The researchers, from the University 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.
The results 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.”
The 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.
The 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.
The 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.
The 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.
The research was supported in part by the European Union, the European Research Council, the Engineering and Physical Sciences Research Council, Academy of Medical Sciences/The Health Foundation, and the National Institute for Health Research.
The study was reported in The Lancet Digital Health.
Landmark breakthrough in understanding Alzheimer’s
Brain cells vulnerable to Alzheimer’s Disease have been identified for the first time, in a breakthrough scientists hope could lead to targeted treatments to boost the brain’s resilience.
It has so far remained unknown in Alzheimer’s research why some brain cells succumb to the disease years before symptoms first appear, while others seem unaffected by the degeneration surrounding them until the disease’s final stages.
Now, in a groundbreaking study, the neurons that are among the first victims of the disease – accumulating toxic ‘tangles’ and dying off earlier than neighbouring cells – have been identified for the first time.
“We know which neurons are first to die in other neurodegenerative diseases like Parkinson’s disease and ALS, but not Alzheimer’s,” says co-senior author Martin Kampmann, associate professor in the UCSF Institute for Neurodegenerative Diseases.
“If we understood why these neurons are so vulnerable, maybe we could identify interventions that could make them, and the brain as a whole, more resilient to the disease.”
Alzheimer’s researchers have long studied why certain cells are more prone to producing the toxic tangles of the protein known as tau, whose spread through the brain drives widespread cell death and resulting progressive memory loss, dementia, and other symptoms.
But researchers have not looked closely at whether all cells are equally vulnerable to the toxic effects of these protein accumulations.
“The belief in the field has been that once these trash proteins are there, it’s always ‘game over’ for the cell, but our lab has been finding that that is not the case,” said Lea Grinberg, senior co-author and associate professor in the UCSF Memory and Ageing Centre.
“Some cells end up with high levels of tau tangles well into the progression of the disease, but for some reason don’t die.
“It has become a pressing question for us to understand the specific factors that make some cells selectively vulnerable to Alzheimer’s pathology, while other cells appear able to resist it for years, if not decades.”
To identify selectively vulnerable neurons, the researchers studied brain tissue from people who had died at different stages of Alzheimer’s disease, obtained from the UCSF Neurodegenerative Disease Brain Bank and the Brazilian BioBank for Ageing Studies.
The São Paulo-based biobank collects tissue samples from a broad population of deceased individuals, including many without a neurological diagnosis whose brains nevertheless show signs of very early-stage neurodegenerative disease, which is otherwise very difficult to study in humans.
The team studied tissue from ten donor brains using a technique called single-nucleus RNA sequencing, which let them group neurons based on patterns of gene activity.
In a brain region called the entorhinal cortex, one of the first areas attacked by Alzheimer’s, the researchers identified a particular subset of neurons that began to disappear very early on in the disease.
Later in the course of the disease, the researchers found, a similar group of neurons were also first to die off when degeneration reached the brain’s superior frontal gyrus.
“These findings support the view that tau buildup is a critical driver of neurodegeneration, but we also know from other data from the that not every cell that builds up these aggregates is equally susceptible,” adds researcher Kun Leng.
“Our discovery of a molecular identifier for these selectively vulnerable cells gives us the opportunity to study in detail exactly why they succumb to tau pathology, and what could be done to make them more resilient.
“This would be a totally new and much more targeted approach to developing therapies to slow or prevent the spread of Alzheimer’s disease.”
Patients enabled to take control of recovery through new programmes
Two new Recovery Facilitation Programmes (RFP) designed to empower people to take greater control of their recovery and enable them to better manage their conditions have been launched.
Energise Health’s six-week programmes, Energise Recovery and Energise Recovery 4Life, equip both recently-diagnosed people and those living with long-term conditions with the knowledge and skills they need to make beneficial and lasting changes.
Energise Recovery – for those at an early stage of recovery – and Energise Recovery 4Life – for those at least six months into their recovery journey – are online programmes that offer live teaching sessions on a range of topics, alongside practical activities and guided coursework.
Energise Health has been created by Nurse Pain Specialist Dr Dee Burrows and Occupational Therapist Victoria Collins, who brought together years of expertise to develop these programmes, which they have seen, from their own experiences, are badly needed.
“The concept came from a really challenging case we were both working on, where we realised that had this particular client been given access to something like this at an early stage in their recovery, it would have prevented so many secondary complications,” says Victoria.
The programmes – devised over 18 months, in consultation with experts in the field – aim to educate participants in how to tackle and improve issues around pain, stress, depression, poor sleep and lack of confidence in daily activity. Participants are shown how to adopt a bespoke range of strategies that they can incorporate into their daily lives to help them manage.
Although the business launched during the COVID-19 pandemic, unlike many initiatives that were taken online out of necessity, Energise Recovery and Energise Recovery 4Life were intentionally developed as online programmes.
