Towards 10-minute Magnetic Resonance Scanning in Children - Developing Accelerated Imaging Using Machine Learning
Lead Research Organisation:
University College London
Department Name: Institute of Cardiovascular Science
Abstract
Magnetic Resonance Imaging (MRI) scans play a vital role in helping many ill children, by finding out what the problem is and helping plan their treatment. MRI is safe because it does not use radiation. MRI scans produce good-quality pictures or images of many parts of the body, including the brain, heart, spine, joints and other organs. The main problem is they take a long time - often over an hour. During the scan, the child has to keep very still and may even need to hold their breath many times. This is especially hard for children and unwell patients. Hence, younger children under 8 years old need a general anaesthetic, to put them to sleep during the scan. In many childhood diseases, for example in cancer, children may need many MRI scans to follow up disease progression and treatment. Being put to sleep for all of these scans is not pleasant for the child and may occasionally cause problems. It also puts a lot of pressure on hospitals who need to find the doctors, beds, equipment and funds for this.
One way of overcoming these problems would be to speed up the MRI scans so the children do not have to keep still or hold their breath. The simplest way of doing this is to collect less data for each image, but this causes so much distortion in the images that they cannot be used. There are some ways of converting these into useful images, but these are complicated and take too long to use in a hospital.
Machine Learning is an upcoming way of teaching computers to find complicated patterns in large amounts of information. Recent advances mean that computers are now so powerful that they can learn effectively. Machine Learning has been successfully used for analysing many types of images, for example to perform de-noising, interpolation, image classification and border identification. Despite its popularity, only a few recent studies have shown its potential for reconstruction of MRI images. This is partly due to the greater complexity of the problem and importantly, the large amounts of data required to 'learn' the solution. At Great Ormond Street Hospital, we have MRI images from over 100,000 children and scan an additional 10,000 children each year, all of which we could use to help train and test Machine Learning technologies.
I have already shown that basic Machine Learning techniques can remove distortions from MRI scans of the heart, so I am well placed to develop Machine Learning techniques to reconstruct MRI images from other children's diseases, as well as developing more advanced Machine Learning techniques. I showed Machine Learning to be faster than existing reconstruction methods and the images were of better quality than more conventional state-of-the-art techniques. However, much more work is needed to get Machine Learning working reliably in children's scans and to make the most of the possible benefits.
If we can use fast scanning with Machine Learning we could shorten scan times from 1 hour to about 10 minutes for children having MRI scans. They would not have to keep completely still for the scan and would not have to hold their breath, therefore reducing the need to put patients to sleep. This would make MRI scanning far less difficult and daunting for children, and would eliminate the cost and side effects from the anaesthetic. Quicker scans would help reduce waiting lists and costs for the NHS. It would also mean that MRI scanning would be used far more often, so it could help many more children. Additionally, these techniques could enable MRI scans to become affordable in some countries for the first time.
One way of overcoming these problems would be to speed up the MRI scans so the children do not have to keep still or hold their breath. The simplest way of doing this is to collect less data for each image, but this causes so much distortion in the images that they cannot be used. There are some ways of converting these into useful images, but these are complicated and take too long to use in a hospital.
Machine Learning is an upcoming way of teaching computers to find complicated patterns in large amounts of information. Recent advances mean that computers are now so powerful that they can learn effectively. Machine Learning has been successfully used for analysing many types of images, for example to perform de-noising, interpolation, image classification and border identification. Despite its popularity, only a few recent studies have shown its potential for reconstruction of MRI images. This is partly due to the greater complexity of the problem and importantly, the large amounts of data required to 'learn' the solution. At Great Ormond Street Hospital, we have MRI images from over 100,000 children and scan an additional 10,000 children each year, all of which we could use to help train and test Machine Learning technologies.
I have already shown that basic Machine Learning techniques can remove distortions from MRI scans of the heart, so I am well placed to develop Machine Learning techniques to reconstruct MRI images from other children's diseases, as well as developing more advanced Machine Learning techniques. I showed Machine Learning to be faster than existing reconstruction methods and the images were of better quality than more conventional state-of-the-art techniques. However, much more work is needed to get Machine Learning working reliably in children's scans and to make the most of the possible benefits.
