Tools
Tools
Kumar, Ayush (2023) Analysing the Impact of Deep Learning and Data Augmentation on Medical Image Classification. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Computer vision techniques are implemented and utilized in different fields. In large laboratories, medical image classification plays a pivotal role in the diagnosis of diseases. In this research, computational power is harnessed to identify patients suffering from pneumonia using images of frontal chest X-rays as dataset for deep learning. Pneumonia is a condition in which lung air sacks are infected by bacteria or viruses. Pneumonia can be diagnosed in any age group but it is most common in young children and elderly people. Deep learning convolution neural network(CNN) models implemented in research experiment are ResNet, VGG, EfficientNet, GoogleNet and DenseNet for medical image classification. In the research experiment novel approach is implemented to conduct a comprehensive investigation of the influence of different deep learning and data augmentation techniques on all five distinct CNN models. The research experiment is conducted in two different phases, phase one models are implemented without data augmentation to systematically test multiple hyperparameters and in phase two, the optimal test case scenario of phase one is utilized for the implementation of data augmentation techniques. The assessment of these models in research experiment involves evaluation metrics like accuracy, recall, precision and loss. The analysis of these performance metrics of all distinct models is conducted with the intention of determining the optimal scenario.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Yaqoob, Abid UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 15 May 2025 16:05 |
| Last Modified: | 15 May 2025 16:05 |
| URI: | https://norma.ncirl.ie/id/eprint/7556 |
Actions (login required)
 |
View Item |