Quantitative measurement of nerve cells and myelin sheaths from microscopic images via two-staged segmentation

  • Authors:

  • Yung-Chun Liu;Chih-Kai Chen;Hsin-Chen Chen;Syu-Huai Hong;Cheng-Chang Yang;I-Ming Jou;Yung-Nien Sun

  • Affiliations:

  • Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C. and Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C.;Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C. and Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C.;Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C. and Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C.;Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C. and Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C.;Institute of Basic Medical Sciences, National Cheng Kung University, Taiwan, R.O.C. and Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C.;Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C. and Department of Orthopedics, National Cheng Kung University Hospital, Taiwan, R.O.C.;Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C. and Medical Device Innovation Center, National Cheng Kung University, Taiwan, R.O.C.

  • Venue:
  • ACIIDS'12 Proceedings of the 4th Asian conference on Intelligent Information and Database Systems - Volume Part III
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Cell morphology measurement is important in evaluating the injury level of nervous system. However, current measurement process is mostly achieved by manual estimation which is subjective and time-consuming. We hence propose a two-stage method to automatically segment axons and myelin sheaths from microscopic images for measuring the cell morphology quantitatively. First, an automatic thresholding method is used to obtain axon candidates and then geometric and image properties are used to assure the axon regions. Second, the outer contour of myelin sheath is segmented using the active contour model with the obtained axon contour as the initial solution. Then, the desired morphological parameters can be readily measured. In the experiments, we used seven nerve images for accuracy validation and achieved very small contour distance errors (less than 0.5 μm with nerve diameter around 8 μm in average). Overall, the proposed method is found efficient and useful in nerve parameter evaluation.