If we can use fast scanning with Machine Learning we could shorten scan times from 1 hour to about 10 minutes for children having MRI scans. They would not have to keep completely still for the scan and would not have to hold their breath, therefore reducing the need to put patients to sleep. This would make MRI scanning far less difficult and daunting for children, and would eliminate the cost and side effects from the anaesthetic. Quicker scans would help reduce waiting lists and costs for the NHS. It would also mean that MRI scanning would be used far more often, so it could help many more children. Additionally, these techniques could enable MRI scans to become affordable in some countries for the first time.
Planned Impact
Magnetic Resonance Imaging (MRI) plays a vital role in diagnosis, management and monitoring of many childhood diseases. However, a complete examination is slow and requires the use of general anaesthesia (GA) in children under 8years. This fellowship will develop Machine Learning (ML) techniques to speed up the acquisition of MRI data, reducing total scan times from ~1hour to ~10minutes. Motion correction techniques will be incorporated to reduce the need for patient cooperation, making it possible to dispense with GA. In addition, fast and accurate image interpretation tools will be created, to help efficient and reproducible analysis and disease classification.
Impact on Patients;
Combined, this will make MRIs safer, more comfortable and less daunting, improving children's experience. The work will also increase accessibility and tolerance of MRI in paediatric diseases, allowing it to be used more routinely, both for initial diagnosis and follow-up of childhood illness. Together with improved image quality, reduced motion artefact, as well as higher resolution imaging and/or acquisition of additional data, these have the potential to improve diagnostic accuracy, monitoring and hence outcomes in childhood diseases.
Impact on Clinical Research;
In the short-term, these technologies will position the UK at the forefront of clinical research, and encourage pharmaceutical companies to use MRI in clinical trials. This is because they will reduce scan costs and simplify recruitment by enabling research scans to be performed on clinical patients (due to more efficient protocols). Additional populations may be recruited, where MRI may not have been ethically acceptable or practical before because of the need for GA or long scan times-improving understanding of other diseases. Additionally, more scans may be performed, improving the quality of data, allowing higher resolution imaging or acquisition of additional data.
Impact on NHS;
In the mid-term, benefits to the NHS include reduced risk and cost of GA, allowing redeployment of valuable anaesthetic staff and reducing pressure on equipment and hospital beds. Reduced requirements for patient compliance will reduce unsatisfactory scans and recall rates. Shortened scan times will reduce scan costs and allow an increase the number of patients that can be examined each day, ultimately reducing waiting lists. The technologies will help improve diagnosis and management of paediatric disease, preventing cost and side effects of ineffective treatment. By achieving high quality, fast scanning using existing scanner technology, these techniques may also reduce the need to upgrade scanners.
Other Clinical Applications;
The proposed techniques can also be applied to MRI of other systems, e.g. musculoskeletal or gastrointestinal imaging, as well as to adult MRI protocols, where similar benefits to patients, research studies and the NHS can be achieved. In the long term, it is possible these technologies may enable MRI to replace CT in some cases-eliminating the need for ionising radiation and CT contrast agent, reducing risk to patients, and freeing up CT resources.
Worldwide and Industrial Impact;
These technologies have the potential to transform paediatric MRI from an expensive, infrequently used technique, into a high throughput imaging technique that is routinely used clinically and in research studies in paediatric disease. Reduced scan times and costs would also have worldwide healthcare impact, including in countries where MRI is currently still too expensive for widespread use. This makes these technologies attractive to MRI scanner manufacturers, opening up new markets. Additionally, existing rolling software updates to existing MRI scanners enable worldwide deployment of these new techniques. Existing links with Siemens Healthcare (who are project partners), will allow short term translation to other sites and ultimately integration into the vendor's product.
Impact on Patients;
Combined, this will make MRIs safer, more comfortable and less daunting, improving children's experience. The work will also increase accessibility and tolerance of MRI in paediatric diseases, allowing it to be used more routinely, both for initial diagnosis and follow-up of childhood illness. Together with improved image quality, reduced motion artefact, as well as higher resolution imaging and/or acquisition of additional data, these have the potential to improve diagnostic accuracy, monitoring and hence outcomes in childhood diseases.
