Classification of Breast Ultrasound Images: An Analysis Using Machine Intelligent Based Approach

Purpose: Breast Cancer (BC) is considered as one of the most dangerous diseases, especially in women. The survivability patient a challenging task if breast cancer severe stage. It very much essential for early classification ultrasound images (BUIs) into several categories such benign (BN), malignant (MG) and normal (NL), etc. so that preventive measures can be taken accordingly at earliest. Approach: In this work, machine intelligent (MI) based approach proposed BUIs BN, MG NL types. focused on stacking (hybridization) Logistic Regression (LRG), Support Vector Machine (SVMN), Random Forest (RFS) Neural Network (NNT) methods to carry out classification. method compared with other learning (ML) LRG, SVMN, RFS, NNT, Decision Tree (DTR), AdaBoost (ADB), Naïve Bayes (NBY), K-Nearest Neighbor (KNNH) Stochastic Gradient Descent (SGDC) performance analysis. Result: ML have been implemented using Python Orange 3.26.0. 750 TLDIs having 250 numbers each type are from Kaggle source. all assessed parameters accuracy (CA), F1, Precision (PR) Recall (RC). From results, it found capable providing better results terms CA, PR RC DTR, ADB, NBY, KNNH SGD. Originality: MI by focusing RFS NNT types NL. performs SGDC methods. Paper Type: Conceptual Research.