A Stimulating Lunch at Oxford University

During my trip to the UK two weeks ago I visited Oxford University and had lunch with a number of faculty members at Keble College.  In particular, I sat next to Professor Sir Michael Brady with whom I had a fascinating conversation. 

Professor Brady is BP Professor of Information Engineering in the Department of Engineering Science at Oxford.  He has a broad range of research interests.  In his words, ". . . the themes that characterise Information Engineering, and that have characterised my research in Oxford, irrespective of the domain of application, are:

• it is rooted in real problems, that have varied from mobile robots for application in manufacturing to systems to help diagnose breast cancer;
• it mobilises and develops ideas from Computing Science, particularly the ideas of representation and distributed computer architecture. This is particularly evident in my work on mobile robotics, but also in that on teleconferencing and medical image analysis. A particular theme is the application of Artificial Intelligence, in the quest to make systems 'smart';
• it builds on a solid mathematical foundation. This permeates all of my work, whether it is a differential geometrical analysis of image surfaces, a model for x-ray image formation, infrared image analysis, or a model of defocussing blur in an image; and
• the work is intrinsically inter-disciplinary: at Oxford I have worked with radiologists, clinical neurologists, psychiatrists, psychologists, as well as with people from a range of industries."

After conducting research in artificial intelligence and robotics for several years, Professor Brady became interested in medical image analysis, and in particular, how it might be used in oncology research for the early diagnosis of cancer.  His work initially focused on breast cancer, but more recently has included colorectal and liver cancer, as well as research on brain image analysis.  He is a co-founder of the Wolfson Medical Vision Laboratory at Oxford, and of Mirada Solutions, a company that develops tools for medical image analysis and is now part of Siemens Medical Solutions.

In 2002 Oxford University, the UK Government and IBM announced the formation of the eDiamond project to build a sophisticated computing Grid that would enable early screening and diagnosis of breast cancer and provide medical professionals with highly detailed information to help treat the disease.  The eDiamond Grid computing project enables hospitals to store and share mammograms in digital form, and provides physicians with advanced analytical tools and capabilities to better detect cancer in patients as early as possible.  Professor Brady was heavily involved in the formation of the eDiamond project, and many of the digital mammographic analysis tools used in the project come from his and his colleagure’s work at Oxford and Mirada Solutions.

He has no doubt that digital medical image analysis will become standard in the future, because of the much higher flexibility and lower costs it offers compared to the use of x-ray film.  This will make breast cancer screening much more readily available around the world and help save lives.  But, - arguably even more important, - the quality of treatment would significantly improve, as physicians take advantage of advanced medical tools to better diagnose and treat potential cancer in patients.  The advanced supercomputers involved can detect details that would elude a human, as well as reduce the inevitable human errors that are caused when information is incomplete or a physician is just plain tired after many hours of visually inspecting x-ray films.    

During our lunch, we discussed the potential of leveraging the highly visual and interactive capabilities of the new generation of game technologies now coming to the market in order to provide physicians with extremely high quality, detailed visual images that they can rotate, zoom in or out and manipulate in a variety of ways to help them better see and analyze the information embedded in the image -  however small.  The new Cell blades we recently announced should help in the development of this new generation of highly visual medical imaging applications. 

Professor Brady also mentioned that at Oxford researchers in the humanities were increasingly using IT in their work, to provide, for example, online access to a variety of original materials that are scattered across many different locations around the world or that may be hard to examine directly because of their fragility.  This led to a very interesting discussion of how the kinds of interactive virtual world platforms and tools that have become increasingly popular in online games like Second Life and World of Warcraft could be used to teach subjects like history or literature. 

Imagine for example interacting with a virtual world based on the Iliad or the Odyssey, to learn about the characters in a much more active way, and perhaps explore alternative ways that the stories could have played out if some events had happened in a different manner.  Or learning history by getting a much more vivid picture of what life was like in different eras and different civilizations, such as ancient Egypt or medieval Europe, - by interacting with virtual world simulations that have been designed to be as historically realistic as possible.  I know that the development tools to build such applications must significantly improve, but I am confident that over time they will.  These are very good examples of the new applications emerging across a variety of disciplines as supercomputing capabilities become more powerful, inexpensive, visual and interactive.  The possibilities are fascinating and endless. 

It was indeed a highly stimulating lunch at Oxford.  Lots of food for thought.   

Comments

[Chris Yeh]

Irving,

I totally agree that immersive games are the future of education.

In today's passion-driven world, teaching in a manner that bores people is a non-starter.

I've been arguing for games as an educational medium for years:
http://chrisyeh.blogspot.com/2005/06/future-of-education.html

Is Big Blue doing anything in this area?

[Eddie]

Irving,

One brief thought (as I was also reading about your suggestion that engineers need to be have better liberal arts and business skills) ... the same can be said for the "business suits / managers" ... when was the last time a manager actually wrote a little bit of code such as XHTML, CSS, Python or C++? Let's not forget that it works both ways ... the days of managers not getting their hands dirty and understanding the world that engineers have to live in is finished, just as are the days that engineers can only be engineering (writing code, etc.).

[Michael]

I could think of a no better time for the re emergence of the Smithsonian's National Museum of American History, Information Age, People, Information, and Technology exhibition. It is a privilege to travel with you IWB in the unfolding of our present integrated space. I thought I would share an EMC blog on history of storage ..http://event.on24.com/eventRegistration/EventLobbyServlet?target=lobby.jsp&playerwidth=635&playerheight=476&defaultstream=wm150&onload=launchwebcast&eventid=16760&sessionid=1&key=0720434523FDFA0EA535BAE35F8F1409&eventuserid=4660003