A sophisticated edge detection method for muscle biopsy image analysis

  • Authors:

  • P. Tzekis;A. Papastergiou;A. Hatzigaidas;A. Cheva

  • Affiliations:

  • School of Sciences - Department of Mathematics, Aristotle University of Thessaloniki, Greece;Department of Electronics, Alexander Technological Educational Institute of Thessaloniki, Aristotle University of Thessaloniki, Greece;Department of Electronics, Alexander Technological Educational Institute of Thessaloniki, Aristotle University of Thessaloniki, Greece;Department of Pathology, Medical School, Aristotle University of Thessaloniki, Greece

  • Venue:
  • SSIP'07 Proceedings of the 7th WSEAS International Conference on Signal, Speech and Image Processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Muscle biopsy image morphometric analysis provides valuable diagnostic information to expert clinicians. Subsequently, there is an indispensable need to support muscle fiber morphometry with computer-aided automated systems that require no user interaction. The first step towards producing such a system is the automated border detection of muscle fibers. The objective of this work is to investigate the potential performance of edge detection algorithms, as well as any optimal combination of them, towards automated identification of regions of interest in a muscle biopsy image. Finally, a sophisticated edge detection model is proposed, that seems to closely resemble actual fibers boundaries and can be a reliable base for an accurate and effective segmentation of muscle biopsy images.