Cancer

AI-based pathology predicts origins for cancers of unknown primary

Using weakly-supervised AI to predict the primary origin of metastatic tumors, with application to Cancers of Unknown Primary (CUP).

Data-efficient and weakly supervised computational pathology on whole-slide images

Data-efficient and interpretable classification of digitized histopathology slides using only slide-level training labels, with application to cancer subtyping, metastasis detection and more.

Pathomic Fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis

An integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis.