EPSRC-NIHR HTC Partnership Award 'Plus': Medical Image Analysis Network (MedIAN)

Lead Research Organisation: University of Oxford
Department Name: Engineering Science

Abstract

The EPSRC-NIHR Healthcare Technology Co-operatives Partnership Network in Medical Image Analysis seeks to bring leading UK researchers in medical image analysis together to identify new opportunities for medical image analysis methodology research within the clinical areas of high morbidity/unmet need of the NIHR Cardiovascular HTC and HTC in Colorectal Therapies.

The HTCs are working with patient groups and clinicians on identifying unmet clinical needs in these areas. An aim of the Medical Image Analysis Network (MedIAN) is to bring together imaging scientists with different skills sets and experiences to consider how technological advances in how images are acquired and images (and associated information) are analysed can be applied to solve some of these problems.

The primary purpose of the Network is to encourage new collaborations to be set up between academic healthcare technologists, clinicians and industry partners to develop and evaluate new solutions. Network members are jointly tasked to work on some of the hardest medical image analysis problems there are today. The hope is that the resulting research will lead to new image-based biomarkers and quantification methods which will allow earlier detection of disease, and better stratification of disease so that the most appropriate therapy can be selected for a patient, and new image-based quantitative tools will lead to increases success of interventions and therapies and improve the
overall well-being of patients with these conditions.

How is MedIAN aiming achieve this goal? MedIAN is encouraging the development of new collaborations through scientific meetings with other networks/organisations, Clinical Readiness events which allow clinicians to evaluate current methods, and Challenge competitions which allow the international medical image analysis community to benchmark method on given clinical problems.

This new award will augment the existing one by enabling a number of new activities to be run: People and Knowledge Exchanges between UK research groups for early career researchers, Medical Image Analysis hackathons, Scoping Workshops to help work-up grant proposals and the facilitation of two national meetings for early career researchers (ECRs) working in medical image analysis which will be run by ECRs for ECRs. The new award will also enable a new internet resource to be set up which aims to be a focal information portal for UK medical image analysis researchers and those who wish to work with them.

Planned Impact

The main non-academic beneficiaries of MedIAN activities are patients, clinicians, establishments where treatment happens, and companies that make healthcare products.

Clinical Impact:
The HTC partners will take the lead on this. The HTCs will use their knowledge gleaned from interactions with NHS Patient & Public Involvement groups, and clinicians linked to their HTC to pose new challenges to MedIAN members that may lead to technical solutions to some of the most challenging problems in diagnosis and treatment of patients with high morbidity conditions. Clinical impact at network award end will be measured in terms of the degree of active engagement of clinicians in the network and as partners on feasibility studies and grant submissions.

Commercial Impact:
The technology area of interest of this Network is likely to be of great interest to industry (imaging companies, medtech companies who use imaging for guidance, and medical diagnostic companies). The timeline from concept to product is typically of the order of 5-7 years in this area, so it unlikely that there will commercial success stories to report by award end. Commercial impact at network award end may be measured in terms of the degree of active engagement and support of industry in the network and as partners on
grant submissions. Intellectual Property may also be generated in feasibility projects and protection will be managed following the standard practices of the institutions involved.

Societal Impact:
The Network aims to make its own unique contribution to improving healthcare products and services, and through this, improve the quality of life of patients with high morbidity conditions. Direct benefits of network outputs are likely to be realised in the medium term. However, the network aims to contribute to societal needs for better solutions for rapid and early detection of conditions, and personalised surgery to improve patient outcome, as well as to reduce the cost of healthcare by developing healthcare technology solutions that will encourage clinical adoption of lower-cost imaging technology.

Publications

10 25 50
publication icon
Hill EJ (2016) Clinical Trial of Oral Nelfinavir before and during Radiation Therapy for Advanced Rectal Cancer. in Clinical cancer research : an official journal of the American Association for Cancer Research

publication icon
Kannan P (2018) Functional Parameters Derived from Magnetic Resonance Imaging Reflect Vascular Morphology in Preclinical Tumors and in Human Liver Metastases. in Clinical cancer research : an official journal of the American Association for Cancer Research

publication icon
Shi K (2017) Editorial for the special issue of "Computational methods for molecular imaging" for computerized medical imaging and graphics. in Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society

publication icon
Swierczynski P (2018) A level-set approach to joint image segmentation and registration with application to CT lung imaging. in Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society

publication icon
Roque T (2016) A DCE-MRI imaging-based model for simulation of vascular tumour growth. in Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference

publication icon
Song S (2019) Patch-based Adaptive Background Subtraction for Vascular Enhancement in X-ray Cineangiograms. in IEEE journal of biomedical and health informatics

