King’s Staff International Exchange Programme

Kavitha is the Preclinical Imaging Facilities Manager for the School of Biomedical Engineering and Imaging Sciences.

I found out about King’s Staff International Exchange Programme at a Professional Services Staff Mentoring Scheme lunch mixer in 2016, whilst chatting to a fellow attendee. I had always hoped to be able to visit the company InviCRO LLM (Boston, USA) which developed one of the software packages we use within our School for preclinical image analysis. I had come to know various members of the InviCRO team over the past 8 years following their inception and through our evolving relationship as we used their software ‘Vivoquant’. I had also been interested in the research conducted at the University of Pittsburgh as their interests, choices of radio-isotopes and disease targets for imaging closely aligned with our own.
At the end of May 2017, one month after submission of my application, I found out that I was one of the fortunate to be selected by King’s Worldwide. At this point I had already made contact with both UMPC Pittsburgh and InviCRO and had identified hosts who were willing to welcome me to their respective institutions. I decided to travel to the US in September 2017 and promptly booked on an Icelandic airline called ‘Wow airlines’! In spite of its exuberant name, purple airplanes and purple-dressed cabin crew, the flight were straight-forward from London to Pittsburgh via Reykjavik…sadly Iceland was having a heatwave (8 °C) and so there was no snow to be seen from the aircraft!

Pics for blog - Kavitha- 041017

Pittsburgh was a lovely green city filled with tall conifers, green spaces and enjoying unseasonable temperatures of 27 °C. During my two days there, I visited UMPC Presbyterian hospital and had a tour of their PET centre, Siemans cyclotron, radiochemistry labs, and multiple scanners. I had the pleasure of meeting various personnel ranging from Dr Scott Mason, Dr Jonathan Carney, and Dr Brian Lopresti, who were able to describe to me the differences in regulatory structures in the USA for preclinical and radiation work and the workflow from PET isotope production to patient administration. During my visit a new Mediso PET/CT scanner was being acceptance tested and I got to see how this scanner design differed from ours at King’s which was exciting. I also got to meet Prof Carolyn Anderson, Dr Barry Edwards and their teams at UPMC Hillman Cancer Centre and toured their facilities and shared our common practices and differences. They had an interest in acquiring the Vivoquant software which we use at King’s and I was able to very quickly demonstrate to them some of its functionalities using their trial version. Happily I was going to visit InviCRO in Boston and so was able to ensure they got introduced to the correct people at Invicro who could help them evaluate the software.
Moving on from sunny Pittsburgh to Boston was a little difficult. Stormy weather delayed us taking off from Pittsburgh as there was poor visibility for landing in Boston and we arrived well past midnight. The following day, I was due to attend the Invicro User meeting and by some lucky coincidence I had booked to stay directly opposite the meeting venue! I was warmly welcomed by various members of the Invicro team and got to put faces to the names of colleagues with whom I’d had emailed and spoken to via telecon over the years. My presentation was well received and whilst it was a little daunting to have my presentation broadcast live to other Vivoquant users around the world, it was great to be able to reach out to fellow scientists via technology. I met with other speakers and attendees from around the US and straight away exchanged thoughts, ideas and contact details. I had dinner my hosts Ciara Finucane, Whitney Woodson and visitors from Invicro London (previously Immanova – acquisition officially announced a few days prior to my visit). I had a pleasant evening with amiable company and an invitation to visit Invicro London upon my return to the UK. On my final day in Boston, I spent time at Invicro headquarters and visited their labs, saw their novel instruments, chatted with particular specialists regarding the software, certain hardware equipment which we at King’s might be interested in using and the possibility of Invicro hosting a user meeting in the UK, now that they had a strong presence in London. All in all, I was well taken care of by all my hosts and felt I had something to offer whilst learning about the different scientific challenges, laboratory setups, research environments and workflows in the US.
I would recommend the King’s Staff International Exchange Programme to all my colleagues here at King’s as this has been a fruitful and rewarding experience. I have returned to the School of Biomedical Engineering and Imaging Sciences feeling very fortunate that I work in such a vibrant and exciting environment and feel renewed in my enthusiasm of our multidisciplinary, problem-solving and forward thinking ethos!