Impact on Clinical Research;
In the short-term, these technologies will position the UK at the forefront of clinical research, and encourage pharmaceutical companies to use MRI in clinical trials. This is because they will reduce scan costs and simplify recruitment by enabling research scans to be performed on clinical patients (due to more efficient protocols). Additional populations may be recruited, where MRI may not have been ethically acceptable or practical before because of the need for GA or long scan times-improving understanding of other diseases. Additionally, more scans may be performed, improving the quality of data, allowing higher resolution imaging or acquisition of additional data.
Impact on NHS;
In the mid-term, benefits to the NHS include reduced risk and cost of GA, allowing redeployment of valuable anaesthetic staff and reducing pressure on equipment and hospital beds. Reduced requirements for patient compliance will reduce unsatisfactory scans and recall rates. Shortened scan times will reduce scan costs and allow an increase the number of patients that can be examined each day, ultimately reducing waiting lists. The technologies will help improve diagnosis and management of paediatric disease, preventing cost and side effects of ineffective treatment. By achieving high quality, fast scanning using existing scanner technology, these techniques may also reduce the need to upgrade scanners.
Other Clinical Applications;
The proposed techniques can also be applied to MRI of other systems, e.g. musculoskeletal or gastrointestinal imaging, as well as to adult MRI protocols, where similar benefits to patients, research studies and the NHS can be achieved. In the long term, it is possible these technologies may enable MRI to replace CT in some cases-eliminating the need for ionising radiation and CT contrast agent, reducing risk to patients, and freeing up CT resources.
Worldwide and Industrial Impact;
These technologies have the potential to transform paediatric MRI from an expensive, infrequently used technique, into a high throughput imaging technique that is routinely used clinically and in research studies in paediatric disease. Reduced scan times and costs would also have worldwide healthcare impact, including in countries where MRI is currently still too expensive for widespread use. This makes these technologies attractive to MRI scanner manufacturers, opening up new markets. Additionally, existing rolling software updates to existing MRI scanners enable worldwide deployment of these new techniques. Existing links with Siemens Healthcare (who are project partners), will allow short term translation to other sites and ultimately integration into the vendor's product.
Organisations
- University College London (Fellow, Lead Research Organisation)
- Nationwide Children's Hospital (Collaboration)
- Siemens Healthcare (Collaboration)
- University College Hospital (Collaboration)
- Royal Veterinary College (RVC) (Collaboration)
- Lund University (Collaboration)
- Sydney Hospital (Collaboration)
- National Institute for Health Research (Collaboration)
- Great Ormond Street Hospital (Project Partner)
- Siemens plc (UK) (Project Partner)
Publications
Baker R
(2023)
2D sodium MRI of the human calf using half-sinc excitation pulses and compressed sensing
in Magnetic Resonance in Medicine
Yao T
(2024)
A Deep Learning Pipeline for Assessing Ventricular Volumes from a Cardiac MRI Registry of Patients with Single Ventricle Physiology.
in Radiology. Artificial intelligence
Steeden J
(2022)
Artificial Intelligence in Cardiothoracic Imaging
Montalt-Tordera J
(2022)
Automatic segmentation of the great arteries for computational hemodynamic assessment.
in Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance
Jaubert O
(2021)
Deep artifact suppression for spiral real-time phase contrast cardiac magnetic resonance imaging in congenital heart disease.
in Magnetic resonance imaging
Montalt-Tordera J
(2022)
Editorial for "Automatic Time-Resolved Cardiovascular Segmentation of 4D Flow MRI Using Deep Learning"
in Journal of Magnetic Resonance Imaging
Jaubert O
(2022)
FReSCO: Flow Reconstruction and Segmentation for low-latency Cardiac Output monitoring using deep artifact suppression and segmentation.
in Magnetic resonance in medicine
Jaubert O
(2024)
HyperSLICE: HyperBand optimized spiral for low-latency interactive cardiac examination.
in Magnetic resonance in medicine
Montalt-Tordera J
(2021)
Machine learning in Magnetic Resonance Imaging: Image reconstruction.
in Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)
Kowalik GT
(2020)
Perturbed spiral real-time phase-contrast MR with compressive sensing reconstruction for assessment of flow in children.
in Magnetic resonance in medicine
Montalt-Tordera J
(2020)
Rapid 3D whole-heart cine imaging using golden ratio stack of spirals.
