Colorectal Cancer Tissue Classification Based on Machine Learning - CORE

Log Date
Dataset Raw


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 image