 
Description EPSRC Healthcare Impact Partnerships
Amount £950,000 (GBP)
Funding ID EP/P023509/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 10/2017 
End 09/2020
 
Description EPSRC Research Grant
Amount £707,983 (GBP)
Funding ID EP/R005982/1, EP/R005516/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 02/2018 
End 01/2021
 
Description ERC Starting Grant
Amount € 1,500,000 (EUR)
Organisation European Commission H2020 
Sector Public
Country Belgium
Start 02/2018 
End 01/2023
 
Description Healthcare Impact Partnership
Amount £932,050 (GBP)
Funding ID EP/P023509/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 10/2017 
End 09/2020
 
Description Clinical collaboration 
Organisation Addenbrooke's Hospital
Department Kidney Transplant Team
Country United Kingdom 
Sector Hospitals 
PI Contribution We have been developing software for brain lesion quantification used in clinical research by our collaborator.
Collaborator Contribution Our collaborator has provided research and clinical data for method development and evalaution.
Impact See publication output.
Start Year 2016
 
Description EPSRC Centre for Mathematical and Statistical Analysis of Multimodal Clinical Imaging 
Organisation Engineering and Physical Sciences Research Council (EPSRC)
Department Centre For Mathematical And Statistical Analysis Of Multimodal Clinical Imaging
Country United Kingdom 
Sector Academic/University 
PI Contribution Attend and participate in the EPSRC Centre's annual meeting.
Collaborator Contribution Sharing of knowledge between networks.
Impact Sharing of knowledge between network members.
Start Year 2017
 
Description Intelligent Ultrasound Ltd 
Organisation Intelligent Ultrasound Ltd
PI Contribution Partner on EPSRC/Innovate UK SMI Project.
Collaborator Contribution Licence agreement to use IDF software for research purposes. Licence to use AQABUS software for research purposes. IU is an medical image analysis SME and is also part of the MedIAN Network.
Impact See separate entry
Start Year 2013
 
Description NIHR Cardiovascular HTC 
Organisation National Institute for Health Research
Country United Kingdom 
Sector Public 
PI Contribution The NIHR Cardiovascular HTC was a collaborator on the original MedIAN bid. We share information on events between our networks and have run an event together.
Collaborator Contribution We share information on events between our networks and have run an event together.
Impact A joint event was held with follow-up including connecting with the UK Biobank.
Start Year 2014
 
Description NIHR Cardiovascular MIC 
Organisation National Institute for Health Research
Country United Kingdom 
Sector Public 
PI Contribution The NIHR Cardiovascular MIC replaced the HTC of the same name in January 2018 and we continue to work with them on sharing information and will run a joint meeting in 2018.
Collaborator Contribution See above.
Impact Sharing information and running joint events.
Start Year 2018
 
Description NIHR Colorectal HTC 
Organisation National Institute for Health Research
Country United Kingdom 
Sector Public 
PI Contribution The NIHR Colorectal Therapies HTC was one of the two HTCs we partnered with initially. Their strength is in identifying new important unmet clinical needs. Leeds based, they also offered us a way to reach out to researchers in this part of the country.
Collaborator Contribution The HTC has advised on activities and suggested members of their network who might be interested in MedIAN. Their HTC was set up before our network and they could offer experience/advice on how to design effective workshops. The HTC ended in 2017 and was superseded by a MIC from January 2018 (see separate entry).
Impact Joint multi-disciplnary collaborations (industry, clinical, academic) in medicine/engineering/physical sciences.
Start Year 2014
 
Description NIHR Surgical MedTech Co-operative 
Organisation National Institute for Health Research
Department NIHR Surgical MedTech Co-operative
PI Contribution The NIHR Colorectal Therapies HTC became the NIHR Surgical MedTech Co-operative in January 2018. We continue to have periodic discussions, plan to hold a joint event in 2018, and share information between our complementary networks.
Collaborator Contribution See above.
Impact Joint events; sharing information between our respective networks.
Start Year 2018
 
Description Oxford AHSN 
Organisation Oxford Academic Health Science Network
Country United Kingdom 
Sector Public 
PI Contribution Sharing of information between complementary networks.
Collaborator Contribution Sharing of information between complementary networks.
Impact Sharing of information about events, funding opportunities etc.
Start Year 2015
 