 

Advertisements

iFind Blog No. 5: A Little Reflection

David Lloyd_crop
David

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.

ifind blog pic
Reflecting on the iFind project (pun by David, not me – Ed)

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?

Imperial Festival 2017

By Samuel Vennin

This post originally appeared on the Medical Imaging CDT website.

Last week-end, many students from the CDT and staff from the division animated a stall at the Imperial Festival to present some of our work in medical imaging. The Festival is an annual event aiming to showcasing research and engage a large audience with science. From Energy and Environment to Robots, there was a wide spectrum of fields represented, each with funny animations and thought-provoking experiences to interact with the audience. I have attended the Festival as a spectator ever since I have been in London so it was great fun living it from the other side, and being the one trying to convey basic ideas about the science we carry in the CDT while making it entertaining and lively.

Our stall was located in the Health and Body Zone and we presented our research next to teams talking about detection of particles in the air that we breathe or measurement of the strength of the arm. We based our interactions on many easy experiments and materials covering the main imaging modalities (MRI, Ultrasound, PET) so that people can better understand how we obtain pictures of the bodies or why we use contrast agents.

For example, we explained the difference in the quality of images obtained with a MRI and a PET scanner and in which situations one would be favoured over the other. This served as an introduction to contrast agents whose design and conception was also explained by a video “starring” one of the CDT supervisors, Dr Phil Miller, which you can see below.

A little game helped to explain the use of those contrast agents. Four vials were filled with an invisible liquid and in one was added a colorant that would only turn blue when illuminated by a specific light. Using a UV-flashlight, people had to identify the vial containing this colorant.Another station involved spectators guessing which body part of a foetus on an echo scan was highlighted. We could then introduce the iFind project and the concept of atlases common to other imaging techniques.

Finally we carried out a survey for our own knowledge, and as a conversation starter. We wanted to know whether people would agree that their anonymised scans be shared with private companies for research purposes. People had to place a ping-pong ball in a “Yes” or “No” box. At the end of the day, the Yes box was more than full (some people had started to use tally marks to make their vote count) with 120 balls while the No one only contained 5 balls. This seems to indicate that people have no problem helping science at the condition that their identity remain unknown, regardless of if the research is public or privately funded. Obviously though, the audience attending Imperial Festival might bemuch more biased than the general population.

I was surprised overall of how quickly people could pick up complex ideas like the concept of contrast agents and the differences between an MRI and a PET scan. Kids were very insightful and we couldn’t get away with just saying “we put the body in the scanner and we obtain those beautiful pictures”. We had to explain the signals that we get from the scanner and where they come from. As a kid told me, “it is actually much more complicated than taking a picture with my camera”. Adults could relate more to the experience of being in a scanner and were mostly keen to know more about the operating details like why is an MRI scanner so noisy or why is there no one else in the scanning room other than the patient during a scan. Both the kids and adults, really liked the game on the body parts of foetuses as they found it enjoyable and playful. Some children were happy that they don’t look like a 20-week old foetus anymore.

The whole event lasted 6 hours each day and we were all both sore and voiceless at the end of it. Having to force your voice in a hall filled with hundreds of people was quite exhausting but it was worth it as visitors seemed really interested. Maybe we sparked vocations in some children? It was also interesting because we couldn’t have a prepared speech since we always had quickly questions that forced us to go off-script. It kept us on our toes the whole time but was also mentally demanding. Finally, I loved the fact that, for once, I felt knowledgeable and was able to answer the questions asked. We are training to become experts in our field and unknown is a part of our daily life. Transmitting a knowledge, rather than acquiring it or creating it, is a different game as maybe the phenomenon we describe are basic and simple, but we don’t have the help of the jargon words we would normally use. We had to think about our research in a different way. I love those opportunities to convey research in basic and simple terms to a diverse audience and it was great fun to engage with all those people. I would love to do it again.