in Magnetic resonance imaging
Steeden JA
(2020)
Rapid whole-heart CMR with single volume super-resolution.
in Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance
Jaubert O
(2021)
Real-time deep artifact suppression using recurrent U-Nets for low-latency cardiac MRI.
in Magnetic resonance in medicine
Nayak KS
(2022)
Real-Time Magnetic Resonance Imaging.
in Journal of magnetic resonance imaging : JMRI
Montalt-Tordera J
(2021)
Reducing Contrast Agent Dose in Cardiovascular MR Angiography with Deep Learning.
in Journal of magnetic resonance imaging : JMRI
Description | This grant is investigating the use of Machine Learning (ML) to assist with reconstruction of MRI data in the clinical environment. We have shown some really impressive results with highly accelerated acquisitions, with ML reconstructions on the scanner in the hospital. This has huge impact on patient throughput, and patient comfort, as well as enabling some novel research protocols, which would not have been possible beforehand. |
Exploitation Route | More large-scale multi-site studies are necessary to fully validate these techniques in the clinical environment. We are currently performing one such study across 6 International sites, with our industrial collaborators, Siemens, to enable translation into routine clinical practise internationally. |
Sectors | Healthcare |
Description | The technologies developed have been applied to clinical scanning at multiple UCL hospitals, to speed up MRI scanning, and improve patient comfort. Our work also addressed faster and more accurate/reproducible data analysis, which has been integrated into the clinical service at Great Ormind Street hospital and The Royal Free hospital. |
First Year Of Impact | 2018 |
Sector | Healthcare |
Impact Types | Societal,Economic |
Description | Annual Meeting Program Committee Member for ISMRM |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Influencing teaching and training and priority areas for MRI for researchers as well as clinicians |
URL | https://www.ismrm.org/meetings-workshops/future-ismrm-meetings/ |
Description | Chair of AI Subcommittee for Paediatric SCMR |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Particularly increasing the understanding for clinicians about the use and limitations of Machine Learning in MRI. How it is useful, what it can be used for, what they can do to help develop new tools, when it works and what its limitations are. |
URL | https://scmr.org/members/group.aspx?code=SC-PCHD |
Description | Chair of Physics and Engineering Table for ISMRM Education Committee |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Better education of the MRI community |
URL | https://www.ismrm.org/online-education-program/meet-your-education-committee/ |
Description | Committee member for EACVI |
Geographic Reach | Europe |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Improving training of radiologists, radiographers and cardiologists for cardiovascular imaging |
URL | https://www.escardio.org/Education/Career-Development/Certification/Cardiovascular-Magnetic-Resonanc... |
Description | Educational Board Member for ISMRM |
Geographic Reach | Multiple continents/international |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Focus currently is about curating a database of the best MRI teaching materials |
URL | https://www.ismrm.org/online-education-program/ |
Description | Exam board representative in for pediatric EuroCMR |
Geographic Reach | Europe |
Policy Influence Type | Influenced training of practitioners or researchers |
Impact | Training of cardiologists and radiologists, and their subsequent examinations to achieve full qualification |
Description | CCP in Synergistic Reconstruction for Biomedical Imaging |
Amount | £476,024 (GBP) |
Funding ID | EP/T026693/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 04/2020 |
End | 03/2025 |
Description | Development of Novel, Fast Techniques for Sodium Imaging Using Magnetic Resonance Imaging |
Amount | £50,000 (GBP) |
Organisation | UCL Partners |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 04/2020 |
End | 03/2022 |
Description | NIHR UCLH Biomedical Research Centre Cardiovascular Diseases Theme |
Amount | £58,407 (GBP) |
Funding ID | BRC870/CM/JS/101320 |
Organisation | University College London |
Sector | Academic/University |
Country | United Kingdom |
Start | 04/2022 |
End | 05/2023 |
Description | Novel Intestinal Motility Imaging To Identify Prodromal Parkinson Disease And Response To Systemic Therapy For Synucleinopathy |
Amount | £620,000 (GBP) |
Funding ID | MJFF-021438 |
Organisation | Michael J Fox Foundation |
Sector | Charity/Non Profit |
Country | United States |
Start | 11/2022 |
End | 10/2025 |
