AI Research Group

The AI Research group is the foundation of Canon’s AI Centre of Excellence. It is made up of scientists, engineers, and clinical researchers, and plays host to a thriving student cohort of Canon-sponsored MSc, PhD and EngD students. We aim to develop clinical decision support algorithms that drive forward healthcare technologies, ranging from diagnostic systems, through to descriptive analytics and predictive analytics, supporting Precision Medicine. The group has a special responsibility to explore novel techniques and share knowledge on the state of the art in medical AI with the wider Canon Medical Group as part of our Centre of Excellence responsibility. We work with truly multi-modal medical datasets, beyond Canon Medical’s traditional roots in medical imaging, with sub-teams specialising in bioinformatics.

In pursuit of this vision, the team collaborates with global academic partners and clinical collaborators, as well as Canon Medical group colleagues in Edinburgh, Japan, Europe and the US, helping us translate the AI state-of-the-art into effective clinical decision support technologies.

To maintain our technical skills and support our research, AI scientists have opportunities to attend and present at training courses and international conferences in artificial intelligence, healthcare informatics, and clinical sciences.

Project Spotlight

Mesothelioma Research is focused on cancer-related to asbestos exposure, which develops in the pleural space around the lungs. The tumour is complex in shape, and it is highly time-consuming to measure accurately. This results in uncertainty around the extent of disease progression when assessing patients.

This uncertainty around disease measurement complicates clinical trials into new treatments for the disease, which remains untreatable.

As a part of the Data Lab’s Cancer Innovation Challenge, research at Canon Medical Research Europe and the University of Glasgow was undertaken to develop deep learning algorithms to automate the measurement of mesothelioma.

The work is being continued as a part of the international collaboration PREDICT-Meso.

The AI Research team is a partner in the Integrated Technologies for Improved Polyp Surveillance (INCISE) project. The aim is to develop a polyp risk stratification tool using multi-modal data including clinical, genomic, immunohistochemistry, and digital pathology. The role of the team is to integrate the multi-modal data to produce the final risk score.

Robust and explainable representation learning in deep learning for healthcare data. AI algorithms can fail when applied to data that is different to that seen in training, for instance coming from different scanners, different patient populations, or different clinical workflows and healthcare systems. Wrong or misleading AI predictions may lead to errors in clinical decision-making.

The AI Research team is collaborating with the VIOS lab at the University of Edinburgh on robust and explainable representation learning in deep learning for healthcare data. We have developed methods drawing on compositionality, causality, and generative modelling. This project is led by Professor Sotirios Tsaftaris, the Canon Medical/Royal Academy of Engineering Chair of Healthcare AI.

What our people say

“I really enjoy working with motivated colleagues on challenging technical projects that contribute to the future of healthcare AI. It’s especially rewarding to work at the interface of industry, academia and clinical practice; through our collaboration with the University of Edinburgh, we have been able to jointly pursue early-stage research with direct applicability to Canon’s technologies. We have also seen the release of Canon’s first natural language processing algorithm, which was the result of our AI research extending beyond imaging to include all patient data.”

Alison, Principal Scientist

“As a recent graduate, interning in the AI Research team at Canon medical was an incredible opportunity to develop my skills in machine learning in a supportive, motivating and warm environment. I was given the freedom to work on meaningful and innovative state-of-the-art AI solutions. The experience has inspired me to pursue a career in AI.”

Lucas, Intern