DESIGN AND IMPLEMENTATION OF DEEP LEARNING BASED CERVICAL CANCER DISEASE DETECTION AND CLASSIFICATION MODEL
ABSRACT
Cervical 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 the 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 occurs 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. A sample of cervical cancer images was taken from Bethazeta Hospital in Addis Ababa, Ethiopia, and some of the data was added from the public dataset. It is proposed to detect and classify cervical cancer using a deep learning model. The proposed approach has two main phases. In the first phase the designed model is trained and tested by the collected dataset and the data is classified using different neural networks. Finally, the deep learning model that can detect and classify the given image into 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, a data augmentation technique is used to generate more images to fit the proposed model using 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.
DESIGN AND IMPLEMENTATION OF DEEP LEARNING-BASED CERVICAL CANCER DISEASE DETECTION AND CLASSIFICATION MODEL, GET MORE COMPUTER SCIENCE PROJECT TOPICS AND MATERIALS