Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Detection of Melanoma Skin Cancer by Elastic Scattering Spectra: A Proposed Classification Method Publisher



Shirkavand A1, 2 ; Sarkar S3, 5 ; Ataiefashtami L4 ; Mohammadreza H3, 5
Authors
Show Affiliations
Authors Affiliations
  1. 1. Medical Laser Research Center (MLRC), Academic Center for Education, Culture and Research (ACECR), Tehran, Iran
  2. 2. Laser and Plasma research institute, Shahid Beheshti University, Tehran, Iran
  3. 3. Institute of advanced technologies in medicine (IAMT), Research Center for Science and Technology in Medicine (RCSTIM), Tehran University of Medical Sciences, Tehran, Iran
  4. 4. Dermatology department, Cell therapy clinic, Rooyan Institute, Academic Center for Education, Culture and Research (ACECR), Tehran, Iran
  5. 5. Institute of advanced technologies in medicine (IAMT), Research Center for Science and Technology in Medicine (RCSTIM), Tehran University of Medical Sciences, Tehran, Iran

Source: Iranian Journal of Medical Physics Published:2017


Abstract

Introduction: There is a strong need for developing clinical technologies and instruments for prompt tissue assessment in a variety of oncological applications as smart methods. Elastic scattering spectroscopy (ESS) is a real-time, noninvasive, point-measurement, optical diagnostic technique for malignancy detection through changes at cellular and subcellular levels, especially important in early diagnosis of invasive skin cancer, melanoma. In fact, this preliminary study was conducted to provide a classification method for analyzing the ESS spectra. Elastic scattering spectra related to the normal skin and melanoma lesions, which were already confirmed pathologically, were provided as input from an ESS database. Materials and Methods: A program was developed in MATLAB based on singular value decomposition and K-means algorithm for classification. Results: Accuracy and sensitivity of the proposed classifying method for normal and melanoma spectra were 87.5% and 80%, respectively. Conclusion: This method can be helpful for classification of melanoma and normal spectra. However, a large body of data and modifications are required to achieve better sensitivity for clinical applications.