MOAB: Multi-Modal Outer Arithmetic Block for Fusion of Histopathological Images and Genetic Data for Brain Tumor Grading

Our Contributions

• We introduce a novel Multi-modal Outer Arithmetic Block(MOAB) that fuses latent representations of different modalities using arithmetic operations.
• We demonstrate MOAB’s ability to capture rich representations of fused data in a brain cancer application using ROI histology images and genetic data.
• MOAB outperforms the previous state-of-art by producing more discriminative fused features for classification. This is also demonstrated with t-SNE plots, which visualize the improved separability of classes thanks to MOAB.

## Paper Available Here