Tubule segmentation of fluorescence microscopy images based on convolutional neural networks with inhomogeneity correction

Soonam Lee, Chichen Fu, Paul Salama, Kenneth W. Dunn, Edward J. Delp

Research output: Contribution to journalConference article

4 Scopus citations


Fluorescence microscopy has become a widely used tool for studying various biological structures of in vivo tissue or cells. However, quantitative analysis of these biological structures re- mains a challenge due to their complexity which is exacerbated by distortions caused by lens aberrations and light scattering. Moreover, manual quantification of such image volumes is an in- tractable and error-prone process, making the need for automated image analysis methods crucial. This paper describes a segmen- tation method for tubular structures in fluorescence microscopy images using convolutional neural networks with data augmen- tation and inhomogeneity correction. The segmentation results of the proposed method are visually and numerically compared with other microscopy segmentation methods. Experimental re- sults indicate that the proposed method has better performance with correctly segmenting and identifying multiple tubular struc- tures compared to other methods.

Original languageEnglish (US)
Article numberS11
JournalIS and T International Symposium on Electronic Imaging Science and Technology
StatePublished - Jan 1 2018
Event16th Computational Imaging Conference, COMIG 2018 - Burlingame, United States
Duration: Jan 28 2018Feb 1 2018


ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Software
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Cite this