Description | Quantitative Reporting in Crohn's Disease: Maximising available MRI data to better direct patient treatment, speed up treatment decisions and improve healthcare outcomes |
Amount | £182,000 (GBP) |
Funding ID | 73477 |
Organisation | Innovate UK |
Sector | Public |
Country | United Kingdom |
Start | 05/2020 |
End | 11/2020 |
Description | Towards 10-minute Magnetic Resonance Scanning in Children - Developing Accelerated Imaging Using Machine Learning |
Amount | £989,997 (GBP) |
Funding ID | MR/S032290/1 |
Organisation | Medical Research Council (MRC) |
Sector | Public |
Country | United Kingdom |
Start | 02/2020 |
End | 04/2025 |
Title | TensorFlow NUFFT |
Description | TensorFlow NUFFT is a fast, native non-uniform fast Fourier transform op for TensorFlow. It provides: Fast CPU/GPU kernels. The TensorFlow framework automatically handles device placement as usual. A simple, well-documented Python interface. Gradient definitions for automatic differentiation. Shape functions to support static shape inference. |
Type Of Material | Improvements to research infrastructure |
Year Produced | 2021 |
Provided To Others? | Yes |
Impact | Used in MRI and space research |
URL | https://github.com/mrphys/tensorflow-nufft |
Title | TensorFlow-MRI A Library for Modern Computational MRI on Heterogenous Systems |
Description | TensorFlow MRI is a library of TensorFlow operators for computational MRI which includes: A fast, native non-uniform fast Fourier transform (NUFFT) operator (see also TensorFlow NUFFT). A unified gateway for MR image reconstruction, which supports parallel imaging, compressed sensing, machine learning and partial Fourier methods. Common linear and nonlinear operators, such as Fourier operators and regularizers, to aid in the development of novel image reconstruction techniques. Multicoil imaging operators, such as coil combination, coil compression and estimation of coil sensitivity maps. Calculation of non-Cartesian k-space trajectories and sampling density estimation. A collection of Keras objects including models, layers, metrics, loss functions and callbacks for rapid development of neural networks. Many other differentiable operators for common tasks such as array manipulation and image/signal processing. |
Type Of Material | Improvements to research infrastructure |
Year Produced | 2021 |
Provided To Others? | Yes |
Impact | Used internationally, and referenced accordingly |
URL | https://github.com/mrphys/tensorflow-mri |
Description | Creating fast MRI techniques for Sodium imaging |
Organisation | National Institute for Health Research |
Department | UCLH/UCL Biomedical Research Centre |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | Myself and my research team have developed novel rapid 2D MRI technique for quantification of sodium In the leg muscle/skin. We have developed a novel 2D spiral sequence with novel RF pulses to enable very short echo times (necessary for Sodium imaging) We have developed and optimised compressive sensing reconstruction for 2D sodium imaging in the leg We have validated the technique in the leg of 10 healthy volunteers. This will be used clinically in a number of studies looking at salt loading in hypertension, dialysis, Gordons syndrome, Geiltmans syndrome, as well as others. |
Collaborator Contribution | Provided funding for a post-doc. An additional grant from UCL BRC provided money to develop sodium phantoms. UCLH clinical partners provided access to the Multi-nuclear scanner free of charge UCLH clinical partners performed image analysis for the validation paper |
Impact | Paper in revision for Magnetic resonance in medicine Abstract at ISMRM conference 2022. Talk at ISMRM multinuclear workshop 2023. |
Start Year | 2022 |
Description | Development of novel sequences for abdominal MRI imaging |
Organisation | University College Hospital |
Department | University College London Hospitals Charity (UCLH) |
Country | United Kingdom |
Sector | Charity/Non Profit |
PI Contribution | Have an innovate grant to develop novel sequences for abdominal imaging in crones disease in children Have an additional Michael J Fox grant to develop novel sequences for abdominal imaging in parkinsons disease patients Begun work on 2D sequences with compressed sensing reconstructions Some initial work on 3D sequences |
Collaborator Contribution | access to Motilent software for analysis of data access to database of abdominal patient data for training of ML networks |
Impact | Paper on super-resolution to be submitted imminently Grant fro innovate UK Grant from Michael J Fox |
Start Year | 2021 |
Description | Machine Learning in the abdomen |
Organisation | Nationwide Children's Hospital |
Country | United States |
Sector | Hospitals |
PI Contribution | We will provide machine learning frameworks and models to train networks |
