Multi-stain learning for neuropathology evaluation
About
Definitive diagnosis of neurodegenerative diseases traditionally relies on postmortem histopathology. While whole slide imaging has modernized pathology workflows, diagnostic performance still depends heavily on stain availability. We introduce a deep learning framework for multi-stain WSI analysis that operates effectively when some stains are missing. This approach offers a promising pathway to improve diagnostic accuracy in settings with limited staining resources.
Speaker
Lingyi Xu
Lingyi Xu is a Ph.D. student in the Faculty of Computing & Data Sciences at Boston University. She is currently working with Professor Vijaya B. Kolachalama on computation-assisted methods that help with cancer diagnosis and treatment. Her research focuses on graph representation learning, especially in clinical settings, to improve diagnostic accuracy, efficiency, and interpretability.