based on it, (2) the computation of skeleton points along the branch central axes, and (3) the reliable detection of branching points and of problematic regions. These are preprocessing steps to gather information which is needed by the subsequent construction of a graph representing the geometry of the neuron and a final surface reconstruction.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2002.800888