ICL & CU researchers develop an AI algorithm that recognises various types of brain injuries.

Imperial College London (ICL) and Cambridge University (CU) researchers have developed an AI algorithm that recognises various types of brain injuries. The algorithm, which has been clinically tested and approved on CT scans, can segment and distinguish multiple brain lesions; therefore, the results could be beneficial in large-scale research studies, to develop additional personalised therapies for head injuries.

However, Cambridge University outlined that different types of blood, in or around the brain, can lead to different outcomes; therefore, radiologists will often make judgments to decide the best suitable approach for the patient.

The tool, trained on over six-hundred different CT scans, shows brain lesions of different types and sizes.

Professor David Menon, Cambridge’s Department of Medicine and co-senior author, stated: “CT is an incredibly important diagnostic tool, but it’s rarely used quantitatively. Often, much of the rich information available in a CT scan is missed and as researchers, we know that the type, volume and location of a lesion on the brain are important to patient outcomes. We hope it will help us identify which lesions get larger and progress and understand why they progress so that we can develop more personalised treatment for patients in future.”

Dr Virginia, Cambridge’s Department of Medicine and co-first author, stated: “Detailed assessment of a CT scan with annotations can take hours, especially in patients with more severe injuries. We wanted to design and develop a tool that could automatically identify and quantify the different types of brain lesions so that we could use it in research and explore its possible use in a hospital setting.”