“We designed this to be online as we wanted a facilitated group-based programme,” says Dee.
“And when you are supporting people who are living with injuries or conditions, their recovery is best facilitated if they have the energy to spend on it, rather than exhausting themselves through travel. It is also a more environmentally friendly model, which is important to both of us.
“We can have people from across the country, whether Edinburgh, Leeds, or Cornwall coming together in a way that will benefit them individually and collectively. We look forward to sharing it with more people.”
Energise Recovery and Energise Recovery 4Life introduce participants to a range of strategies from mindfulness to Tai Chi, belly breathing to sleep management, diet to exercise and connecting with others, all backed by a comprehensive handbook and activity diary.
“We are enabling people to try a range of different strategies – all of which have been carefully chosen for this purpose, determine which ones they want to pursue and learn how to integrate them into their daily routine,” says Victoria.
“We enable them to develop a personalised toolkit, with strategies to manage their conditions. Participants can develop their own script. We are empowering them to find out what works for them.”
In the six-month pilot of both programmes, engagement levels were 100 per cent in terms of both session attendance and self-reporting, with ongoing success seen in terms of individual outcomes. On average, participants started their programme with 3.75 self-management strategies, rising to 26.25 at programme completion.
“What we do is based on the principles of hope, engagement, support and self-management, and the desire to change is something we look for when accepting participants,” says Dee.
Victoria says: “The programmes are a foundation. We provide high quality resources and links for people to learn more and develop if they wish, and, through our teaching, explain key components and how they might be applied. It is bitesize and digestible.
“We are enabling people to enhance their ability to self-manage. By adopting the strategies into their lives, we have already seen how this can give individuals hope for the future and be of great benefit to their mental, social and physical wellbeing.”
Dee adds: “While the early stage Energise Recovery Programme will always give the best possible chance of recovery, Energise Recovery 4Life can be equally beneficial for those with long-term conditions, including, for instance, Long Covid
“We have noticed that some participants do better with their clinical interventions when they have completed the Programme as a foundation and have a toolkit of strategies in place. It can also, however, work well in tandem with, or after clinical interventions.”
Concussion substitutions approved in football – but move ‘doesn’t go far enough’
Years of campaigning for concussion substitutions to be introduced into football look set to deliver some success, with Premier League clubs preparing to adopt the policy to help address the need to protect players from the effects of head injury.
In a trial move, expected to take effect from fixtures next week, teams can use up to two substitutes in the event of head injuries, which will be in addition to the usual three substitutions that can be made in a normal match.
The substitutions – which will be permanent and not for 10-minute durations as in rugby, to allow for players to leave the pitch for medical assessment and return if deemed able – are expected to be approved at a meeting of the Premier League tomorrow.
Pressure has been mounting on football to address the issue of players suffering concussion and head injuries during matches, with on-pitch medics having to make decisions in three minutes on a player’s ability to continue, returning him to the pitch, or else removing him from the match completely.
The Premier League will become the first league to adopt concussion substitutes, and the finer details are currently being agreed with FIFA ahead of their expected introduction in a matter of days.
However, brain injury charity Headway argue that the move still does not go far enough in awarding protection to players, and argued permanent substitutions are not the way forward.
“We’ve been pushing for many years to bring football up to date with other sports in terms of concussion substitutes, but this plan involves permanent substitutes rather than concussion substitutes,” deputy chief executive Luke Griggs tells NR Times.
“So in that sense, it’s a bit disappointing.
“The FA chief executive said in December they needed to explain why permanent substitutes are better than temporary substitutes in this situation, but that has not happened.”
While it is a step forward that players are being protected, say Headway, the 10-minute alternative that works in sports like rugby has much greater benefits.
“In sounds great that football are introducing this measure which has been needed for a long time, but in practice, the medical assessment of the player is still going to have to be made in that three minute window on the pitch, rather than in the quiet confines of the dressing room if you had ten minutes,” says Luke.
“You also need a degree of honesty from the players in being able to assess them properly, and for them to say they feel nauseous and have blurred vision after a collision. If they know they are going to be taken off for the whole match, rather than the potential to return after ten minutes, then they might not want to be so honest.
“Of course we realise that even in ten minutes some symptoms may not present themselves, and it could be 24 hours later or maybe longer, ten minutes off the pitch to make an assessment is an awful lot better than three minutes on it.”
Interviews5 months ago
The neuropsychologist teaching tai chi
Legal7 months ago
Assessments in the virtual world
News5 months ago
A game-changer in rehab exercise
More headlines10 months ago
Frontal lobe paradox – how can we best help service users?
News8 months ago
“Because rehab won’t wait”
News8 months ago
Meet the Moodmemo…
More headlines5 months ago
Brain injury case study: Simon’s story
News9 months ago
A 20-year adventure in rehab robotics