Breast cancer recognition based on performance evaluation of machine learning algorithms

Breast cancer is the one common cause of death in both developed worlds and most death-causing disease diagnosed among women. <span lang="EN-US">Early recognition this condition can help to minimize rates. The breast problem statement, brief, not reliable for accuracy recognition. They have a high degree classification as well diagnostic capabilities. classifications are normal, benign cancer, malignant cancer. Machine learning (ML) techniques now widely used In paper, some machine technics been investigated diagnose (BC) on magnetic resonance imaging (MRI) images using multi-step processes. first step has take MRI image an input pre-processing image, then use feature extraction by (scale-invariant transform (SIFT), histogram oriented gradient (HOG), local binary patterns (LBP), bag words (BoW), edge-oriented (EOH)). Next we implement classifying algorithms (KNN, decision tree (DT), naïve Bayes, ANN, SVM, RF, AdaBoost), detect classify normal or region purpose datasets like ACRIN-Contralateral-Breast-MRI, dataset) collected our from Erbil Sulaymaniyah hospital results was 91.9%, result ACRIN 97% Cancer 92.3%.</span>