MAESTRO Jr - Multi-sensing AI Environment for Surgical Task & Role Optimisation

Principal Investigator(s): Professor Fabio Cuzzolin, Dr George Mylonas

Project start: October 2021

Project finish: December 2022

Funded by: EPSRC

 News

MAESTRO Jr has started on October 1st 2021! We are looking for a postdoctoral research fellow, from now until the end of the project in December 2022.

About us

While performing complex tasks in the challenging environment of an operating room (OR), staff must interact and communicate at various levels. Potential sources of human error are manifold and serious patient harm may occur because of pressure and cognitive overload. Today's operating rooms do heavily rely on technology, but with little or no functional integration between devices. Our MAESTRO concept aims at laying the foundations for the operating room of the mid-21st Century, as a surgical environment powered by trustable, human-understanding artificial intelligence able to continually adapt and learn the best way to optimise safety, efficacy, teamwork, economy, and clinical outcomes.

MAESTRO Jr.'s objectives are therefore:

  1. to deploy and test a platform integrating multiple sensing modalities as a sandpit for further research;
  2. to validate the multi-sensor fusion sensing of escalating cognitive load;
  3. to perform multimodal situation awareness for automated surgical check-listing;
  4. to study the feasibility of continual learning for adapting to new surgical teams and procedures, as the pillar of an AI-assisted OR of the future.

The EPSRC call for Transformative Healthcare Technologies is a high risk, high return initiative implemented in two phases. Phase 1, the development phase, projects are identifed that demonstrate readiness in order to deliver an ambitious programme of research in Phase 2. MAESTRO Jr has been funded under Phase 1.

In the programme delivery phase, awardees in development phase will be invited to bid into a second call, where we envisage supporting around four to six substantive programmes of research.

The project is led by Dr George Mylonas, Imperial College London. Co-investigators are Prof Fabio Cuzzolin (Oxford Brookes), Dr James Kinross (Senior Lecturer in Surgery at ICL) and Mr Daniel Leff, a Reader in Surgery with the Depts of BioSurgery and Surgical Technology, the Hamlyn Centre and the CRUK Centre at ICL.

Imperial College London is a world-class university with a mission to benefit society through excellence in science, engineering, medicine and business. Imperial grew out of Prince Albert's vision for an area of culture, including the Royal Albert Hall, Natural History Museum, Victoria & Albert Museum, and the Royal Colleges that would go on to form Imperial College.

Research impact

MAESTRO Jr will benefit: (i) healthcare organisations, including the NHS, through reduction of surgical errors; (ii) individual hospitals, in terms of reduced costs and shorter waiting lists; (iii) healthcare staff via reduced cognitive workload, improved work satisfaction and lower friction with colleagues; (iv) patients and their families, through increased patient safety; (v) researchers in all scientific fields involved, via the dataset and codebases we will make; and (vi) the wider public and the UK economy at large, in terms of strengthened competitiveness and novel market opportunities.

We obviously expect this work to strongly impact the field of surgical robotics, and AI for healthcare at large. MAESTRO will introduce a new holistic paradigm which will bring closer the dream of a smart operating room.The MAESTRO concept will strongly contribute to the emerging paradigm of a human-centric AI. The proposed work is foundational and transformative when it comes to the rapidly growing fields of continual learning (continually reducing a model’s uncertainty about a problem via evidence accumulation) and, in Phase 2, (inverse) reinforcement learning (RL).

Membership

Staff

Name Role Email
Professor Fabio Cuzzolin Professor of Artificial Intelligence fabio.cuzzolin@brookes.ac.uk

Students

Name Thesis Title Supervisors Completed
Salman Khan Deep Scene Graph Models for Complex Activity Detection Professor Fabio Cuzzolin, Dr Tjeerd olde Scheper

Active

Mr Izzedin Teeti Predictive Algorithms for Advanced Autonomous Vehicle Perception Dr Andrew Bradley, Professor Fabio Cuzzolin

Active

Collaborators

Name Role Organisation
Dr George Mylonas Director of HARMS Lab, Lecturer in Robotics and Technology in Cancer Imperial College London