Description SINAPSE 
Organisation Scottish Imaging Network: A Platform for Scientific Excellence (SINAPSE)
Country United Kingdom 
Sector Public 
PI Contribution SINAPSE and MedIAN via the MIUA conference which was held in Edinburgh in 2017.
Collaborator Contribution We are considering running a joint event and SINAPSE will also contribute to a BigData workshop to be held in Oxford in 2018.
Impact Agreement to work together on events of mutual interest and share information between our two networks.
Start Year 2017
 
Description UK Biobank 
Organisation UK Biobank
Country United Kingdom 
Sector Charity/Non Profit 
PI Contribution The UK Biobank Imaging consortium is gathering a large amount of image data on study subjects. MedIAN participants have discussed with UK Biobank consortium partners challenges in automated image analysis of the cardiac image data.
Collaborator Contribution Knowledge exchange. Some partners have followed up with UK Biobank to consider how they can support analysis. One example is the SmartHeart Programme Grant.
Impact Individuals followed up from the workshop to consider how they might support the UK Biobank.
Start Year 2016
 
Description British Institute of Radiology Annual Conference - Machine learning for automated reporting using big data, Dr Ali Gooya 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Ali Gooya from the University of Sheffield gave a plenary talk at BIR AC 2016 entitled Machine learning for automated reporting using big data. The main goal was to increase awareness on the role of Machine Learning and Deep Learning in automated medical image analysis and reporting. The audience was very interested in this domain and a number of follow up activities in the network in this space have followed.
Year(s) Of Engagement Activity 2006
URL https://www.bir.org.uk/education-and-events/annual-congress-2016/
 
Description Developments in Healthcare Imaging - Connecting with Industry 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact Presented the MedIAN network and invited participants to join the community.
Year(s) Of Engagement Activity 2017
URL http://www.turing-gateway.cam.ac.uk/event/tgmw48/programme
 
Description IEEE Trans Med Imaging: Special Issue on Simulation and Synthesis in Medical Image Analysis 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact This special issue and accompanying editorial in one of the top journals of our field, introduces the Special Issue on Simulation and Synthesis in Medical Imaging. This special issue was run between Prof AF Frangi and Dr S Tsaftaris (both from UK) and Prof JL Prince (from Johns Hopkins University). In this editorial, we define so-far ambiguous terms of simulation and synthesis in medical imaging. We also briefly discuss the synergistic importance of mechanistic (hypothesis- driven) and phenomenological (data-driven) models of medical image generation. Finally, we introduce the twelve papers published in this issue covering both mechanistic (5) and phenomenological (7) medical image generation. This rich selection of papers covers applications in cardiology, retinopathy, histopathology, neurosciences, and oncology. It also covers all mainstream diagnostic medical imaging modalities. We conclude the editorial with a personal view on the field and highlight some existing challenges and future research opportunities.
Year(s) Of Engagement Activity 2018
URL https://ieee-tmi.org/fast-facts/featured-article.asp?id=28&title=Special-Edition:-Simulation-and-Syn...
 
Description Invited talk at CVPR 2017 workshop 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Gave an invited talk as part of a workshop at CVPR 2017 (Hawaii) which aimed to give an overview to computer vision researchers or problems and state-of-the-art research in medical image analysis. A little follow-up but discussion was quite passive (we might have been competing with the weather on the last day of the meeting!)
Year(s) Of Engagement Activity 2017
 
Description MEIbioeng16 Session 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Academic Lead: Alison Noble. Organised and participated in a session on the EPSRC Healthcare Technologies Networks at MEIbioeng16 held in Oxford. Purpose to present the Networks and discuss possible synergies as well as advertise the networks to the conference attendees.
Year(s) Of Engagement Activity 2016
 
Description MICCAI16 Challenge 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Sponsored international Challenge at MICCAI 2016 STACOM-SLAWT
Year(s) Of Engagement Activity 2016
URL http://www.doc.ic.ac.uk/~rkarim/la_lv_framework/wall/index.html
 
Description MedIAN Cardiovascular Scientific Workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Academic Leads: Alison Noble, Alex Frangi. MedIAN Cardiovascular workshop that discussed issues in analysis of UK Biobank cardiovascular data.
Year(s) Of Engagement Activity 2016
 
