Fractal analysis in the detection of colonic cancer images

Abdelrahim Nasser Esgiar, Raouf N.G. Naguib, Bayan S. Sharif, Mark K. Bennett, Alan Murray

Research output: Contribution to journalArticlepeer-review

154 Scopus citations

Abstract

The aim of this study was to investigate the value of fractal dimension in separating normal and cancerous images, and to examine the relationship between fractal dimension and traditional texture analysis features. Forty-four normal images and 58 cancer images from sections of the colon were analyzed. A "leave-one-out" analysis approach was used to classify the samples into each group. With fractal analysis there was a highly significant difference between groups (p < 0.0001). Correlation and entropy features showed greater differences between the groups (p < 0.0001). Nevertheless, the addition of fractal analysis to the feature analysis improved the sensitivity from 90% to 95% and specificity from 86% to 93%.

Original languageBritish English
Pages (from-to)54-58
Number of pages5
JournalIEEE Transactions on Information Technology in Biomedicine
Volume6
Issue number1
DOIs
StatePublished - Mar 2002

Keywords

  • Cancer
  • Classification
  • Colon
  • Fractal analysis
  • Image analysis
  • Quantitative pathology
  • Texture

Fingerprint

Dive into the research topics of 'Fractal analysis in the detection of colonic cancer images'. Together they form a unique fingerprint.

Cite this