Date of Award
2-7-2023
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Information Science
First Advisor
Daniel Berleant
Abstract
The purpose of this research is to apply both computer vision and natural language processing techniques for visual question answering (VQA) on a medical image dataset. Deep learning and machine learning libraries were used in the research. The research includes understanding key achievements in the field of visual question answering, identifying techniques applied in general images and applying them along with new techniques to medical images. There are many more articles explaining the application of visual question answering to general images than on applying VQA specifically to medical images. In this research, I initially developed a model of VQA that performs with reasonable accuracy to predict answers to questions about medical images, continued to develop better models focused on medical images and finally developed VQA models that performed even better at answering questions on the images. Studying diagnostic images often takes significant amounts of time by experienced physicians. We are in times when AI has become increasingly applied around us and my research is consequently focused on moving toward the goal of achieving AI based decisions to healthcare to improve patient care. Studies show that AI could support efficiency of doctors at diagnosing various diseases from medical images, and VQA is one of the growing areas of research that contribute to that goal.
Recommended Citation
Kodali, Venkat Ramana Kodali, "Deep Learning Architectures for Visual Question Answering on Medical Images" (2023). Theses and Dissertations. 1115.
https://research.ualr.edu/etd/1115
