MIDI (MR Imaging Abnormality Deep Learning Identification)
- Conditions
- Neurological Disorder
- Registration Number
- NCT04368481
- Lead Sponsor
- King's College Hospital NHS Trust
- Brief Summary
The study involves the development and testing of an artificial intelligence (AI) tool that can identify abnormalities using patient head scans conducted for routine clinical care and research volunteer scans. A deep learning algorithm will be developed using a dataset of retrospective and prospective MRI head scans to train, validate, and test convolutional networks using software developed at the Department of Biomedical Engineering, King's College London. The reference standard will be consultant radiologist reports of the MRI head scans.
- Detailed Description
An automated strategy for identifying abnormalities in head scans could address the unmet clinical need for faster abnormality identification times, potentially allowing for early intervention to improve short- and long-term clinical outcomes. Radiologist shortages and increased demand for MRI scans lead to delays in reporting, particularly in the outpatient setting.
Furthermore, there is a wide variation in the management of incidental findings (IFs) discovered in 'healthy volunteers.' The routine reporting of 'healthy volunteer' scans by a radiologist poses logistical and financial challenges. It would be valuable to devise automated strategies to reliably and accurately identify IFs, potentially reducing the number of scans requiring routine radiological review by up to 90%, thus increasing the feasibility of implementing a routine reporting strategy.
Deep learning is a novel technique in computer science that automatically learns hierarchies of relevant features directly from the raw inputs (such as MRI or CT) using multi-layered neural networks. A deep learning algorithm will be trained on a large database of head MRI scans to recognize scans with abnormalities. This algorithm will be trained to classify a subset of these scans as normal or abnormal and then tested on an independent subset to determine its validity.
If the tested neural network demonstrates high diagnostic accuracy, future research participants and patients may benefit, as not all institutions currently review their research scans for incidental findings and clinical scans may not be reported for weeks in some cases. In both research and clinical scenarios, an algorithm could rapidly identify abnormal pathology and prioritize scans for reporting.
In summary, the aim is to develop a deep learning abnormality detection algorithm for use in both research and clinical settings.
Recruitment & Eligibility
- Status
- RECRUITING
- Sex
- All
- Target Recruitment
- 30000
- All head MRI scans with compatible sequences
- > 18 years old
- No corresponding radiologist report
- No consent for future use of the research images held within the historic database stored at The Centre for Neuroimaging Sciences (Kings College London).
- Poor image quality
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Sensitivity and specificity of a convolutional neural network to recognise abnormalities on head MRI scans. At end of study (5-year study) Sensitivity, specificity, positive predictive value, and negative predictive values.
- Secondary Outcome Measures
Name Time Method Sensitivity and specificity of a convolutional neural network to broadly categorise abnormalities on head MRI scans. At end of study (5-year study) Sensitivity, specificity, positive predictive value, and negative predictive values.
Trial Locations
- Locations (32)
South Eastern Health & Social Care Trust
🇬🇧Dundonald, United Kingdom
The Queen Elizabeth Hospital King'S Lynn Nhs Trust
🇬🇧King's Lynn, United Kingdom
Princess Royal University Hospital, King's College Hospital NHS Foundation Trust
🇬🇧Orpington, Kent, United Kingdom
Buckinghamshire Healthcare Nhs Trust (Stoke Mandeville)
🇬🇧Aylesbury, United Kingdom
Mid and South Essex NHS Foundation Trust
🇬🇧Basildon, United Kingdom
Forth Valley Royal Hospital
🇬🇧Larbert, United Kingdom
Leeds Teaching Hospital NHS Trust
🇬🇧Leeds, United Kingdom
Medway Nhs Foundation Trust
🇬🇧Gillingham, United Kingdom
Bedfordshire Hospitals Nhs Foundation Trust
🇬🇧Bedford, United Kingdom
Northern Lincolnshire and Goole Nhs Foundation Trust
🇬🇧Scunthorpe, United Kingdom
East Kent Hospitals University Nhs Foundation Trust
🇬🇧Canterbury, United Kingdom
Queen Victoria Hospital Nhs Foundation Trust
🇬🇧East Grinstead, United Kingdom
Kingston Hospital Nhs Foundation Trust
🇬🇧Kingston, United Kingdom
Kings' College Hospital
🇬🇧London, United Kingdom
Calderdale and Huddersfield NHS Foundation Trust
🇬🇧Huddersfield, United Kingdom
NHS FIFE
🇬🇧Kirkcaldy, United Kingdom
CNS, Maudsley Hospital, South London and Maudsley NHS Foundation Trust
🇬🇧London, United Kingdom
Croydon University Hospital, Croydon Health Services NHS Trust
🇬🇧London, United Kingdom
Norfolk and Norwich University Hospitals Nhs Foundation Trust
🇬🇧Norwich, United Kingdom
Guy's Hospital, Guy's and St Thomas's NHS Foundation Trust
🇬🇧London, United Kingdom
St George'S University Hospitals Nhs Foundation Trust
🇬🇧Tooting, United Kingdom
Queen's Medical Centre University Hospital, Nottingham University Hospitals NHS Foundation Trust
🇬🇧Nottingham, United Kingdom
St George's Hospital, St George's University Hospital NHS Foundation Trust
🇬🇧London, United Kingdom
Betsi Cadwaladr University Health Board
🇬🇧Bodelwyddan, United Kingdom
University Hospitals of Leicester Nhs Trust
🇬🇧Leicester, United Kingdom
St Thomas' Hospital, Guy's and St Thomas's NHS Foundation Trust
🇬🇧London, United Kingdom
Mid and South Essex Nhs Foundation Trust
🇬🇧Southend, United Kingdom
Surrey and Sussex Healthcare Nhs Trust
🇬🇧Redhill, United Kingdom
East Sussex Healthcare Nhs Trust
🇬🇧Saint Leonards-on-Sea, United Kingdom
Torbay and South Devon Nhs Foundation Trust
🇬🇧Torquay, United Kingdom
West Hertfordshire Hospitals Nhs Trust
🇬🇧Watford, United Kingdom
Royal Cornwall Hospitals Nhs Trust
🇬🇧Truro, United Kingdom