Projects

This is for CS6190 probabilistic machine learning project. Here, we have taken a small dataset of medical images (~230) and used two probabilistic approaches, generative adversarial networks (GAN) and variational autoencoder (VAE), to generate more realistic images to increase the number of samples, which play significant roles in deep learning-based methodologies.

We utilized the transfer learning approach to detect abnormalities because of its ability to share knowledge from similar tasks. We used an updated version of a pre-trained model (DenseNet169) to detect abnormalities for five different organs of the upper extremity.