 

 

 

*Staff from the CDT included: Matt Allinson, Josephine Bourner, Christopher Bowles, Cen Chen, Marta Dazzi, Rhiannon Evans,  Jorge Mariscal Harana, Sophie Morse, Rob Robinson, Elisa Roccia and Samuel Vennin,

I’m a Scientist Get me Out of Here!

danielfovargueDan Fovargue is a researcher on the FORCE imaging project in the Department of Biomedical engineering. Here he describes his experience taking part in I’m a Scientist, Get Me Out of Here!”

This post originally appeared on the King’s Engaged Research Network blog. 

Why did you want to engage the public? 

I recently participated in an I’m a Scientist: Get me out of here event. Past events had piqued my interest, as I was drawn to the opportunity to explain and think about a range of topics in science. The competition aspect of the event also seemed really fun. So this time around, when I saw that they were running a medical physics zone I was especially keen to join, knowing that the focus would be on topics related to my research.

I work on MR elastography, which is an imaging and engineering method for non-invasively measuring tissue stiffness. Although this is a method with much potential, it is still somewhat unknown, especially in the public. It seems then, that elastography could benefit from some outreach and exposure, so I was additionally motivated to participate in this event.

 I'm a Scientist, Get me out of here! logo

Who did you engage with and what did you do?

The events are competitions between five scientists focusing in a certain area. The scientists answer questions from students (years 7-12) both by posting responses on a website and by discussing during live chat sessions. The students vote for a scientist based on how the scientists answered their questions. The most common questions covered the why’s and how’s of becoming a scientist. These were followed by an assortment of science questions across many disciplines, including the cool (black holes, artificial intelligence) and the controversial (big bang, evolution, climate change).

Of course, there were plenty of questions related to medical physics. One helpful feature of the competition was that the scientists had profiles with information on their research (as well as hobbies). This way, the students could tailor questions to each scientist, including asking about their specific work and research. However, the philosophy of the event is to allow any question to be asked, so the students don’t have to stick to science. This results in another category of random and silly, but usually interesting, questions. 

What was the impact?

Fortunately, I got to answer lots of questions about how elastography works, what we can apply it to, and how it improves diagnoses. I even had a few rather insightful questions regarding the specifics of the physical processes in elastography, mostly questioning what types of mechanical waves can be seen with MRI and how this relates to measuring tissue stiffness. I also had the opportunity to highlight the work of other members of the elastography research group at KCL and other collaborators. I think the students were impressed that people I work with are currently applying elastography to a broad range of diseases like heart failure, breast cancer, and liver fibrosis.

Hopefully, even the students who aren’t currently too interested in science were able to get something out of this event. Part of the point is to simply show that scientists are normal enough people and break down the walls of the ivory tower. I tried to take this to heart, so I made sure to be myself and discuss a variety of topics with the students. 

How did it influence your research/you as a researcher?

Explaining my research and other scientific topics in this format was challenging but very rewarding. It was interesting to go from a meeting with my PI to answering a year 8 student’s question on elastography. The students also asked a lot of big picture questions, like where my work fits in with cancer treatment in general. I had to do some reading on cancer during the event to answer these questions appropriately which, in turn, gave me a better appreciation and understanding of the clinical side of medical physics.

During the live chat sessions there was very little time to plan out answers. I would read a question, try to think of a clever response, spend a few seconds writing, sometimes read back over it, and then move on to the next question. I usually like to think very carefully when explaining concepts, but the pace here did not allow for this. So, although, these 30 minute sessions could be exhausting, they really helped me improve my ability to explain concepts quickly and increase my confidence while doing so. There was just no time to second guess myself.

