3 Analysis of divergence aspects of breast in breast cancer patients that change due to COVID-19
Shawni Dutta, Samir Kumar Bandyopadhyay · 2021
Breast cancer develops from cells lining the milk ducts and slowly grows into a lump or a tumor. Breast cancer may be invasive or noninvasive. Invasive cancer spreads from the milk duct or lobule to other tissues in the breast, whereas noninvasive ones lack the ability to invade other breast tissues. Noninvasive breast cancer is called in situ and may remain inactive for the entire lifetime. Due to the heterogeneity nature of breast, density as well as mass is variable in size and shape. This chapter analyzes two datasets. The first dataset is Breast Cancer Wisconsin (Diagnostic) dataset from UCI machine learning repository during COVID-19 and another image dataset collected from different hospitals of West Bengal, India. This chapter proposed techniques for detection of both image dataset and nonimage dataset. So it is a unique approach for the analysis of breast cancer. The chapter proposed three approaches for increasing the efficiency of the detection. The first approach attempts to utilize gradient boosting algorithm to be applied on Breast Cancer on Wisconsin (Diagnostic) dataset and obtain prediction results. The second approach is proposed using stacked gated recurrent unit-long short-term memory-bidirectional recurrent neural network that accepts health records of a patient for determining the possibility of being affected by breast cancer. This approach also used the same dataset, that is, Wisconsin (Diagnostic) dataset is collected from UCI as of the first approach. The third dataset is collected from different hospitals and the third approach utilizes this dataset for the detection of breast cancer. All collected magnetic resonance images from hospital reports are diagnosed by radiologists of the respective hospitals. All the three implemented methods have shown promising results in terms of breast cancer disease detection.