Tools
Tools
Gungor, Urun (2023) Leukemia Cell Classification with using DC-GAN versus 3 Traditional Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration manual)
Download (3MB) | Preview |
Abstract
Leukemia is one of the deadliest cancer types. Therefore, early diagnosis is one of the most critical processes of cancer treatment. Traditional diagnosis of leukemia is a long, costly, and complex process involving the possibility of expert error. Therefore, many researchers focused on this issue with machine learning. But the problem is that the datasets available are imbalanced because of patients’ privacy therefore the classification models are inclined to overfit.
This research focuses on increasing classification model accuracy by solving the imbalanced data problem by using Deep Convolutional Generative Adversarial Network and 3 traditional techniques which are Adaptive Synthetic (ADASYN) sampling approach, Weighted random sampling, and data augmentation. The results of the classification models are compared with their accuracy, data generation speed, and cost.
According to the results fast and high-quality images were generated using DCGAN and the classification model was developed by adding those images. On the other hand, traditional techniques produced low-quality images and did not solve the overfitting problem on the classification model.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Mulwa, Catherine UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RB Pathology R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 22 Nov 2024 11:25 |
| Last Modified: | 22 Nov 2024 11:25 |
| URI: | https://norma.ncirl.ie/id/eprint/7189 |
Actions (login required)
 |
View Item |