Deep Learning

Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide Images

Using co-attention mapping between WSIs and genomic to capture multimodal interactions between histology images and genes for predicting patient survival. By adapting Transformer layers as a general encoder backbone in MIL, we consistently outperform current SOTA for survival prediction across 5 different cancer datasets (4,730 WSIs, 67 million patches).

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.

Weakly supervised prostate tma classification via graph convolutional networks

Semi-supervised histology classification using deep multiple instance learning and contrastive predictive coding