Total intracranial volume (TIV) is the volume enclosed inside the cranium, inclusive of the meninges and the brain. TIV is extensively used to correct variations in inter-subject head size for the evaluation of neurodegen- erative diseases. In this work, we present an automatic method to generate a TIV mask from MR images while synthesizing a CT image to be used in subsequent analysis. In addition, we propose an alternative way to obtain ground truth TIV masks using a semi-manual approach, which results in significant time savings. We train a conditional generative adversarial network (cGAN) using 2D MR slices to realize our tasks. The quantitative evaluation showed that the model was able to synthesize CT and generate TIV masks that closely approximate the reference images. This study also provides a comparison of the described method against skull stripping tools that output a mask enclosing the cranial volume, using MRI scan. In particular, highlighting the deficiencies in using such tools to approximate the volume using MRI scan.

Medical Image Analysis: Project 1: (Prof Jerry Prince, ECE, Johns Hopkins University)

A hybrid segmentation approach employing K-means and KNN for the brain tumor segmentation task to achieve a dice score of 0.59. Extracted hand-crafted intensity, shape, and texture features with random forest regressor for the survival task. The average segmentation time per subject was 5.71 seconds.

Machine Learning: Project: (Prof. Najim Dehak, ECE, Johns Hopkins University)

Used Generative Adversarial Network to synthesize face images from voice samples using the EmoVoxCeleb dataset. Added an emotion recognition module which improved the reconstructed faces images’ PSNR by 1.29 dB and SSIM by 0.051.