̽��ֱ�� of Cambridge - Virginia Newcombe

Advanced MRI scans help identify one in three concussion patients with ‘hidden disease’

cjb250 — Thu, 08 Aug 2024 22:30:10 +0000

Around one in 200 people in Europe every year will suffer concussion. In the UK, more than 1 million people attend Emergency Departments annually with a recent head injury. It is the most common form of brain injury worldwide.

When a patient in the UK presents at an Emergency Department with head injury, they are assessed according to the NICE head injury guidelines. Depending on their symptoms, they may be referred for a CT scan, which looks for brain injuries including bruising, bleeding and swelling.

However, CT scans identify abnormalities in fewer than one in 10 patients with concussion, yet 30-40% of patients discharged from the Emergency Department following a scan experience significant symptoms that can last for years and be potentially life-changing. These include severe fatigue, poor memory, headaches, and mental health issues (including anxiety, depression, and post-traumatic stress).

Dr Virginia Newcombe from the Department of Medicine at the ̽��ֱ�� of Cambridge and an Intensive Care Medicine and Emergency Physician at Addenbrooke’s Hospital, Cambridge, said: “ ̽��ֱ��majority of head injury patients are sent home with a piece of paper telling them the symptoms of post-concussion to look out for and are told to seek help from their GP if their symptoms worsen.

“ ̽��ֱ��problem is that the nature of concussion means patients and their GPs often don’t recognise that their symptoms are serious enough to need follow-up. Patients describe it as a ‘hidden disease’, unlike, say, breaking a bone. Without objective evidence of a brain injury, such as a scan, these patients often feel that their symptoms are dismissed or ignored when they seek help.”

In a study published today in eClinicalMedicine, Dr Newcombe and colleagues show that an advanced form of MRI known as diffusion tensor imaging (DTI) can substantially improve existing prognostic models for patients with concussion who have been given a normal CT brain.

DTI measures how water molecules move in tissue, providing detailed images of the pathways, known as white matter tracts, that connect different parts of the brain. Standard MRI scanners can be adapted to measure this data, which can be used to calculate a DTI ‘score’ based on the number of different brain regions with abnormalities.

Dr Newcombe and colleagues studied data from more than 1,000 patients recruited to the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) study between December 2014 and December 2017. 38% of the patients had an incomplete recovery, meaning that three months after discharge their symptoms were still persisting.

̽��ֱ��team assigned DTI scores to the 153 patients who had received a DTI scan. This significantly improved the accuracy of the prognosis – whereas the current clinical model would correctly predict in 69 cases out of 100 that a patient would have a poorer outcome, DTI increased this to 82 cases out of 100.

dti_images_web.jpg

Whole brain diffusion tensor tractography showing healthy patient (left) and patient at two days (centre) and six weeks (right) after severe traumatic brain injury (Credit: Virginia Newcombe)

̽��ֱ��researchers also looked at blood biomarkers – proteins released into the blood as a result of head injury – to see whether any of these could improve the accuracy of the prognosis. Although the biomarkers alone were not sufficient, concentrations of two particular proteins – glial fibrillary acidic protein (GFAP) within the first 12 hours and neurofilament light (NFL) between 12 and 24 hours following injury – were useful in identifying those patients who might benefit from a DTI scan.

Dr Newcombe said: “Concussion is the number one neurological condition to affect adults, but health services don’t have the resources to routinely bring back every patient for a follow-up, which is why we need a way of identifying those patients at greatest risk of persistent symptoms.

“Current methods for assessing an individual’s outlook following head injury are not good enough, but using DTI – which, in theory, should be possible for any centre with an MRI scanner – can help us make much more accurate assessments. Given that symptoms of concussion can have a significant impact on an individual’s life, this is urgently needed.”

̽��ֱ��team plan to look in greater details at blood biomarkers, to see if they can identify new ways to provide even simpler, more practical predictors. They will also be exploring ways to bring DTI into clinical practice.

Dr Sophie Richter, a NIHR Clinical Lecturer in Emergency Medicine and first author, Cambridge, added: “We want to see if there is a way to integrate the different types of information obtained when a patient presents at hospital with brain injury – symptoms assessment, blood tests and brain scans, for example – to improve our assessment of a patient’s injury and prognosis.”

