Mohan, Meenu (2024) Medical Diagnosis: AI-Driven Disease Exposing Using Images. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
The research being investigated looks into the use of AI in health evaluation, particularly for identifying covid from X-rays and cancer from CT images. I created an accurate diagnosis system using advanced deep learning techniques, including transfer learning with VGG16 architecture and explainable AI methods like GradCAM technology and SHAP. This study addresses two main questions:
1) Can AI-based X-ray detection outperform RT-PCR for COVID 19 detection?
2) Can the AI system accurately detect early-stage chest cancer compared to skilled radiologists?
Research results show that based on artificial intelligence approaches may enhance diagnostic accuracy and efficiency in healthcare image evaluation, potentially leading to previous disease detection and improved patient outcomes.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Raj, Kislay 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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence R Medicine > Diseases > Outbreaks of disease > Epidemics > COVID-19 Pandemic, 2020- R Medicine > Healthcare Industry H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics |
Divisions: | School of Computing > Master of Science in Artificial Intelligence |
Depositing User: | Ciara O'Brien |
Date Deposited: | 18 Jun 2025 14:06 |
Last Modified: | 18 Jun 2025 14:06 |
URI: | https://norma.ncirl.ie/id/eprint/7920 |
Actions (login required)
![]() |
View Item |