The use of neural networks and texture analysis for rapid objective selection of regions of interest in cytoskeletal images

Amanda D Felder Derkacs, Samuel R. Ward, Richard L. Lieber*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Understanding cytoskeletal dynamics in living tissue is prerequisite to understanding mechanisms of injury, mechanotransduction, and mechanical signaling. Real-time visualization is now possible using transfection with plasmids that encode fluorescent cytoskeletal proteins. Using this approach with the muscle-specific intermediate filament protein desmin, we found that a green fluorescent protein-desmin chimeric protein was unevenly distributed throughout the muscle fiber, resulting in some image areas that were saturated as well as others that lacked any signal. Our goal was to analyze the muscle fiber cytoskeletal network quantitatively in an unbiased fashion. To objectively select areas of the muscle fiber that are suitable for analysis, we devised a method that provides objective classification of regions of images of striated cytoskeletal structures into "usable" and "unusable" categories. This method consists of a combination of spatial analysis of the image using Fourier methods along with a boosted neural network that "decides" on the quality of the image based on previous training. We trained the neural network using the expert opinion of three scientists familiar with these types of images. We found that this method was over 300 times faster than manual classification and that it permitted objective and accurate classification of image regions.

Original languageEnglish (US)
Pages (from-to)115-122
Number of pages8
JournalMicroscopy and Microanalysis
Volume18
Issue number1
DOIs
StatePublished - Feb 2012

Keywords

  • classification
  • confocal microscopy
  • image analysis
  • skeletal muscle

ASJC Scopus subject areas

  • Instrumentation

Fingerprint Dive into the research topics of 'The use of neural networks and texture analysis for rapid objective selection of regions of interest in cytoskeletal images'. Together they form a unique fingerprint.

Cite this