Last Friday, our 265th iFind volunteer arrived for her ultrasound with her partner and their chirpy two-year old daughter in tow. Once the scan started the little girl sat quietly with her father, slightly disinterested, even when he pointed out the face of her soon-to-be baby sister on the ultrasound screen. It wasn’t until we pulled open the blinds at the end of the scan, revealing the River Thames glistening between Westminster Palace and London Eye, that her apathy finally subsided and she bounced up and down with glee.
Why am I telling you this? So two-year olds don’t care much for ultrasound scans… got it. Well, there’s a little more to this story. You see, that little girl had been in this room before – and she definitely didn’t have the same response when the blinds went up the last time. Her mother (iFind participant number two hundred and sixty-five) was actually volunteering for iFind for the second time, having previously been iFind participant number… five. Yup, that excitable little two-year old had once been the unborn face we glimpsed on the ultrasound machine, right back at the very beginning of our project.
Cool right? We thought so too. In fact, it was a pretty fascinating reminder of how much time has passed since we started over three years ago, and a good opportunity to reflect on how far we’ve come since then (which, it turns out, is a long way). But more on that later. Firstly, a reminder of where we’re going: we are developing a fully integrated system of robotics, ultrasound, and computing that can automatically acquire and analyse the diagnostic imaging needed to detect fetal abnormalities. Yes, it’s ambitious; and no, we’re not (quite) there yet. But working with iFind is a bit like a mission to the moon: it will be exciting when we get there, but it’s just as exciting watching the incredible new technologies we are developing along the way.
OK then, what have we achieved? Well, for a start, we have built on the routine screening ultrasounds from thousands of our iFind 1 volunteers to help inform this incredible automatic image detection software, designed by my colleagues Christian Baumgartner and Bernard Kainz using clever machine learning algorithms. My clinical colleagues Caroline Knight, Jackie Matthew and Tara Fletcher are already investigating the ways in which this might be useful to the teams performing routine antenatal screening scans, and by combining this software with the detailed tracking data from our iFind 2 volunteers – as demonstrated in this video from my colleagues Nicolas Toussaint and Alberto Gomez – we are starting to develop the backbone of the software that will guide the robotic elements of the final system (which, as my colleagues James Housden, Yohan Noh, Shuangyi Wang and Davi Singh will tell you, is amazing… but also top secret – for now. Sorry).
From the MRI side of things, iFind volunteer 265 means we’re now over half way to our target of 500 complete fetal MRI scans, providing detailed imaging of the fetus to develop our final “atlas” of normal fetal development, being generated by Tong Zhang. We have seen some incredible yoga moves, some (technically flawless) moonwalking… and some babies just asking us to keep the noise down up there. In the last few months Jackie also completed her research looking at fetal weight, and we can now routinely report the fetal volume and weight in some of our MRI scans. In the area I am interested in – the fetal heart – Josh van Amerom has published these excitingly detailed video loops of the fetal cardiac motion, with more developments in the pipeline. And finally, by using MRI with motion correction techniques, my own research is already providing useful diagnostic information for real patients at St Thomas’ hospital, helping our clinical colleagues to provide the highest standards of care.
So there you have it. 265 patients in and we’ve come a long, long way. It’s thrilling to think where we might be in another three years. When I was told that I may have scanned that little girl before she was born, I joked, “Ah! I thought I recognised her”. I didn’t, of course. But the way things are going with iFind, one day… who knows?