Texture analysis for colorectal tumour biopsies using multispectral imagery

R. Peyret, Ahmed Bouridane, Somaya Al-Maadeed, Suchithra Kunhoth, Fouad Khelifi

Research output: Contribution to conferencePaperpeer-review

13 Citations (Scopus)

Abstract

Colorectal cancer is one of the most common cancers in the world. As part of its diagnosis, a histological analysis is often run on biopsy samples. Multispecral imagery taken from cancer tissues can be useful to capture more meaningful features. However, the resulting data is usually very large having a large number of varying feature types. This papers aims to investigate and compare the performances of multispectral imagery taken from colorectal biopsies using different techniques for texture feature extraction inclduing local binary patterns, Haraclick features and local intensity order patterns. Various classifiers such as Support Vector Machine and Random Forest are also investigated. The results show the superiority of multispectral imaging over the classical panchromatic approach. In the multispectral imagery's analysis, the local binary patterns combined with Support Vector Machine classifier gives very good results achieving an accuracy of 91.3%.
Original languageEnglish
DOIs
Publication statusPublished - Aug 2015
Event37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015 ) - Milan
Duration: 1 Aug 2015 → …

Conference

Conference37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015 )
Period1/08/15 → …

Fingerprint

Dive into the research topics of 'Texture analysis for colorectal tumour biopsies using multispectral imagery'. Together they form a unique fingerprint.

Cite this