rss
J Clin Pathol 2005;58:932-938 doi:10.1136/jcp.2004.022095
  • Original article

A novel wavelet neural network based pathological stage detection technique for an oral precancerous condition

  1. R R Paul1,
  2. A Mukherjee2,
  3. P K Dutta3,
  4. S Banerjee4,
  5. M Pal5,
  6. J Chatterjee6,
  7. K Chaudhuri7,
  8. K Mukkerjee8
  1. 1Department of Oral and Maxillofacial Pathology, R Ahmed Dental College and Hospital, Kolkata, 700 014, India
  2. 2Centre of Excellence for Embedded Systems, Tata Consultancy Services, Kolkata, 700 091, India
  3. 3Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, 721 302 West Bengal, India
  4. 4Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur, 721 302, India
  5. 5Institute of Interdisciplinary Scientific Research, Kolkata, 700 005, West Bengal, India
  6. 6Department of Radiology (Diagnosis) Medical College Hospitals, Kolkata, 700 073, India
  7. 7Human Genetics and Genomics Group, Indian Institute of Chemical Biology, Kolkata, 700 032, India
  8. 8Indian Institute of Chemical Biology
  1. Correspondence to:
 Dr K Chaudhuri
 Human Genetics and Genomics Group, Indian Institute of Chemical Biology, 4, Raja S C Mullick Road, Kolkata-700032, India; kchaudhuriiicb.res.in
  • Accepted 22 February 2005

Abstract

Aim: To describe a novel neural network based oral precancer (oral submucous fibrosis; OSF) stage detection method.

Method: The wavelet coefficients of transmission electron microscopy images of collagen fibres from normal oral submucosa and OSF tissues were used to choose the feature vector which, in turn, was used to train the artificial neural network.

Results: The trained network was able to classify normal and oral precancer stages (less advanced and advanced) after obtaining the image as an input.

Conclusions: The results obtained from this proposed technique were promising and suggest that with further optimisation this method could be used to detect and stage OSF, and could be adapted for other conditions.

Footnotes

    This Article

    1. Abstract
    2. Full text
    3. PDF

    Responses

    1. Submit a response
    2. No responses published

    Register for free content

    The full back archive is now available for all BMJ Journals. Institutional subscribers may access the entire archive as part of their subscription. Personal subscribers will also have access to all content when logged in. Non-subscribers who register have free access to all articles published before 2006 right back to volume 1 issue 1. Register here to access the free archive of all BMJ Journals.

    Don't forget to sign up for content alerts so you keep up to date with all the articles as they are published.