Abstract
As the world population continues to grow, a significant challenge emerges to provide healthcare facilities to an ever-expanding population. Harnessing the power of AI, this challenge could be easily mitigated. One of the solutions to solve the lack of manpower in the field of medical sector is to incorporate AI to help in the decision making of the medical profession. In order to automate the identification of diseases in the field of chest x-rays, this thesis conducts a thorough investigation of image classification and object recognition techniques. With an emphasis on improving diagnostic capabilities, the work makes use of cutting-edge image classification and object identification models, to detect the anomalies in chest X-rays.
The study highlights the results of these experiments and discusses how crucial it is to constantly enhance and improve in order to correctly identify the disease as a whole. Evaluation and visual assessments of model outputs provide a deeper understanding of their effectiveness, laying the groundwork for future advancements in using machine learning for detecting deformities in chest X-rays.