Overall this was a really fun experience. Oh! And I won!

If you’re interested in taking part in I’m A Scientist yourself, take a look at their website: https://imascientist.org.uk/  

Taking part in a research study: a different perspective

Jenny Cook
Dr Jenny Cook

Dr Jenny Cook is a Research Associate at King’s College London studying the impact of engaging publics with health research.

I am a researcher in Public Engagement for King’ College London and the National Institute for Health Research Biomedical Research Centre, part of my job role is to promote taking part in clinical research to the general population.

So last month I decided to practice what I preach and took part in a research study at the Division of Imaging Sciences and Biomedical Imaging based over at St Thomas Hospital. The study is called the iFind project which stands for intelligent Fetal Imaging and Diagnosis.

The study, funded jointly by the Wellcome Trust and EPSRC aims to improve the accuracy of routine 18-20 week screening in pregnancy, by bringing together advanced ultrasound and magnetic resonance imaging (MRI) techniques, robotics and computer aided diagnostics.

So when I realised I was eligible to take part, for a couple of extra hospital visits, I thought it would be for a good cause!

I had worked previously with the iFind team to engage different audiences with the project as educational and interactive sessions using a pregnant tummy mannequin and the ultrasound machines for the King’s Health Partners Summer School and International Clinical Trials day.

I emailed them for more details and was put in touch with a very friendly Research Midwife who sent me over a patient information pack and some available dates.

I arrived at the Clinical Research Facility on a grey drizzly morning and was met by Josie, a friendly researcher who ran through some final consent and information forms with me. She reassured me about the practical details of the study, like who would be present and how long each part would last.

I went into the Ultrasound room and was met by three people; a research sonographer, one fetal cardiac clinician researcher and another working on the imaging robotics part of the project.

They talked me through the images they were collecting and explained what they meant and why they were important to the study. They also showed me how they can create the 3D images using the new software and at the end printed me out five pictures for me to take home.

Since taking part in iFind, I was also contacted to take part in another study, this time using Magnetic Resonance Imaging (MRI) to look at fetal brain development in the Developing Human Connectome Project. The aim of this study is to map the baby’s brain development before and after birth to understand better how the brain grows and how problems may arise.

This involved coming into St Thomas’s post-natal scanning department and spending about 60 minutes inside a big MRI machine. I have to admit, it was quite noisy and cramped in there, but the imaging team were fantastic and reassuring. I had music in my headphones, plenty of pillows and came out a couple of times for a quick break. After the scan, Laura from the team went through my images with me and showed me a video of my baby moving in my stomach and the different parts of her brain. They also sent me links to the images, so I can keep them.

babyjenny
A saggital view of Jenny’s baby’s brain

The results of these images and scans in the future will contribute to a database of images that will help research. By understanding the potential benefits of using imaging and detecting more problems before birth, they hope to provide better information to parents and their doctors, and allow babies to get access to the treatments they need as soon as possible after they are born.


If you are interested in participating in the iFind project or any other fetal studies please contact: gst-tr.fetalbookings@nhs.net.
For further information on the iFIND study please contact: iFIND@gstt.nhs.uk

Student’s Mission to Improve Prenatal Imaging in Rural Bangladesh

Faisel Alam, a Masters student from the division of Imaging Science has been working with a new charity launched by KCL students to improve access to medical imaging for pregnant mothers in rural Bangladesh. He’s just returned from a trip to the country where they worked alongside local medical professionals leading seminars on best practice and offering access to healthcare to patients who otherwise may not have been able to receive it.

Maternal Aid Association (MAA) is a grassroots student led charity striving to improve situations in resource-poor settings such as Bangladesh, to bring about safe, effective, high quality maternal healthcare. This is the first overseas trip MAA have taken with the aim of providing high quality long-term sustainable maternal care in rural areas of Bangladesh. MAA has established strong links with British healthcare professionals, Bangladeshi universities, medical professionals and healthcare students in Bangladesh.

