Raboh, Moshe; Levanony, Dana; Dufort, Paul; Sitek, Arkadiusz

There are many different sources of information beyond the actual images that serve to inform radiologists when they are making diagnoses. To better utilize and explore the power of context in medical imaging we developed a classification algorithm based on convolutional neural networks with various contexts to classify liver lesions in multi-phase computed tomography. We designed an algorithm, to efficiently handle 3D context, clinical context, and co-occurrences context considering the presence or absence of other lesions in the volume to inform classification of a lesion under consideration. Our evaluation demonstrates that this novel algorithm substantially improves classification results.