Tools
Tools
Anota, Olawaunmi Sunday (2021) Comparative Analysis of Deep Learning and Machine Learning Techniques in Predicting Radiation Pneumonitis. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
Radiation pneumonitis (RP) is a form of lung damage induced by an irritant that develops when patients with Non-small Lung Cancer (NSCLC) get radiation therapy. Due to the complexity of computed tomography (CT) scan images, different transformations, augmentation, and normalization approaches are used in the data preparation. The goal of this research is to compare the performance of deep learning techniques with that of machine learning in predicting radiation pneumonitis in patients with Non-Small Cell Lung Cancer. The Cancer Imaging Archive (TCIA) 4D-Lung dataset containing 1699 images was adopted. In this study, three classification models were implemented- VGG16, Capsule Neural Network (CapsuleNet) and Support Vector Machine (SVM) based on deep learning and machine learning with the goal of creating a binary classifier that can predict radiation pneumonitis in Non-Small Cell Lung Cancer patients and the obtained outcome was compared. The Sensitivity and Specificity evaluation metrics of all the implemented classifier models are obtained in this study. To increase models performance, several parameter tuning was employed. From the implementation of models, it is shown that VGG16 had the best performance output of sensitivity 100% and specificity 95%.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software R Medicine > Healthcare Industry |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Clara Chan |
| Date Deposited: | 10 Nov 2021 16:10 |
| Last Modified: | 10 Nov 2021 16:10 |
| URI: | https://norma.ncirl.ie/id/eprint/5132 |
Actions (login required)
 |
View Item |