With over 100 exhibitors at the annual Radiological Society of North America conference using NVIDIA technology to bring AI to radiology, 2019 looks to be a tipping point for AI in healthcare. Despite AI's great potential, a key challenge remains: gaining access to the huge volumes of data required to train AI models while protecting patient privacy. Partnering with the industry, we've created a solution. Today at RSNA, we're introducing NVIDIA Clara Federated Learning, which takes advantage of a distributed, collaborative learning technique that keeps patient data where it belongs -- inside the walls of a healthcare provider. Clara Federated Learning (Clara FL) runs on our recently announced NVIDIA EGX intelligent edge computing platform.
Nvidia Corp. wants to make artificial intelligence a staple of the healthcare industry with a new distributed learning technique announced today that can train machine learning models while protecting patient privacy. AI holds great promise, but for industries such as healthcare where data privacy is of paramount importance, tapping into that potential is a big challenge. The problem is that any data that might be useful to train models is almost always confidential, which means it can't be shared with technology partners. Nvidia reckons it can solve this problem with its new Clara Federated Learning technique, which ensures that patient data remains within healthcare providers' systems at all times. Clara FL is a reference application for distributed AI training that's designed to run on Nvidia's recently announced EGX intelligent edge computing platform.
I'm at the Society for Imaging Informatics in Medicine (SIIM) annual meeting this week, and looking forward to collaborating with the industry and share our latest work at the intersection of AI and medicine with the informatics community. Radiology has had a history of pushing leading edge technology in hospitals. For example, many of the earliest computer networks installed in healthcare were required because of the demands of the earliest networked modalities transmitting images to storage. That trend has continued ever since, where young startups to industry titans are exploring the tremendous potential AI holds to save the medical imaging field time and money while working to improve patient care. The field of radiology is embracing this opportunity.
Owkin, which is developing Federated Learning and AI technologies to advance medical research, announces it is teaming up with technology company NVIDIA and King's College London (KCL) to deliver Federated Learning in the healthcare and life sciences sector. The King's College London Medical Imaging and AI Centre for Value Based Healthcare (AI4VBH) is one of the world's most ambitious Federated Learning projects in healthcare. It will initially connect four of London's premier teaching hospitals before expanding throughout the UK, and will offer AI services to accelerate research and improve clinical practice in a wide range of therapeutic areas, including cancer, heart failure and neurodegenerative disease. Owkin's co-founder and Chief Scientific Officer, Gilles Wainrib, said: "This partnership brings together the best players in life science & healthcare, machine learning and data center infrastructure. NVIDIA's platforms create the ideal and flexible footprint for hospitals to invest in machine learning. King's College London has assembled the engineering, medical and data science talent, the high-quality patient data, and the governance framework in the AI4VBH Centre, that will show the world the future of healthcare analytics and the power of machine learning. Together we will be enabling the formation of a decentralized dataset that will generate enormous value for research and clinical practice. Owkin hopes to demonstrate that a Federating Learning architecture is safer for patients, and statistically equivalent to the traditional pooled model for analysis. Owkin also sees huge research potential to analyse the patient data in the AI4VBH Centre to identify new biomarkers, and high value subgroups for clinical trial design and diagnostics."
AI researchers from Nvidia and King's College London have used federated learning to train a neural network for brain tumor segmentation, a milestone Nvidia claims is a first for medical image analysis. The technique can allow data-sharing between hospitals and researchers while preserving patient privacy. Federated learning is an approach to machine learning that -- when using a client-server approach -- can eliminate the need to create a single data lake in order to train models. Instead, models are trained locally on devices that then transfer insights from multiple machines to a central model. "You need to get to these innovations, and I believe there's kind of two ways. One, which we released last August, is create the best generalizable model that you have today and just send it to each one of these hospitals, where they can localize it for their own patients," Nvidia director of healthcare Abdul Halabi told VentureBeat in a phone interview.