Skip navigation
st. Mary's University Institutional Repository St. Mary's University Institutional Repository

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/7508
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGebeyehu, Nunu-
dc.date.accessioned2023-03-07T12:22:56Z-
dc.date.available2023-03-07T12:22:56Z-
dc.date.issued2023-01-
dc.identifier.uri.-
dc.identifier.urihttp://hdl.handle.net/123456789/7508-
dc.description.abstractCervical cancer is the second most common and second most deadly cancer in Ethiopia. The disease's incidence and prevalence are increasing over time due to population growth and aging, as well as an increase in the prevalence of well-established risk factors. Cervical cancer knowledge and awareness among Ethiopian women is quite low. It is the most deadly disease caused by the uncontrolled growth of body cells, accounting for approximately 9.6 million deaths each year in world. In women, abnormal cell growth can affect various body organs such as the breast and the cervix. 85-90 percent of the fatality rate of cervical cancer occur in low and middle-income countries due to a lack of public awareness about the disease's causes and consequences. As a result, it is necessary to create a cervical cancer detection and classification model using deep learning techniques to assist experts. Sample of cervical cancer images were taken from Bethazeta Hospital in Addis Ababa, Ethiopia and some of data was added from public dataset. It is proposed to detect and classify cervical cancer using deep learning model. The proposed approach has two main phases. In first phase the designed model is trained and tested by collected dataset and the data is classified using different neural network. Finally, the deep learning model that can detect and classify the given image in to Type_1, Type_2 and Type_3 is done. The dataset contains 2085 original cervical cancer images. From this, 80% of the images are used for training and the rest for testing the model. During training, data augmentation technique is used to generate more images to fit the proposed model using by Keras libraries. The Convolutional Neural Network and Hybrid of Convolutional Neural Network and Long Short Term Memory model can successfully detect and classify the given image with an accuracy of 99.04% and 98.72% respectively.en_US
dc.language.isoenen_US
dc.publisherST. MARY’S UNIVERSITYen_US
dc.subjectDeep Learning, Cervical Cancer, Convolutional Neural Network, Long Short Term Memory, Classification, Detection.en_US
dc.titleDEEP LEARNING BASED CERVICAL CANCER DISEASE DETECTION AND CLASSIFICATION MODELen_US
dc.typeThesisen_US
Appears in Collections:Master of computer science

Files in This Item:
File Description SizeFormat 
Nunu the last thesis report - Copy.pdf1.73 MBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.