425434300_73892_11704624238969056048

The trip was led by Faisel Alam, MRes Medical Imaging Sciences postgraduate masters’ student at King’s College London. Faisel received a scholarship from the Medical Research Council (MRC) and completed his MRes research project on access to medical imaging across the developing world, using maternal care in Bangladesh as a case study. This project was completed under the supervision of Dr Gregory Mullen, Senior Lecturer in Imaging Biology and Professor Philip Blower from the Division of Imaging Sciences and Biomedical Engineering.

The team of student volunteers spent two weeks working alongside Bangladeshi healthcare professionals from the Sylhet Women Medical College, MAG Osmani Medical College and in varying hospital settings. While there, the team also prepared and led a seminar on maternal care at Sylhet Women Medical College using evidence-based best practice and reflections from their international volunteering experiences. The team participated in three days of health camps at Balaganj, Sylhet – offering free basic health checks in parts of rural Bangladesh. This reached hundreds of local residents that would otherwise not normally have access to basic healthcare.

The team also received basic sonography training from Mrs Susan Halson-Brown – the MSc Ultrasound Lead, and had planned to deliver basic sonography using a portable ultrasound device to pregnant mothers in a rural village in Bangladesh. However, the team faced difficulty delivering the ultrasound station due to unforeseen circumstances around securing trained and qualified sonographers at the rural village health complex from the local hospitals. Nonetheless, this is an area the team will be developing and expanding on in future years.

MAA was founded by Aqil Jaigirdar, a 3rd year King’s College London medical student, and the team comprises current King’s College London healthcare students supported by Professor Janice Rymer, Vice President for the Royal College of Obstetrics and Gynaecology, and Dr Daghni Rajasingham, Consultant Obstetrician Guy’s and St Thomas’ NHS Foundation Trust.

Follow their progress on Snapchat @MaaCharityUK, on Facebook facebook.com/maacharityuk and on Twitter @maacharityuk or view footage from their health complex in a rural Bangladeshi village, Balaganj.425714415_83114_4162099666314729615

The Weighting Game

David Lloyd_crop
David

One of the most important things to get right when imaging an unborn baby is the fetal weight. How do we know the fetus is growing as it should be unless we know how big they are? How can we know that the heart, or brain, or lungs, are developing normally, unless we can compare them to the rest of the body?

Unfortunately, it isn’t so easy as just popping the baby on a set of scales. They are floating in water, attached to a placenta via a long umbilical cord, surrounded by a muscular womb, and – oh yeah! – their mother. So any time we guess how much the fetus weighs, it is just that: a guess.

The most commonly used formula to estimate the fetal weight was developed in the 1980s by Dr Francis Hadlock, using ultrasound to measure the head, abdomen and thighs, and guessing the weight of the baby from that. This method can actually be pretty inaccurate – for example, we know that ultrasound can be a bit blurry, doesn’t define the edge of bones very well, and depends on finding exactly the right angles to measure which might not always be possible. Amazingly though, we’ve not been able to find a better way since then; almost every routine scan in the UK will use this method. As my fetal medicine colleague Jackie Matthew put it: “a lot of people think it’s just down to how good the sonographer is – but it’s really not that simple”. Now though, as part of the iFind project, we are working on new ways of estimating the fetal weight which we hope will be far more accurate.

fetus_placenta
Zhang & Davidson’s 3D rendering of a fetal MRI

When each of our iFind 2 volunteers attends for an extra ultrasound and MRI scan, we use these to build a three-dimensional “atlas” of the fetus, which will form the foundation for the technologies we develop to screen for fetal abnormalities. Being able to see the baby in “3D” like this is one of the jobs of my colleagues Tong Zhang and Alice Davidson – the latter of whom produced this beautiful rendering of a fetus from an MRI scan. But this image doesn’t just look amazing: it also means we could have a much more accurate way of guessing the baby’s weight than a few blurry ultrasound measurements. Knowing how much space the baby takes up in three dimensions – the fetal volume – means we could potentially estimate far more precisely whether the baby is growing normally.

