Heterogeneity Aspects of Breast for Breast Cancer Patients Change due to COVID-19

Breast cancer develops from cells lining the milk ducts and slowly grows into a lump or a tumour. Breast cancer may be invasive or non-invasive. Invasive cancer spreads from the milk duct or lobule to other tissues in the breast, whereas, non-invasive ones lack the ability to invade other breast tissues. Non-invasive breast cancer is called in situ and may remain inactive for entire lifetime. Due to heterogeneity nature of breast, density as well as masses is variable in size and shape. A dataset of 18056 patients are collected from 20 Government Hospitals and 50 Private Hospitals in West Bengal before COVID-19 and after COVID-19. The classification of patients are made on three classes- Normal, Sign of Abnormality and Abnormality. The reports of MRIs of patients in January 2020 and February 2020 are collected from different hospitals. It is treated as dataset before COVID-19 . MRIS of patients in April 2020 and May 2020 are dataset during COVID-19. The entire datasets are accumulated for testing of any change in patients MRIS after the official announcement of new virus COVID-19 in March 2020. The aim of the paper is to make a comparison of any change in size and shape of masses of MRIs of patients before and after COVId-19. All collected MRIs reports are diagnosed by radiologists of hospitals.


Introduction
Breast is referred as mammary gland in scientific term. With reference to the Merriam-Webster dictionary the Breast is either of the pair of mammary glands extending from the front of the chest in pubescent and adult females of humans and some other mammals. It is also either of the analogous but rudimentary organs of the male chest especially when enlarged [1].
Several researches have shown that study of heterogeneity in mammogram may save lives and increases treatment options [2]. Breast cancer, a malignant tumour developed from breast cells is considered to be one of the major causes for the increase in mortality among women, especially in developed and developing countries [3].
Most masses in breast are benign and do not grow uncontrollably or spread. Some breast cancers are called in situ because they are confined within the ducts (ductal carcinoma in situ) or lobules (lobular carcinoma in situ) of the breast. Nearly all cancers at this stage can be cured. Lobular carcinoma in situ (also known as lobular neoplasia) is an indicator of increased risk for developing invasive cancer in either breast.
The breast cancer diagnosis process during COVID-19 needs attention whether shape of the abnormal masses is changed or not. If there is any change then it requires immediate attention for treatment.
It was mentioned in the abstract that a study over 50 patients has been made to identify any changes before or after COVID-19. This paper detects change of masses and their shapes.

Related Works
A search on internet has been made relating to such study but nothing is found. So the proposed method for observing the changes in mass in breast is compared with the existing methods for detection of breast cancer.
Researchers proposed Computer Aided Diagnosis (CAD) for detection of abnormal masses [4].
The recent studies show that the majority of clinical tests including digital mammography and biopsies on patients performed manually. So it is wastage of valuable time of medical practitioners, if it is found benign. At the same time the possibility of false detection is increasing in the manual system. The efficiency of CAD system can screen the benign cases easily and assist the experts in terms of qualitative and quantitative precision. Thus CAD has become a part of routine clinical detection of breast cancer on mammograms at many mass screening program and hospitals [5].
CAD system starts from image preparation, pre-processing, features extraction, registration, segmentation and detection of abnormal mass in breast, if present. The process of segmentation of the part of the affected breast is most important. Segmentation is related with the pectoral muscle suppression, edge detection, determination of Region of Interest (ROI), anatomical segmentation, segmentation of abnormalities like mass and micro-calcification.
The preparation, pre-processing and features extraction are normally made for making the image in such a way that no unwanted parts are seen in the images which are the input to next steps to detect correctly the abnormalities in the next phases.
Researchers reviewed several well accepted mammogram image registration techniques and classified them according to their functionality. The primary objective of registration is to align one image to another by finding the optimal transformation or mapping function. It involves a searching plan to enhance a similarity measure. This similarity measure is determined using certain characteristics of the images. Feature space, transformation, similarity measure and search strategy constitute a typical registration framework in automated image processing systems like CAD. The enhancement of mammogram is also performed by intensity and contrast manipulation, noise reduction, background removal, edge sharpening, filtering etc.

Data Set
Dataset is a collection of similar and related data stored for processing. Further this can be defined as a collection of data that contains individual data units organized in a specific format.
A data set generally contains a collection of many types of data. Medical dataset can be defined as a collection of pieces of information, especially those that are part of a collection to be used for the the diagnosis of diseases. In this paper data set, containing mammogram images from hospitals along with their reports, are stored for the same selected patients before and after COVID-19. The shapes of masses of patients before COVID-19 are analyzed since these data are compared with the shapes of masses of patients after COVID-19. These data are obtained from different Government hospitals as well as from Private Hospitals. Generally, data set before COVID-19 are normally stored in the hospitals along with details of patient information as well as their diagnostic reports. The radiologist has provided all relevant information regarding any abnormality present. The images are classified into normal, tends to be sign of breast cancer and also patients who already detected as breast cancer patients. These detections are based on the diagnosis of radiologists. The mass can also be classified according to the type of mass present such as well-defined/circumscribed masses, spiculated masses, ill-defined masses etc. In this paper the main consideration is to detect any change of shape in masses and also normal/ tends to breast cancer patients may have sign of abnormal mass in their MRI.

Proposed Method
The objective of the paper is to find out the presence of abnormal mass created in normal patients and as well as in tends to breast cancer patients. Also if there is any change of masses in confirmed breast cancer patients due to COVID-19 then it has to be specified for immediate treatment.
The masses i.e. tissues which are absent in normal breast anatomy is called abnormal masses.  Figure 1 shows the result of a MRI of a patient (tends to be a breast cancer patient) after using the approach from the set of MRIs images of patients before COVID-19. It is shown in figure 1.