MIDI (MR Imaging Abnormality Deep Learning Identification)

Neurological Disorder Clinical Trial

— MIDI  

Official title:

Deep Learning for Identification of Abnormalities on Head MRI

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT04368481
• Other study ID #: KCH18-197
• Status: Recruiting
• Start date: April 1, 2019
• Est. completion date: March 31, 2025

Study information

• Verified date: April 2024
• Source: King's College Hospital NHS Trust
• Contact: MIDI Central Team
• Phone: +44(0)20 7848 9670
• Email: kch-tr.midistudy[@]nhs.net
• Is FDA regulated: No
• Study type: Observational

Clinical Trial 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.

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 information / eligibility

• Status: Recruiting
• Enrollment: 30000
• Est. completion date: March 31, 2025
• Est. primary completion date: August 31, 2024
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• All head MRI scans with compatible sequences

• > 18 years old

Exclusion Criteria:

• 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

Related Conditions & MeSH terms

• Nervous System Diseases
• Neurological Disorder

Locations

Country	Name	City	State
United Kingdom	Buckinghamshire Healthcare Nhs Trust (Stoke Mandeville)	Aylesbury
United Kingdom	Mid and South Essex NHS Foundation Trust	Basildon
United Kingdom	Bedfordshire Hospitals Nhs Foundation Trust	Bedford
United Kingdom	Betsi Cadwaladr University Health Board	Bodelwyddan
United Kingdom	East Kent Hospitals University Nhs Foundation Trust	Canterbury
United Kingdom	South Eastern Health & Social Care Trust	Dundonald
United Kingdom	Queen Victoria Hospital Nhs Foundation Trust	East Grinstead
United Kingdom	Medway Nhs Foundation Trust	Gillingham
United Kingdom	Northern Lincolnshire and Goole Nhs Foundation Trust	Grimsby
United Kingdom	Calderdale and Huddersfield NHS Foundation Trust	Huddersfield
United Kingdom	The Queen Elizabeth Hospital King'S Lynn Nhs Trust	King's Lynn
United Kingdom	Kingston Hospital Nhs Foundation Trust	Kingston
United Kingdom	NHS FIFE	Kirkcaldy
United Kingdom	Forth Valley Royal Hospital	Larbert
United Kingdom	Leeds Teaching Hospital NHS Trust	Leeds
United Kingdom	University Hospitals of Leicester Nhs Trust	Leicester
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	Guy's Hospital, Guy's and St Thomas's NHS Foundation Trust	London
United Kingdom	Kings' College Hospital	London
United Kingdom	St George's Hospital, St George's University Hospital NHS Foundation Trust	London
United Kingdom	St Thomas' Hospital, Guy's and St Thomas's NHS Foundation Trust	London
United Kingdom	Norfolk and Norwich University Hospitals Nhs Foundation Trust	Norwich
United Kingdom	Queen's Medical Centre University Hospital, Nottingham University Hospitals NHS Foundation Trust	Nottingham
United Kingdom	Princess Royal University Hospital, King's College Hospital NHS Foundation Trust	Orpington	Kent
United Kingdom	Surrey and Sussex Healthcare Nhs Trust	Redhill
United Kingdom	East Sussex Healthcare Nhs Trust	Saint Leonards-on-Sea
United Kingdom	Northern Lincolnshire and Goole Nhs Foundation Trust	Scunthorpe
United Kingdom	Mid and South Essex Nhs Foundation Trust	Southend
United Kingdom	St George'S University Hospitals Nhs Foundation Trust	Tooting
United Kingdom	Torbay and South Devon Nhs Foundation Trust	Torquay
United Kingdom	Royal Cornwall Hospitals Nhs Trust	Truro
United Kingdom	West Hertfordshire Hospitals Nhs Trust	Watford

Sponsors (2)

Lead Sponsor	Collaborator
King's College Hospital NHS Trust	King's College London

Country where clinical trial is conducted

United Kingdom, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Sensitivity and specificity of a convolutional neural network to recognise abnormalities on head MRI scans.	Sensitivity, specificity, positive predictive value, and negative predictive values.	At end of study (5-year study)
Secondary	Sensitivity and specificity of a convolutional neural network to broadly categorise abnormalities on head MRI scans.	Sensitivity, specificity, positive predictive value, and negative predictive values.	At end of study (5-year study)