Breast Cancer Detection using Machine Learning Algorithm (ANN)

Breast Cancer Detection using Machine Learning Algorithm (ANN)

Hiba Masood¹ ,  Mr Vinayak V.  Palmur²

¹ Master of Engineering student, Department of Computer Science and Technology, V.V.P.I.E.T. Solapur,  Maharashtra, India.

² HOD, Department of Computer Science and Engineering, V.V.P.I.E.T. Solapur, Maharashtra, India.

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Breast cancer (BC) is one among the foremost common cancers among women worldwide, representing the bulk of latest cancer cases and cancer-related deaths consistent with global statistics, making it a significant public health problem in today’s society. For identifying and earlier diagnosis of Brest cancer we require oncologists to examine the breast lesions for detection classifying of various stages of cancer. These manual examinations are very time consuming and some time we can say that it may inefficient in many cases. So there is a primary need of creating an efficient method for the diagnoses of those cancerous cells without the human interference with high accuracy.

The early diagnosis of breast cancer (BC) can improve the prognosis and chance of survival significantly, as it can promote timely clinical treatment to patients. Some accurate classification of benign tumors can be preventing patients undergoing long-term   treatments. Thus, the correct diagnosis of breast cancer (BC) and classification of patients into malignant or benign groups is the subject of much research. Because of its unique advantages in critical features detection from complex breast cancer (BC) datasets, machine learning (ML) is widely recognized as the methodology of choice in breast cancer (BC) pattern classification and forecast modeling. In this system, we aim to review machine learning (ML) techniques and their applications in breast cancer (BC) diagnosis and prognosis.

In this research, we uses different image processing techniques for developing the imaging biomarkers through the mammographic analysis and based on Machine Learning algorithms we are aiming to detect breast cancer in early stages to support the diagnosis and get fastest attention seeking of high-risk patients. For achieving this automatic classification of breast cancer based on mammograms, a generalized regression artificial neural network was actually trained and tested to separate the different types of tumors like malignant and benign tumors. And that reaching accuracy near about 95.83%. By using the biomarker and trained neural nets, a specific computer-aided diagnosis system is being designed.

Key Words: breast cancer detection, digital image processing, artificial neural networks, biomarkers, computer-aided diagnosis