Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/437831
Title: | Automated algorithm development and analysis of PAP smear images to diagnose cervical cancer |
Researcher: | Gnanasaravanan, S |
Guide(s): | Somasundaram, D |
Keywords: | Engineering and Technology Engineering Engineering Biomedical Cervical cancer Diagnostic Papsmear test |
University: | Anna University |
Completed Date: | 2022 |
Abstract: | Cervical cancer is the fourth most common cancer in women. In 2018, an estimated 570000 women were diagnosed with cervical cancer worldwide and about 311000 women died from the disease. This will be treated as a national public issue in our country, more over one fourth of the reports registered in India compared with worldwide. International Statistics shown that, approximately 1 in 53 women gets infected due to cervical cancer in India. Majorly in Mizoram state. The screening of the cervical cancer plays a major role in diagnostic of cancer in early stages for treatment. Still analysing early screening of cervical cancer cells is a challenging task for researchers in and around the world. Many research works focused on the segmentation of the cervical cancer cells. cervical cancer is analysed using the papsmear test. Researchers proposed many invasive and non-invasive methods for the analysis of the cervical cancer cells. In the earlier research work, many algorithms failed to detect the papsmear cells due to the non-rigid structure and overlapping the papsmear cells. For the analysis of the cervical cancer improved methods are necessary to improve the accuracy in the segmentation and the classification of papsmear cells. In clinical analysis, human intervention causes errors and the time consumption is high for analysing these cells. To overcome these problems, semi-automated and automated methods are proposed to diagnose the cervical cancer cells. newlineDeep learning approaches inspire distinct features and powerful classifiers for many computer vision applications, proposing novel deep learning model to handle in the wild is vital. As a result, the remaining work contributions are based on the development of deep learning model based on Convolutional Neural Networks (CNN). newline |
Pagination: | xvi,140p. |
URI: | http://hdl.handle.net/10603/437831 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 69.83 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 3.05 MB | Adobe PDF | View/Open | |
03_content.pdf | 237.62 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 55.71 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 428.97 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 184.86 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 1.41 MB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 1.55 MB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 930.98 kB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 283.89 kB | Adobe PDF | View/Open | |
11_annexures.pdf | 152.07 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 69.85 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: