Classification for Urinary Bladder Epithelial Cancer Cell Basing on Random Forest Algorithm
Yeyu Huang1, Yeen Huang21Department of Information Science and Technology, Jinan University, Guangzhou, China; School of Chemistry, Sun Yat-sen University, Guangzhou, China, 2Department of Epidemiology and BioStatistics, Sun Yat-sen University, Guangzhou, China,
Objectives: Classification diagnosis of urinary bladder epithelial cancer cell was strongly influenced by subjective judgments, which is made by pathologists, resulting in the presence of high false positive rate and false negative rate of diagnosis. Therefore, Random Forest was performed to diagnosis and classification urinary bladder epithelial cancer cell for exploring the feasibility and application value of its method. Methods: A total number of 258 urinary bladder epithelial cancer samples were collected and diagnosed. Morphological and colorimetric features of samples were evaluated by the application of ImageJ. Random Forest algorithm, intergrated with Weka 3.6.6 was performed to training samples and modeling. Test accuracy was calculated by 10-fold Cross-validation. Results: The overall classification accuracy performed by random forest was 98.13% between normal group and lesions group, 98.95% between urothelium dysplastic exfoliated cells and bladder urothelial cancer exfoliated cells. For the classification diagnosis of urinary bladder epithelial cancer cell, the classification diagnostic effect performed by Random Forest was the best while distinguishing lesions cells from normal cells, and bladder urothelial cancer exfoliated cells from urothelium dysplastic exfoliated cells, respectively. Conclusion: It was indicated that Random Forest can be considered as an effective classification method to classified urinary bladder epithelial cancer cells. Keywords: Colorimetric parameters, image analysis, morphological parameters, random forest algorithm, urinary bladder epithelial cancer
Cite This Article
Huang Y, Huang Y. Classification for Urinary Bladder Epithelial Cancer Cell Basing on Random Forest Algorithm. EJMO. 2020; 4(1): 84-88
Corresponding Author: Yeen Huang