İleri Mühendislik Çalışmaları ve Teknolojileri Dergisi

Yazarlar: Elif ÖZTAD

Konular:Mühendislik

Anahtar Kelimeler:Breast cancer,Neural networks,Deep learning,Classification

Özet: Breast cancer is caused by the breakdown of some cells that multiply and often form a mass called a tumor. Tumors can be benign (not cancerous) or malignant (cancerous). Tests such as MRI (magnetic resonance imaging), mammogram, ultrasound, and biopsy are used to diagnose common breast cancer. Since there are two different labels in the data, the estimate is divided into two categories (benign or malignant). In machine learning, this is defined as a classification problem. This study aims to classify whether breast cancer is benign or malignant and predict the relapse and relapse of malignant cases after a certain period of time. The methodology used includes the classification model and neural network methods. Python modules are used to import external datasets in order to grasp the data well and to think about how to handle the data in different ways. For this purpose, basic concepts of machine learning are applied from the dataset and the results are evaluated according to the dataset. Therefore, neural network methods and classification methods are compared with each other to achieve a high accuracy in breast cancer estimation.

---