Collaborator Contribution | Nationwide will provide data to train the networks on |
Impact | Nationwide are currently collecting data |
Start Year | 2020 |
Description | Machine learning for segmentation of Cardiac dog data |
Organisation | Royal Veterinary College (RVC) |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | We will develop machine learning tools for automatic segmentation of the heart in dogs, as well as tools to extract ROIs and perform shape analysis |
Collaborator Contribution | RVC will provide data and segmentations of dog data |
Impact | Tools developed to extract data, and initial segmentation using human-trained networks performed. |
Start Year | 2020 |
Description | Machine learning for segmentation of the heart |
Organisation | Sydney Hospital |
Country | Australia |
Sector | Hospitals |
PI Contribution | This is a multi-site, multi-vendor study. We have performed preliminary data from Siemens vendor. This shows good segmentation quality We will provide machine learning frameworks, Siemens data (SAX on 100 pediatric patients) and tools to anonymise data, and process input and output data. We will perform training of networks and integrate these into final segmentation tools. |
Collaborator Contribution | Sydney hospital will provide 100 GE short axis (SAX) data sets as well as 100 Philips SAX data sets in pediatric patients. They have completed ethics for this, and started data collection. |
Impact | Ethics to collect data. Started data collection and data analysis. |
Start Year | 2020 |
Description | Siemens Healthineers |
Organisation | Siemens Healthcare |
Country | Germany |
Sector | Private |
PI Contribution | We developed a deep-learning method of removing artefact from highly under sampled MRI data |
Collaborator Contribution | Siemens have integrated this into a Works-in-progress package which works on the scanner. We have together been working to distribute this package to ~8 other international sites to perform a multi-site validation study |
Impact | Currently distributed WIP to other international sites to perform validation study, including: - Children's Healthcare of Atlanta, Georgia. USA - Nationwide Children's Hospital, Columbus, Ohio. USA - Royal Free Hospital, London. UK - Ospedale Pediatrico Bambino Gesù, Rome. Italy - Lund University, Sweden - Children's Hospital of Philadelphia, Philadelphia. USA Initial results are promising, however still ironing out a few bugs before we start acquiring data for large study. |
Start Year | 2020 |
Description | Speeding up clinical scanning |
Organisation | Lund University |
Country | Sweden |
Sector | Academic/University |
PI Contribution | Providing fast scanning technologies to do real-time fetal imaging, as well as fast flow imaging in MRI |
Collaborator Contribution | Performing fetal MRI, and sharing data Providing segmentation software - Segment |
Impact | No outputs to date. A book chapter pending. As well as a large multi-site international study |
Start Year | 2020 |
Title | MEthod to reduce whole heart MRI by x3.5 |
Description | Developed a deep learning methodology to perform super resolution imaging on whole heart MRI. This allows reduction in scan time by x3.5 compared to conventional imaging. This was validated in 40 prospective patients. It is being used at GOSH and we are looking at distributing to other sites. |
Type | Diagnostic Tool - Imaging |
Current Stage Of Development | Small-scale adoption |
Year Development Stage Completed | 2020 |
Development Status | Under active development/distribution |
Impact | Reduced scanning times. Improved patient comfort. Increased patient throughput |
Description | ISMRM conference invited talk: "Challenging Nyquist:?Compressed Sensing & Low-Rank Models" |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | Invited talk to ISMRM international conference. Educational talk "Challenging Nyquist: Compressed Sensing & Low-Rank Models" 200-300 in audience. |
Year(s) Of Engagement Activity | 2022 |
URL | https://submissions.mirasmart.com/ISMRM2022/Itinerary/ConferenceMatrixEventDetail.aspx?ses=ET-07 |
Description | ISMRM conference talk |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | ISMRM conference; talk given on super-resolution whole heart imaging work |
Year(s) Of Engagement Activity | 2020 |
Description | Invited Talk at international conference: SCMR (society for cardiovascular imaging) |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | An invited talk to present as faculty member for the 2021 SCMR Scientific Sessions. Session title: Emerging CMR Methods - Motion Correction & Rapid Imaging. My talk title: Real-time CMR. Mixed session with 2 educational talks and 5 scientific abstracts. |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.eventscribe.net/2021/SCMR/ |
