3D neuron tip detection in volumetric microscopy images using an adaptive ray-shooting model. (March 2018)

• Record Type: Journal Article
• Authors: Liu, Min; Gong, Rong; Chen, Weixun; Peng, Hanchuan
• Is Part Of: Pattern recognition. Volume 75(2018:Mar.)
• Page Start: 263
• Page End: 271
• Publication Date: 2018-03
• Subjects: Neuron tips -- Neuron tracing -- Adaptive ray-shooting model -- Multistencils Fast Marching method; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.02.010
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: An automated 3D neuron tips detection method is proposed for volumetric images. A ray-shooting model is used to analyze the intensity distribution of tip points. The length of the rays can change adaptively by Multistencils Fast Marching Method. Abstract: 3D neuron tips could be very good candidates of seeding points for neuron tracing applications. Previously, a ray-shooting model was proposed to detect the neuron tips by analyzing the intensity distribution of the neighborhood around the tip candidates. However, the length of the shooting rays and the number of how many z -slices should be taken into account in this model are fixed empirical numbers, so it cannot handle challenging dataset where the diameter of the neuron varies much. In this paper, we propose an adaptive ray-shooting model by changing the length of the shooting rays and the number of adjacent slices according to the local diameter of the neuron obtained by the Multistencils Fast Marching (MSFM) method. Compared with the previous work, the experiments results show that the proposed method could improve the detection accuracy rate by about 10% in challenging datasets.