Publications
Ensuring accurate staining with deep generative networks for virtual IHC in pathology.
A modification to the loss function of a CycleGAN to improve its mapping ability for pathology images by enforcing realistic stain replication while retaining tissue structure.
Evolution of Convolutional Neural Networks for Lymphoma Classification.
We investigated using deep learning and evolutionary algorithms to classify Lymphoma, achieving a 10-fold cross-validation accuracy of 95.64% and a single run accuracy of 98.41%, surpassing average human pathologist performance.
It's Good to Chat?: Evaluation and Design Guidelines for Combining Open-Domain Social Conversation with Task-Based Dialogue in Intelligent Buildings.
A deployed conversational AI system for a public university building demonstrates no significant difference in task completion between open-domain social chat and task-only versions, but users prefer task-only interactions for future use.