IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER

Arushi Raghuvanshi, Marek Perkowski

2011

Abstract

Melanoma cancer is one of the most dangerous and potentially deadly types of skin cancer; however, if diagnosed early, it is nearly one-hundred percent curable (UnderstMel09). Here we propose an efficient system which helps with the early diagnosis of melanoma cancer. Different image processing techniques and machine learning algorithms are evaluated to distinguish between cancerous and non-cancerous moles. Two image feature databases were created: one compiled from a dermatologist-training tool for melanoma from Hosei University and the other created by extracting features from digital pictures of lesions using a software called Skinseg. We then applied various machine learning techniques on the image feature database using a Python-based tool called Orange. The experiments suggest that among the methods tested, the combination of Bayes machine learning with Hosei image feature extraction is the best method for detecting cancerous moles. Then, using this method, a computer tool was developed to return the probability that an image is cancerous. This is a very practical application as it allows for at-home findings of the probability that a mole is cancerous. This does not replace visits to a doctor, but provides early information that allows people to be proactive in the diagnosis of melanoma cancer.

References

  1. Bosdogianni, Maria Petrou Panagiota. Image Processing: The Fundamentals. New York: John Wiley & Sons, LTD, 1999.
  2. CVIPtools. Southern Illinois University. 7 November 2006.
  3. University of Medicine and Dentistry of New Jersey. March 2009.
  4. “DermWeb: Dull Razor.” UBC Dermatology Department. 21 March 2007. < http://www. dermweb.com/dull_razor/>
  5. Hosei on-line tool. Hosei University, Nov 2009 <https://b0112-web.k.hosei.ac.jp/DermoPerl/>
  6. December 2009.
  7. December 2009.
  8. Russ, John C. The Image Processing Handbook Second Edition. Boca Raton: CRC, 1995.
  9. Orange, Machine Learning tool. Artificial Intelligence Laboratory, University of Ljubljana. 7 Nov 2009. < http://www.ailab.si/orange/>.
  10. Skinseg. Wright State University. 27 Oct 1998.<http://www.cs.wright.edu /agoshtas/ skinseg.html>.
  11. Stanganelli, Ignazio. “Dermoscopy.” Center for Cancer Prevention, Italy. 27 May 2008.
  12. <http://emedicine.medscape.com/article/1130783- overview>
  13. “Understanding Melanoma.” The Skin Cancer Foundation. New York, New York. 13 December 2009. <http://www.skincancer.org/ Melanoma/>.
Download


Paper Citation


in Harvard Style

Raghuvanshi A. and Perkowski M. (2011). IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER . In Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2011) ISBN 978-989-8425-37-9, pages 405-410. DOI: 10.5220/0003173504050410


in Bibtex Style

@conference{biodevices11,
author={Arushi Raghuvanshi and Marek Perkowski},
title={IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER},
booktitle={Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2011)},
year={2011},
pages={405-410},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003173504050410},
isbn={978-989-8425-37-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2011)
TI - IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER
SN - 978-989-8425-37-9
AU - Raghuvanshi A.
AU - Perkowski M.
PY - 2011
SP - 405
EP - 410
DO - 10.5220/0003173504050410