So that’s a win right? Go iFind! Well… not quite. Unfortunately it’s still not that simple – and that’s where Jackie comes in. Her research has some difficult questions to answer: exactly how inaccurate are these ultrasound techniques? How do we do know? Is MRI really better? How do we prove it? And how does a fetal volume equate to a fetal weight? Is it the same through all nine months of pregnancy?

These are tough questions, but like everyone else at iFind, Jackie is determined to find answers. And when she does, it’s these types of new discoveries that should help iFind get closer to its ultimate goal: using new technologies to improve how we see and understand life before birth.

 

Dr David Lloyd is a Clinical Research Fellow at King’s College London and working as part of the iFIND project. The overall aim of the intelligent Fetal Imaging and Diagnosis project is to combine innovative technologies into a clinical ultrasound system that will lead to a radical change in the way fetal screening is performed.

 

Making reproducible research as natural as breathing

Peter CharltonPeter Charlton is a PhD student at King’s College London working as part of the Hospital of the Future (HotF) project. The overall aim of the HotF project is to provide early identification of hospital patients who are deteriorating. Peter’s work focuses on using wearable sensors to continuously assess patients’ health.

One of the key aims of the HotF project is to develop a technique to continuously monitor a patient’s “respiratory rate”: how often they breathe. Respiratory rate often changes early in the progression of a deterioration, giving advanced warning of a severe event such as a heart attack. However, it is currently measured by hand by counting the number of times a patient breathes in a set period of time. This approach is time-consuming, inaccurate, and only provides intermittent measurements. The alternative approach which I’m working on is to estimate respiratory rate from a small, unobtrusive, wearable sensor.

Wearable sensors are currently routinely used to monitor heart rate and blood oxygenation levels. It turns out that the signals which provide these measurements are subtly influenced by respiration, as demonstrated below. If these subtle changes can be extracted reliably, then we could monitor respiratory rate “for free”, without the need for any additional sensors. This may provide all-important information on changes in a patient’s health, allowing clinicians to identify deteriorating patients earlier.

PeterCharlton_heartratesignal

The heart rate is clearly visible in this signal since each spike corresponds to a heart beat. The spikes also vary in height with each of the four breaths. These subtle changes can be used to estimate respiratory rate.

So what’s all this got to do with reproducible research? Well, over the past few decades over 100 papers have been written describing methods for estimating respiratory rate electronically from signals that are already monitored by wearable sensors. If you read them (it takes a long time) then you find that hundreds of methods have been described. The key questions are: which method is the best, and is it good enough to use in clinical practice? Answering these questions can be a daunting task given how many different methods there are. Very few of the methods are publicly available, so to answer these questions you’d have to implement each of the methods yourself. Even once you have done this, you’d need to try them out on some data. Collecting this data is no easy task. Altogether, reproducing scientist’s previous work on this problem is quite difficult.

I’m hoping that this won’t be such a problem in the future. We have recently implemented many of the methods, collected a benchmark dataset on which to test the methods, and reported the results. All of this is publicly available. What’s more, you can download it all for free, from the methods, to the data, to the article describing the results. So in a few clicks you can catch up, reproduce our research, and start making progress yourself, even producing methods like this:

PeterCharlton_resp_video_gif_red

Well, nearly … I’ve written a tutorial on the methods, which is due to be published in a textbook soon. This work can be reproduced exactly. Since then we have extended the range of publicly available resources by adding more methods, and the new benchmark dataset. This most recent work can’t be reproduced exactly since we had to make a few changes before making it publicly available. I intend to make future work on this topic fully reproducible so that researchers can build on our work. Who knows, perhaps this will contribute towards earlier identification of deteriorating patients in the future.