Speaker
Description
In High Energy Experiments there is extensive use of Machine Learning and Deep Learning algorithms. These well-established algorithms extract complex features from the data and are used for event and particle identification, energy estimation, and pile-up suppression. We present the application of these tools in the domain of pituitary tumor identification in MRI and PET-CT scans. The pituitary is a pea-sized gland, housed within a bony structure (sella turcica) at the base of the brain. Precise determination of pituitary is challenging due to structural intricacy, the noise in the data acquisition, and the incompatibility between PET and CT's spatial resolution.
In this presentation, we present the use of deep convolutional network architectures such as UNET, R-CNN for the localization of the pituitary gland. We use Transfer Learning and data augmentation for high accuracy. Two different types of datasets (MRI and CT) available freely on Kaggle were used for this purpose. We provide an explanation of the algorithms used, their performance, and a comparison with different backbones such as ResNet, VGG on the CT scan as well as the MRI image dataset. We also provide the results of using data augmentation on these datasets.
| Session | Societal Applications |
|---|
