Prediction of Cervical Cancer using Deep Learning

Teotia, Mohit (2022) Prediction of Cervical Cancer using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Nowadays, in medical fields, identifying and classifying the precancerous and cancerous phases of cervical cancer is a challenging task, which helps to analyse the various cytology slides. Segmenting nuclei and overlapping cells are frequent steps in the processing of cytology pictures. Deep learning is excelling in medical works for the detection and classification which is easing the tedious medical process and is still an open area for research. Significant results have been observed by utilizing the state-of-the-art architecture of deep learning algorithms therefore in this task, three different deep learning approaches are carried out which are Inception V3, Custom Model, and GAN. Here Inception V3 is based on a transfer learning approach while a custom model is made from scratch using convolutional blocks and GAN is a state-of-the-art model. After training these model on the cytology slide data all executed model is tested over the test set and their performance is evaluated on different metrics. After evaluation of the models, the metrics such as Accuracy, Precision, and recall has been determined. After analysing the results, it is observed that the GAN (Generative Adversarial Network) model has surpassed other models and therefore, can be utilized in the classification of Cytology slides into different classes in real-world application.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	13 Mar 2023 16:58
Last Modified:	13 Mar 2023 16:58
URI:	https://norma.ncirl.ie/id/eprint/6325

Actions (login required)

View Item