Colorectal cancer tissue classification based on machine learning

Min Jen Tsai, Imam Yuadi, Yu Han Tao

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

For digital pathology, automatic recognition of different tissue types in histological images is important for diagnostic assistance and healthcare. Since histological images generally contain more than one tissue type, multi-class texture analysis plays a critical role to solve this problem. This study examines the important statistical features including Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filters, Haralick features, fractal filters, and local binary pattern (LBP) for colorectal cancer tissue identification by using support vector machine (SVM) and decision fusion of feature selection. The average experimental results achieve high identification rate which is significantly superior to the existing known methods. In summary, the proposed method based on machine learning outperforms the techniques described in the literatures and achieve high classification accuracy rate at 93.17% for eight classes and 96.02% for ten classes which demonstrate promising applications for cancer tissue classification of histological images.

Original languageEnglish
Publication statusPublished - 2019
Event23rd Pacific Asia Conference on Information Systems: Secure ICT Platform for the 4th Industrial Revolution, PACIS 2019 - Xi'an, China
Duration: 8 Jul 201912 Jul 2019

Conference

Conference23rd Pacific Asia Conference on Information Systems: Secure ICT Platform for the 4th Industrial Revolution, PACIS 2019
Country/TerritoryChina
CityXi'an
Period8/07/1912/07/19

Keywords

  • Classification
  • Decision Fusion
  • Machine Learning
  • Support Vector Machine

Fingerprint

Dive into the research topics of 'Colorectal cancer tissue classification based on machine learning'. Together they form a unique fingerprint.

Cite this