Open AccessAutomatic neuron segmentation and neural network analysis method for phase contrast microscopy images
Author(s) -
Jincheng Pang,
Nurdan Özkucur,
Michael Ren,
David L. Kaplan,
Michael E. Levin,
Eric L. Miller
Publication year - 2015
Publication title -
biomedical optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.362
H-Index - 86
ISSN - 2156-7085
DOI - 10.1364/boe.6.004395
Subject(s) - computer science , artificial intelligence , photobleaching , computer vision , segmentation , contrast (vision) , image processing , image segmentation , microscopy , fluorophore , image (mathematics) , pattern recognition (psychology) , optics , fluorescence , physics
Phase Contrast Microscopy (PCM) is an important tool for the long term study of living cells. Unlike fluorescence methods which suffer from photobleaching of fluorophore or dye molecules, PCM image contrast is generated by the natural variations in optical index of refraction. Unfortunately, the same physical principles which allow for these studies give rise to complex artifacts in the raw PCM imagery. Of particular interest in this paper are neuron images where these image imperfections manifest in very different ways for the two structures of specific interest: cell bodies (somas) and dendrites. To address these challenges, we introduce a novel parametric image model using the level set framework and an associated variational approach which simultaneously restores and segments this class of images. Using this technique as the basis for an automated image analysis pipeline, results for both the synthetic and real images validate and demonstrate the advantages of our approach.