We work on multi-modal image analysis and on multi-modal artificial intelligence (AI). Multi-modality image analysis combines the interpretative power of complementary imaging modalities (such as ultrasound-MRI, PET-CT, angiography-MRI, echo-MRI) for clinical decision-making; for instance a CT image shows anatomy and an aligned positron emission tomography (PET) image indicates the uptake of a contrast agent (which may highlight cancerous tissue).

Multi-modal artificial intelligence (AI) typically combines multiple types of data (image or video, audio, text, etc) via machine learning. For instance, it can be used to automatically generate a text report from a radiology image or an ultrasound pregnancy scan video.

| Alison Noble
| Abhirup Banerjee
| Konstantinos Kamnitsas
| Vicente Grau
| Daniel Bulte
| Jens Rittscher