Abstract: According to incidence statistics, colon cancer is one of the most common types of cancer in the world. The correct diagnosis of this lesion will provide cancer patients with the most appropriate treatment. Diagnosis is made through visual analysis of tissue samples by a pathologist. This analysis is affected by intra-pathological and inter-pathological variation, and is also a complex and time-consuming task. In order to solve these problems, imaging techniques have been developed to be applied to histological images obtained by digitizing tissue samples. To this end, characterization and classification techniques are being explored to help pathologists and achieve faster and more objective diagnostic determinations. Therefore, this paper proposes a method that combines multi-dimensional fractal technology, curvature transformation and Haralik descriptors for research and captains. Detect colon cancer that has not been studied in the literature. The proposed method considers feature selection methods and various classification methods.
Keywords: colorectal cancer, feature associations, multiresolution features, fractal techniques, curvelet transforms, haralick descriptors.
|
DOI:
10.17148/IJARCCE.2021.106120
