Chest X-ray Disease Diagnosis with Deep Convolutional Neural Networks

I completed this project in conjunction with my graduate coursework as a student in CSE 6250: Big Data Analytics for Healthcare. I worked with my classmates, Charity Hilton and Kausar Mukadam, to develop a PyTorch-based pipeline to use CNNs to detect and localize the 14 thoracic pathologies present in the NIH Chest X-ray dataset.

Our final paper outlines our approach and presents our empirical results.