Logistic Regression Aglorithm For The Screening And Classification Of Breast Cancer: Extraction Of Features From Mammographic Images
This paper focuses on extracting the features of mammographic images for screening and classifying logistic regression and breast cancer. To identify and classify breast cancer, an ML model was employed. In his study, we compared other existing ML models with our models abd also employed the logistic regression (LR). These existing ML models include Wisconsin Breast Cancer Diagnostic (WDBC), Naïve Bayes (NB), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) dataset. There were two stages of performance review in this study: Stage 1: when the WBCD is scaled (feature scale) and Stage 2: when the data set is not scaled. If there is no scaling of the data set characteristics with f1 scores (LR = 97%, SVM = 97%, NB = 95%, MLP = 52%), all the models, excluding MLP, tends to perform excellently well. On the other hand, if the characteristics scale is applied to the data set, all the four models would have f1 scores greater than 90% (SVM = 98%, LR = 97%, NB = 97%, MLP = 97%). There was no change in the f1 score for LR and it used for Binomial Classification because of its low time complexity and simplicity.