̽��ֱ��research was funded by European Union's Seventh Framework Programme, Wellcome and the National Institute for Health and Care Excellence.

Reference
Richter, S et al. Predicting recovery in patients with mild traumatic brain injury and a normal CT using serum biomarkers and diffusion tensor imaging (CENTER-TBI): an observational cohort study. eClinMed; 8 Aug 2024; DOI: 10.1016/j.eclinm.2024.102751

Offering patients with concussion a type of brain scan known as diffusion tensor imaging MRI could help identify the one in three people who will experience persistent symptoms that can be life changing, say Cambridge researchers.

Concussion is the number one neurological condition to affect adults, which is why we need a way of identifying those patients at greatest risk of persistent symptoms

Virginia Newcombe

Callista Images (Getty Images)

Diffusion tensor imaging (DTI) MRI of the human brain - stock photo

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

AI successfully used to identify different types of brain injuries

sc604 — Thu, 14 May 2020 23:42:42 +0000

̽��ֱ��researchers, from the ̽��ֱ�� of Cambridge and Imperial College London, have clinically validated and tested the AI on large sets of CT scans and found that it was successfully able to detect, segment, quantify and differentiate different types of brain lesions.

Their results, reported in ̽��ֱ��Lancet Digital Health, could be useful in large-scale research studies, for developing more personalised treatments for head injuries and, with further validation, could be useful in certain clinical scenarios, such as those where radiological expertise is at a premium.

Head injury is a huge public health burden around the world and affects up to 60 million people each year. It is the leading cause of mortality in young adults. When a patient has had a head injury, they are usually sent for a CT scan to check for blood in or around the brain, and to help determine whether surgery is required.

“CT is an incredibly important diagnostic tool, but it’s rarely used quantitatively,” said co-senior author Professor David Menon, from Cambridge’s Department of Medicine. “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.”

Different types of blood in or around the brain can lead to different patient outcomes, and radiologists will often make estimates in order to determine the best course of treatment.

“Detailed assessment of a CT scan with annotations can take hours, especially in patients with more severe injuries,” said co-first author Dr Virginia Newcombe, also from Cambridge’s Department of Medicine. “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.”

̽��ֱ��researchers developed a machine learning tool based on an artificial neural network. They trained the tool on more than 600 different CT scans, showing brain lesions of different sizes and types. They then validated the tool on an existing large dataset of CT scans.

̽��ֱ��AI was able to classify individual parts of each image and tell whether it was normal or not. This could be useful for future studies in how head injuries progress, since the AI may be more consistent than a human at detecting subtle changes over time.

“This tool will allow us to answer research questions we couldn’t answer before,” said Newcombe. “We want to use it on large datasets to understand how much imaging can tell us about the prognosis of patients.”

“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,” said Menon.

While the researchers are currently planning to use the AI for research only, they say with proper validation, it could also be used in certain clinical scenarios, such as in resource-limited areas where there are few radiologists.

In addition, the researchers say that it could have a potential use in emergency rooms, helping get patients home sooner. Of all the patients who have a head injury, only between 10 and 15% have a lesion that can be seen on a CT scan. ̽��ֱ��AI could help identify these patients who need further treatment, so those without a brain lesion can be sent home, although any clinical use of the tool would need to be thoroughly validated.

̽��ֱ��ability to analyse large datasets automatically will also enable the researchers to solve important clinical research questions that have previously been difficult to answer, including the determination of relevant features for prognosis which in turn may help target therapies.

̽��ֱ��research was supported in part by the European Union, the European Research Council, the Engineering and Physical Sciences Research Council, Academy of Medical Sciences/ ̽��ֱ��Health Foundation, and the National Institute for Health Research.

Reference:
Miguel Monteiro et al. ‘Multi-class semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study.’ ̽��ֱ��Lancet Digital Health (2020). DOI: 10.1016/S2589-7500(20)30085-6

Researchers have developed an AI algorithm that can detect and identify different types of brain injuries.

This tool will allow us to answer research questions we couldn’t answer before

Virginia Newcombe

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes