brain tumor

Project InnerEye – Democratizing Medical Imaging AI

InnerEye is a research project from Microsoft Health Futures that uses state of the art machine learning technology to build innovative tools for the automatic, quantitative analysis of three-dimensional medical images. The goal of Project InnerEye is to democratize AI for medical image analysis and empower researchers, hospitals, life science organizations, and healthcare providers to build medical imaging AI models using Microsoft Azure.

How AI is helping to shrink waiting times for NHS cancer patients

“OSAIRIS is the first cloud-based AI technology to be developed and deployed within the NHS, which we will be able to share across the NHS for patient benefit.”

Dr Raj Jena, oncologist at Cambridge University Hospitals NHS Foundation Trust, UK

The Project InnerEye team has been working closely with the University of Cambridge and Cambridge University Hospitals NHS Foundation Trust through a deep research collaboration around radiotherapy planning for over 10 years. Addenbrookes hospital created a new AI system, OSAIRIS, using open-source software technology from Project InnerEye and Azure Machine Learning (opens in new tab). “OSAIRIS” is saving many hours of doctors’ time in preparing scans and helping to cut the time patients have to wait between referral for radiotherapy and starting treatment.

Read the full story of OSAIRIS in the NHS here. (opens in new tab)

Project InnerEye Technology

Project InnerEye builds upon many years of research in computer vision and machine learning. It employs algorithms such as the latest Convolutional Neural Networks for the automatic, voxel-wise segmentation of medical images. Our peer-reviewed research published in JAMA Network Open shows how AI can augment and accelerate clinicians’ ability to perform radiotherapy planning 13 times faster, with an accuracy that is within the bounds of human expert variability.

Project InnerEye open-source software (OSS) has been created and used for deep learning research by the Project InnerEye team in Microsoft Health Futures. We have released this at no-cost under an MIT open-source license to make it widely available for the global medical imaging community, who can leverage our work. The tools aim to increase productivity for research and development of best-in-class medical imaging AI and help to enable deployment using Microsoft Azure cloud computing (subject to appropriate regulatory approvals). Support for these OSS tools is via GitHub Issues on the relevant repositories.

Collaborations

Project InnerEye has been working closely with the University of Cambridge and Cambridge University Hospitals NHS Foundation Trust through a deep research collaboration around radiotherapy for over a decade. Addenbrookes Hospital developed and deployed their own AI tool, OSAIRIS, using InnerEye OSS to reduce the amount of time cancer patients wait for radiotherapy treatment. Read more. (opens in new tab)

Cambridge University Hospitals logo

“This collaboration between the InnerEye team at Microsoft, and the Department of Oncology at Addenbrooke’s is an example of the type of innovation that we wish to promote within the NHS. It is a good example of what can be achieved when the Trust works in collaboration with industry and the University in order to produce cutting edge technologies with real-world applications in patient care, to benefit the UK.»

Roland Sinker, Chief Executive Officer, Cambridge University Hospitals NHS Foundation Trust

Project InnerEye and Novartis (opens in new tab) have worked together on medical image deep learning models for personalized delivery of therapies through the AI Exploration program.

Project InnerEye supported two projects as part of Microsoft’s Studies in Pandemic Preparedness research program supporting COVID-19 and future pandemic response:

UCL logo
University College London Hospitals - NHS Foundation Trust logo
University Hospitals Birmingham - NHS Foundation Trust logo

Contact

Please send an email to InnerEyeInfo@microsoft.com if you would like further information on this project.

If you have any requests or issues with the InnerEye Deep Learning Toolkit, please submit an Issue via GitHub (opens in new tab).