The yeast Cryptococcus neoformans can cause dangerous infections such as meningitis. The presence of a thick capsule is shown to be correlated with virulence of a yeast cell. This paper reports on our approach towards developing a classifier for detecting virulent cells in images. We present our methods for creating samples, collecting images, preprocessing the images, identifying cells and creating features for each cell. Unsupervised clustering experiments have provided preliminary evidence that our methods results in features that can successfully be used to group and distinguish virulent from normal cells. In our future work we plan to use the same methods and feature set to build supervised classification models.