Date of Award




Document Type

Master's Thesis

Degree Name

Master of Science (MS)


Department of Computer Science

Content Description

1 online resource (iii, 42 pages) : color illustrations.

Dissertation/Thesis Chair

Siwei Lyu

Committee Members

Siwei Lyu


Artificial Intelligence, Chest X-ray, Computer Vision, Deep Learning, Image Processing, Medical Imaging, Chest, Diagnostic imaging, Radiography, Medical, Machine learning, Artificial intelligence

Subject Categories

Computer Engineering | Computer Sciences


Deep Learning is the new state-of-the-art technology in Image Processing. We applied Deep Learning techniques for identification of diseases from Radiographs made publicly available by NIH. We applied some Feature Engineering approach to augment the data from Anterior-Posterior position to Posterior-Anterior position and vice-versa for all the diseases, at the same point we suppressed ‘No Finding’ radiographs which contributed to more than 50% (approximately 60,000) of the dataset to top 1000 images. We also prepared a model by adding a huge amount of noise to the augmented data, which if need be can be deployed at rural locations which lack proper infrastructure for radiograph imaging. For optimization we used the AMS Grad version as proposed by Reddi et al. [1] of Google, New York, of the Adam-Optimizer that shows better learning and convergence to the optimal solution. In the second approach, we try to use the augmented data without a lot of noise to make a model for disease classification. Apart from that we apply Gradient-based Class Activation maps to localize the detected regions for better diagnosis and in helping Radiologists in achieving concurrence.