A MOBILE BASED CERVICAL CANCER DETECTION USING NEURAL NETWORK

ABSTRACT

Cervical cancer, also known as uterine cancer, is considered as the fourth most common disease  worldwide and has increased the death rate as hasty level. Most of the cervix cancer cases are preventable if diagnosed in early stages, by routine screening. This project focuses on A mobile based cervical cancer detection using neural network. The analysis of a digital image of the cervix; captured with a low-level camera, under a contrast agent: the visual inspection with acetic acid (VIA) is known as one of the reference methods to detect cervical cancer were taken into consideration. Gaussian and mean filter techniques were used to remove the speckles. A segmentation algorithm was used to isolate the region of interest (ROI) from the image. Additionally a canny edge detection algorithm was used to find edges. Furthermore, quantification and classification of the images were done. An Android application was used to integrate all the above. This allows usage in rural settings. The results obtained were quite satisfactory (Specificity 79% and Sensitivity of 83%).

CHAPTER ONE

INTRODUCTION

• Background to the Study

Most of the deaths are occurred around the world based on cancer. Breast and Cervical cancers are the most live killing diseases of women patients in and around the world (Susan et al., 2018). Breast cancer is occurred in women patient externally and it can be detected by scanning the breast region. The women patients who are affected by breast cancer, can check themselves, hence it can be detected in women patients at an earlier manner as depicted in Kwok et al., (2011). The cervical cancer is also occurred in the women patient internally and it can be detected by scanning the internal region of the vagina. Human Papillomavirus (HPV) virus (NCCC, 2010) is the main cause of cervical cancer formation in women patients. This virus initially affects the cells in the cervical region of the women patients and spreads over the entire region of the cervix (Robbins et al., 2009).The women patients who are affected by cervical cancer, unable to check themselves, hence it cannot be detected at an earlier stage. Hence, death ratio of the women patients is high due to cervical cancer. The cells inside the cervix are categorized into squamous cells and glandular cells as stated in Mouelhi et al., (2013). Squamous cell carcinoma is the type of cervical cancer which is occurred in women patients due to infection of squamous cells in cervix region and adenocarcinoma, which is another type of cervical cancer which is occurred in the women patients due to the infection of glandular cells in cervix region (American Cancer Society, 2011). Squamous cell carcinoma affects the outer region of the cervix only and adenocarcinoma affects the inner region of the cervix. The cervical cancer in women can be screened by either Pap smear test or Cervicogram test (Katz et al., 2010)

The main reason for the death due to cervical cancer in women patients is that it cannot be detected at an earlier stage and the patients can not receive any symptoms until they reach nal stage of the cancer. The death ratio of the women patients can be reduced if it is detected at an earlier stage only. Hence, this paper proposes a methodology to detect the cervical cancer at an earlier stage to prevent death of women patients. Conventional methods are based on human experts and it is time consuming process. Further, it is not suitable for the developing countries having large population due to the lack of trained experts or  radiologist  in  this  eld  (Susan  et  al.,  2018).  Hence, there is a requirement of fully automated methodology for cervical cancer detection. The cervix region, which is the main region of interest within the cervigram, is located in the central part of the image (Song et al. 2015; Sulaimana et al., 2011).

• Statement of the Problem

Cervical cancer is a global health problem, especially in the developing countries, including Nigeria. It is a disease characterized by uncontrollable growth of the cells of the cervix and symptoms do not present early thereby making the sufferer ignorant of the presence of such condition. However, lack of efficient diagnosis system is hampering the fight against Cervical cancer in Nigeria . The death ratio of the women patients can be reduced if it is detected at an earlier stage only. Hence, this paper proposes a methodology to detect the cervical cancer at an earlier stage to prevent death of women patients.

1.3 Aims And Objectives Of The Study

The aim of this study is on a  Mobile Based Cervical Cancer Detection Using Neural Network.

The following are the specific objectives;

1. To design an automatic system for the detection of cervical Cancer
2. To design a mobile based system suitable only for high resolution cervical images.
3. To develop an automated system that enable proficient and effective detection of Cervical Cancer that can be implemented for commercial purpose.

1.4 Scope of the Study

The scope of the study is on Mobile Based Cervical Cancer Detection Using Neural Network.

 1.5 Significance of the study

Using a mobile based cervical cancer detection system for early diagnosis is the key to better treatment outcome of cervical cancer. However in the developing countries, Nigeria inclusive, this effective tool of early detection still seems to be a mirage. Health care professionals are important predictors of the use of cervical cancer screening (Nwobodo&Malami, 2005). Being knowledgeable about cervical screening for cancer serves as an advantage thus they serve as effective agents in creating awareness about screening, its usefulness in prevention and better treatment outcome of cervical cancer.

This study will help in identifying the level of health workers commitment to utilization of cytology services which in turn will motivate uptake of screening among women folk and as such reduce deaths from cervical cancer.

The findings will also inform the policy makers especially in the health sector to accord high priority to cervical screening, make policies, create programmes and allocate sufficient funds to encourage procurement of vaccines, screening equipment, promote follow-up of results of screening, early diagnosis and treatment of identified cases. These programmes of activities will also form part of the health care service of health institution and thus reduce mortality from cervical cancer. Also, training institutions for health workers should incorporate practical skills on cervical screening in their training centre.

1.6 Limitations of the Study

Financial Constraints: The researcher was with limited funds and cannot visit all the areas to get responses from respondents but was able to get good information concerning the research topic.

Time Constraints: The researcher was involved in other departmental activities like seminars, attendance of lectures et.c which limited  time allocated  for the research but the researcher was able to meet up with the time assigned for the completion of the research work.

Related Project Topics :