Get involved with research

MIDI (MR Imaging Abnormality Deep Learning Identification) (MIDI)

The study involves the development and testing of an AI tool that can identify abnormalities using patient head scans carried out 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.


To develop a decision-making tool using a convolutional neural network that identifies abnormalities on brain MRI scans:

Local Principal Investigator – Dr David Sallomi