Design and development of deep learning algorithm with convolutional neural networks for breast cancer classification

• Published in: International Journal of Research in Engineering and Innovation Vol. 6; no. 3; pp. 142 - 150
• Main Authors: Singh, Rajesh, Patil, Mamata Sanjay, Koli, Anushri S., Tembhe, Harshad R., Shrinagarwar, Vaibhav P.
• Format: Journal Article
• Language: English
• Published: 2022
• ISSN: 2456-6934; 2456-6934
• DOI: 10.36037/IJREI.2022.6301

Breast cancer is one of the primary causes of cancer death among women worldwide. Mammography and ultrasound are used as radiological methods for the early detection of breast cancer in women. Generally, Breast Cancer Detection is done subjectively by expert Radiologists. Still, the radiologist has high inter-observer variability as it is challenging to detect breast cancer tumors in high-density breasts. Many Computers Aided Diagnosis (CAD) systems developed in the past, but accuracy and precision are not up to the mark and are not used in clinical practice. The histopathologist is not well-trained, so it leads to incorrect analysis. With image processing and machine learning, there is an interest in changing dependable pattern acknowledgment-based systems to improve the excellence of diagnosis. Still, there is continuous social demand to design and develop a CAD system for Breast Cancer Detection, which will assist radiologists in making accurate decisions as a second opinion. This paper will use the deep learning model to address the above-discussed issue to efficiently assist in the automatic Breast Cancer Detection for clinical practice. The objective is to analyze existing algorithms and study different pre-processing classification algorithms for mammographic breast cancer classification compared with the state-of-the art methods reported in the literature survey section.