Prediction Analysis of Cancer Cells Using ML Classification Algorithms
Keywords:Weka explorer, dataset, Threshold segmentation, ML Classifiers.
Background: Breast Cancer is one of the most occurring cancers among all the diseases in medical science.
About 1 in 8 women are suffering from breast cancer in their lifetime. In 2020, an estimated 276,480 new
cases of invasive breast cancer are expected to be diagnosed in women along with 48,530 new cases of
non-invasive breast cancer. Apart from women, men are also suffering from breast cancer, but the rate of
occurrence is low in men.
Aim: To classify the breast cancer cells from original mammographic images using processing steps of
Gaussian smoothing, Threshold segmentation, Feature Extraction.
Methodology: Breast cancer datasets are collected and preprocessed using attributes-like Menopause,
Node-Capes, INV Nodes, Irradiate and Class. Three Machine Learning classifiers such as Bagging, Naive
Bayes, and Naive Bayes Multinomial are applied for the classification analysis.
Results: Bagging classifier gives efficiency in the range of 77-86% when we consider Menopause, NodeCapes and Irradiate attributes and Naive Bayes classifier gives efficiency in the range of 71-78% for INVNodes and Class attributes.
Conclusion: It is observed that the bagging classifier gives best efficiency when we consider Menopause,
Node-Capes and Irradiate attributes and Naive Bayes is best suits for INV-Nodes and Class attributes.
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.