Multi-scale segmentation of neurons based on one-class classification

- A multi-scale framework to segment the neurons.
- A mathematically rigorous general approach for the normalization of the response of a multi-scale ensemble of linear filters.
- A multi-scale framework to compute the Laplacian of the 3D image stack and an approach to compute as many decision functions as the number of scales (one for each scale) used for segmentation.
- A mathematical justification for using different low-pass filters to compute the Laplacian and the Hessian matrix.
- An extensive experimental evaluation of the performance of our approach on a number of datasets, including all of the DIADEM competition.

BackgroundHigh resolution multiphoton and confocal microscopy has allowed the acquisition of large amounts of data to be analyzed by neuroscientists. However, manual processing of these images has become infeasible. Thus, there is a need to create automatic methods for the morphological reconstruction of 3D neuronal image stacks.New methodAn algorithm to extract the 3D morphology from a neuron is presented. The main contribution of the paper is the segmentation of the neuron from the background. Our segmentation method is based on one-class classification where the 3D image stack is analyzed at different scales. First, a multi-scale approach is proposed to compute the Laplacian of the 3D image stack. The Laplacian is used to select a training set consisting of background points. A decision function is learned for each scale from the training set that allows determining how similar an unlabeled point is to the points in the background class. Foreground points (dendrites and axons) are assigned as those points that are rejected as background. Finally, the morphological reconstruction of the neuron is extracted by applying a state-of-the-art centerline tracing algorithm on the segmentation.ResultsQuantitative and qualitative results on several datasets demonstrate the ability of our algorithm to accurately and robustly segment and trace neurons.Comparison with existing method(s)Our method was compared to state-of-the-art neuron tracing algorithms.ConclusionsOur approach allows segmentation of thin and low contrast dendrites that are usually difficult to segment. Compared to our previous approach, this algorithm is more accurate and much faster.