Description | Invited talk for Advanced Image Reconstruction Methods Workshop: "Machine Learning for Image Reconstruction in Magnetic Resonance Imaging" |
Form Of Engagement Activity | A formal working group, expert panel or dialogue |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Postgraduate students |
Results and Impact | Invited talk for Advanced Image Reconstruction Methods Workshop: "Machine Learning for Image Reconstruction in Magnetic Resonance Imaging" Teaching and networking |
Year(s) Of Engagement Activity | 2022 |
URL | https://www.ccpsynerbi.ac.uk/node/322 |
Description | Invited talk for international conference SCMR: "Deploying Advanced Reconstruction Methods" |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Invited talk for international conference SCMR: "Deploying Advanced Reconstruction Methods" Audience is academics and clinicians working in Cardiac MRI |
Year(s) Of Engagement Activity | 2023 |
URL | https://www.eventscribe.net/2023/SCMR/ |
Description | Invited talk: "Applications of Machine Learning in MRI for Congenital Heart Disease" as part of the SCMR paediatric/congenital heart disease Machine learning teaching |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Organised by the SCMR Peds/CHD Machine Learning subcommittee (which I chair), this was an educational talk, primarily to clinicians who have no/little experience in th use of machine learning, but an interest in its use, particularly in congenital heart disease. What it can do, how to do it, how effective it is. |
Year(s) Of Engagement Activity | 2020 |
URL | https://scmr.peachnewmedia.com/store/provider/custompage.php?pageid=30 |
Description | Organised a series of 4 workshops on Machine Learning in Congenital Heart Disease in MRI |
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 | I organised and chaired all 4 workshops: Workshop 1. General principles and theory of machine learning Workshop 2. A recap plus Part 1 of a classification task in CHD Workshop 3. Part 2 of a classification task in CHD and recap Workshop 4. A segmentation task in CHD The workshops were reasonably well attended. With 36 / 38 / 44 / 31 people registering for the four workshops respectively. |
Year(s) Of Engagement Activity | 2022,2023 |
URL | https://github.com/mrphys/MLinCHD_Workshop |
Description | SCMR conference: "How I Do It: CMR Physics" |
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 | Talk and Q&A session about background, how to implement in practise and the advantages/disadvantages/problems of fast MRI in the clinical environment. |
Year(s) Of Engagement Activity | 2022 |
Description | School visit: Primary school |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Schools |
Results and Impact | Visited Pirton Primary school. Spent time in 5 classrooms demonstrating science. (1hr in each classroom) Spoke to children from Reception- year 6 |
Year(s) Of Engagement Activity | 2023 |
Description | UCL Medical Physics CDT Seminar |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Postgraduate students |
Results and Impact | CDT seminar about career to date, and balance with family Given to ~the 60 PhD students and senior members of Medical Physics department at UCL (not my department) More female attended than normally seen |
Year(s) Of Engagement Activity | 2020 |
Description | UCL careers talk |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Postgraduate students |
Results and Impact | A talk to a UCL society called The UCL Review. Their idea is to create a UCL student-run peer-reviewed journal, based on projects that students pursue in their own time. This is to give students a better understanding of the peer-reviewing and publishing process, while also allowing them the opportunity to gain experience in writing scientific articles. I spoke to them about career development within academic, and balancing a family life. |
Year(s) Of Engagement Activity | 2021 |
URL | https://www.instagram.com/theuclreview/ |
Description | UCLH BRC patient engagement |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Patients, carers and/or patient groups |
Results and Impact | UCLH BRC Stage 2 Reapplication - CVD Theme PPI/E Session Talk to patients about the research that I have done under the BRC grant funding. Thinking about reapplication for UCLH BRC and what I have contributed to and had an impact upon |
Year(s) Of Engagement Activity | 2021 |
Description | UCLH NIHR BRC Cardiovascular Diseases Theme Science Day - talk |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | Local |
Primary Audience | Other audiences |
Results and Impact | Talk to the local institute about our work to date, what the funding has supported and why we should continue to be supported in the next round. |
Year(s) Of Engagement Activity | 2022 |