Description MedIAN Cardiovascular scientific workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Academic Leads: Alison Noble, Julia Schnabel. A scientific work aimed at engagement between image analysis experts and cardiovascular medicine researchers/clinicians to discuss challenges and new opportunities to work together. Run in collaboration with the NIHR Cardiovascular HTC. Follow-up was meeting to discuss UK Biobank data analysis.
Year(s) Of Engagement Activity 2015
 
Description MedIAN CodeFest 2017 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact Academic Lead: Ben Glocker. Approximately 25 people attended including Imperial, UCL, King's and Oxford students but also people from Brighton, Warwick, Cambridge and Buckingham. Two 'challenges' were prepared to work on, a deep learning introduction to analyse brain MRI, and a virtual reality one using the Oculus Rift. Most participants opted for the deep learning one, and the majority came to learn with little prior experience so we had prepared introductory examples in Python and some ideas for example applications (e.g., gender classification, age regression, brain segmentation).
Everyone seemed to have a lot of fun, and the group formation worked really well with one or two groups trying to do real research. One group tried to map neural nets to random forests based on a recent paper, and the other group looked into predicting fMRI measurements. Of course, there is very little one can do in just two days, but the social and networking aspects were the focus of the event.
Some quotes below from participants:
Attendee from Warwick:
"It was an amazing experience of learning and working together. The provided sample examples were really helpful to understand and reuse to apply our own idea. In our team one member was really good with coding so we learn to code efficiently from him by modifying existing code with our own idea. I hope, similar events will be organized in future with specific interest in cardiac images."
Attendee from Imperial:
"Thanks again for a great codefest! Apologies for all my beginner questions, but it has given me a great flying start."
Year(s) Of Engagement Activity 2017
 
Description MedIAN Colorectal Scientfic Workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Academic Lead: Julia Schnabel, Alex Frangi. Scientific workshop bringing together researchers interested in imaging of colorectal disease held in collaboration with the Colorectal Therapies HTC.
Year(s) Of Engagement Activity 2015
 
Description MedIAN website and digital presence 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Academic Lead: Alison Noble. A major activity in 2016/17 was set up a digital resource as the focal point for the MedIAN Network. The public interface of this is located at www.median.ac.uk. The MVP was launched in September 2017 and a further update will be launched in March 2018. The purpose is to provide a focal point for researchers to find out about opportunities and connect with similarly minded professionals to encourage new collaborations in the medical image analysis space.
Year(s) Of Engagement Activity 2017
URL http://www.median.ac.uk
 
Description Medical Image Computing and COmputer Assisted Interventions 2018 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Prof Alejandro Frangi is General Chair of MICCAI 2018, the premier international conference in Medical Image Analysis. Several other members of MedIAN contribute this year too: Julia Schnabel as Program Chair, Dan Stoyanov as Workshop Chair, Zeike Taylor as Workshop Co-Chair, etc. This conference has been an opportunity for MedIAN to provide leadership to the community and international exposure.
Year(s) Of Engagement Activity 2018
URL http://www.miccai2018.org
 
Description Science Writing Workshop at MIUA 2017 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact MedIAN lead: David Johns (Digital Communications Officer). An activity aimed at promoting awareness of the MedIAN network and its activities and ambitions held at the national Medical Image Understanding and Analysis conference. Comments from scientific writing workshop:
"I really liked the clarity of the concept of a scientific blog and the explanation of the differences from a publication"
"[I liked the] tricks and strategies for writing (list of things you do)"
"I got everything I wanted out of it, can't really think of a way to improve it
Year(s) Of Engagement Activity 2017
 
Description Speaker - International Women in Engineering Day 2017 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Secondary school girls from a number of local schools visited the department to see different areas of engineering and do some simple activities related to engineering. I gave the short talk at tea on some of emerging areas of engineering (wacky engineering) and talked a little about my own research and my field. Feedback from schools was positive for the whole event.
Year(s) Of Engagement Activity 2017
 
Description UCL Partners AHSC Cardiovasvcular eMedLab Workshop 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact This meeting had as purpose to bring together people working on the UK Biobank Data specially those with a technical focus working either on image analysis or data management. The group in Sheffield presented the work they are doing on cardiac image analysis and their work on www.multi-x.org. The work was very well received and we have currently a paper on quality assessment that is under review and whose origins could be traced back to discussions in this meeting with QMUL and Oxford colleagues.
Year(s) Of Engagement Activity 2017
URL https://uclpartners.com/events/cardiovascular-emedlab-workshop/