Lung cancer is the leading cause of cancer-related deaths worldwide, underscoring the importance of early detection. While CT is the gold standard for screening, chest X-rays remain vital due to their accessibility, affordability, and lower radiation exposure. This project explores how machine learning can enhance X-ray based diagnosis using synthetic radiographs generated from CT data. Initial work will focus on detecting and localizing lung nodules, but the scope also includes broader directions such as data augmentation, multi-view projections, and comparisons across imaging modalities. The goal is to assess both opportunities and challenges of applying AI in medical imaging and generate insights for future clinical applications.

I am participating in SuperUROP to gain real-world professional research experience and prepare for future projects such as an MEng thesis. My coursework in machine learning and computer vision has equipped me with strong technical foundations, and I am excited to deepen both my technical and communication skills. I look forward to exploring new ideas and contributing to impactful research in this field.