Segmentation of Glial Cells in 3D Microscopy Images


Glial cells play an important role in regulating synaptogenesis, development of blood-brain barrier, and brain tumor metastasis. Quantitative analysis of glial cells can offer new insights to many studies. However, the complicated morphology of the protrusions of glial cells and the entangled cell-to-cell network cause significant difficulties to the extraction of quantitative information in images. This disclosure presents a new method for instance-level segmentation of glial cells in 3D microscopy images. First, the new method obtains accurate voxel-level segmentation by leveraging the recent advances of fully convolutional networks (FCN). Then it applies a k-terminal cut algorithm to disentangle the complex cell-to-cell connections. Extensive experiments using real 3D images show that the new method has superior performance over the current state-of-the-art methods.

Patent Information:
Medical Diagnostics
For Information, Contact:
Tim Joyce
Technology Commercialization Manager
University of Notre Dame
(574) 631-3029
Danny Chen
Siyuan Zhang
Ian Guldner
Lin Yang
Yizhe Zhang
© 2018. All Rights Reserved. Powered by Inteum