Breast Cancer Classification using Customized ResNet based Convolution Neural Networks

Deep learning is the most frequently used tool in the classification of tumors in medical applications. In recent decades, many research works have been done on the Breast Imaging Reporting & Data System (BI-RADS) atlas based classification of Breast cancer. As reported in the existing research works, training the larger datasets is a challenging task. Therefore, a customized ResNet based Convolution Neural Network (cRN-CNN) with batch normalization is proposed in this manuscript for addressing the above mentioned issue. The proposed cRN-CNN method has the advantage of faster training and computationally effective for the classification of BIRADS atlas based MRI breast cancer records, where the proposed model's performance is superior compared to the conventional CNN model. The extensive experiments performed on the Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) dataset confirmed that the proposed cRN-CNN method achieved better classification results than the existing methods. In the proposed model, the deformation technique based on elastic deformation is also applied to increase the training size of data that helps to improve the outcomes of prediction up-to 99.80%, because of the efficient strategy of batch normalization as customization and elastic deformation.

I. Introduction

Al-Zn-Mg alloys with high mechanical strengths include Breast cancer is one of the most common types of cancer among females and an estimate of 268,600 new breast cancer patients have been diagnosed in the year 2019 [1]. On average 1 among 39 of the females who have breast cancer will die which is equals about 3% among diagnosed and 13% of diagnosed females who are suffering from an invasive type of breast cancer in their lifetime which equals nearly 1 out of 8 people. Breast cancer diagnosis concludes that the causes of death are from other sources and have an average risk than the lifetime risk of breast cancer. Screening mammography is one of the efficient and widely used methods for the detection of breast cancer [2]. There are two views included in the screening mammography of each breast namely from top to bottom view called Cranio Caudal (CC) and an angle based side view called Medio Lateral Obligue (MLO). According to this visual examination, the radiologists will look for the symptoms of mammograms in the MRI images based on the BIRADS Atlas for mammogram descriptors [3] [4]. Some of the major descriptors namely calcifications, masses and architectural distortions are the common symptoms of breast cancer which are taken into account to standardize the terminology of the mammogram report and its corresponding evaluation and actions are to be taken. Radiologists prefer regular follow check-up or short-term check- ups based on the concern level of the cancer abnormality in the patient.