AI successfully used to identify different types of brain injuries


AI successfully used to identify different types of brain injuries
Credit: University of Cambridge

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

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

Head 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 , 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 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 , 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 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.


NIH releases large-scale dataset of CT images


More information:
Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study, The Lancet Digital Health (2020). DOI: 10.1016/S2589-7500(20)30085-6

Citation:
AI successfully used to identify different types of brain injuries (2020, May 14)
retrieved 14 May 2020
from https://medicalxpress.com/news/2020-05-ai-successfully-brain-injuries.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.



loading...

Related posts:

Japan newborn gets liver stem cells in world first
Observing the world during childhood affects the rest of life
American Indians and Alaska Natives have disproportionately higher rates of CVD
Hemmung zelleigenen Enzyms: Strategie für Entwicklung antiviraler Breitbandwirkstoffe
India coronavirus death toll passes China's
AbbVie schließt Übernahme von Allergan ab
Krankheitsauslöser für Pankreatitis identifiziert - Biermann Medizin
Researchers launche clinical trial to help reduce severity of COVID-19 illness in men
Madagascar's 'green gold' against COVID-19 seeks nod beyond Africa
Chemists develop foolproof new test to track the fats we eat
Schmerzen bei Rheuma: Immer mehr Patienten nehmen Opioide ein
Parents struggling to provide for families during pandemic
Funktionelle Magen-Darm-Störungen weltweit: Höhere Prävalenz bei Frauen
Kostengünstige Netzhaut-Diagnostik per Smartphone - Biermann Medizin
Genetische Ursachen für die nicht-alkoholische Fettleber
Age, gender and culture 'predict loneliness'
WHO-Studie: Jeder fünfte Jugendliche in Deutschland ist zu dick
What does recovery from COVID-19 look like?
Madagascar reports first coronavirus death
Britain divided over reopening schools as virus rules ease
Researchers use brain imaging to demonstrate weaker neural suppression for those with autism
Some recommended cardiovascular medications prescribed less frequently to women
How mindfulness can help amid the COVID-19 pandemic
Pandemic halts vaccination for nearly 80 million children
COVID-19 trial finder provides simplified search process for COVID-related clinical trials
Sondererhebung in der Corona-Krise: Medizinklimaindex fällt auf -25,1
Europe relaxing virus restrictions but cases flare elsewhere
Preclinical study offers hope for Hirschsprung's disease
Ultraviolet light has bright future in fight against COVID-19
CD4+-Zellen auf der Überholspur
Pruritus bei Psoriasis: Phase-II-Studie mit NK1-Rezeptorantagonist
Antikörper erkennt Alzheimer-Pathogene - Biermann Medizin
Plan in place to increase production of prefilled syringes for future COVID-19 vaccine
What can a COVID-19 antibody test tell me?
Diabetes mellitus: Ein Risikofaktor für frühe Darmkrebserkrankungen
Erfolgreicher Sonderforschungsbereich zu Hepatitis-Viren und Immunabwehr
India extends nationwide lockdown until end of May
Tackling airborne transmission of COVID-19 indoors
Overcoming challenges of individuals with autism during the COVID-19 pandemic
Africa's tech scene tackles virus
Glucose levels linked to maternal mortality even in non-diabetic women
Dentists re-open in France after two-month lockdown
New research into stem cell mutations could improve regenerative medicine
Hebammenberuf wird beliebter - Biermann Medizin
Besonders fitte Antikörper sollen gegen SARS-CoV-2 helfen
COVID-19 und der neue Alltag mit Maske: Welche sind wofür geeignet?
Harnblasenkarzinom: Neuer Mechanismus der Krebsentstehung entdeckt
Europaweite Register-Studie zeigt Nutzen der Krebsgenomsequenzierung für krebskranke Kinder
Outcomes equal for AYA Hodgkin therapy at peds, adult centers
Zi-Studie zur Inanspruchnahme der Darmkrebsfrüherkennung veröffentlicht
Ten-year results display strong safety and efficacy profile for TPV device
Spain govt seeks 2-week extension of lockdown
Radiologists detail COVID-19 infection controla and radiographer protection in CT exam areas
New studies reveal extent and risks of laughing gas and stimulant abuse among young people
Anti-malarial drug shows promise for brain cancer treatment
Knochenkrebs : Die Schwäche des Tumors
Adolescent exposure to anesthetics may cause alcohol use disorder, new research shows
Coronavirus reminds you of death—and amplifies your core values, both bad and good
Deutsche Krebshilfe und die Arbeitsgemeinschaft Dermatologische Prävention raten zu neuer Normalität...
COVID-19 patients who undergo surgery are at increased risk of postoperative death
Spain revises virus death toll down by nearly 2,000
Virologe Streeck wehrt sich gegen Vorwürfe: „Doof gelaufen“
When could a COVID-19 vaccine be ready?
Using electrical stimulus to regulate genes
Multiple sclerosis risk 29% higher for people living in urban areas, new research reveals
Häufiger Harndrang als Symptom von COVID-19?
Alkoholassoziierte Leberkrankung: Potenzielle Ziele für Medikamente entdeckt
Interaktion von Immunsystem und Gehirn
UK govt boosts vaccine funding as daily virus deaths fall
Hamster tests show masks reduce coronavirus spread: scientists
AI model predicts risk for age-related macular degeneration
Researchers find potential drug treatment targets for alcohol-related liver disease
Coronavirus infections may lead to delirium and potentially PTSD
Tracking, data privacy and getting the numbers right
Bindehautinfektion durch SARS-CoV-2 unwahrscheinlich - Biermann Medizin
Russia says virus cases under 9,000 for first time since May 1
Slovenia opens borders after declaring epidemic over
Möglicher Übertragungsweg? Erstmals SARS-CoV-2 in Muttermilch nachgewiesen
'COVID toes,' other rashes latest possible rare virus signs
How the coronavirus could be prevented from invading a host cell
Coronavirus cases pass 5.25 million worldwide
We can't (and shouldn't) expect clinicians without PPE to treat COVID-19 patients
Treating skin irritations from wearing face masks
Machine that oxygenates blood may help critically ill COVID-19 patients
Apremilast bei pädiatrischer Psoriasis
How scientists hope to stop coronavirus in its tracks
Corona-relevante Vorerkrankungen hätten verhindert werden können
Mental ill health 'substantial health concern' among police, finds international study
Have a reusable face mask? Here's how to wash it the right way
Woche des Sehens 2020: "Die Zukunft im Auge behalten"
IQWiG zu Ösophagus-Chirurgie: Mit der Fallzahl steigt die Qualität
Largest study of its kind of women in labor finds nitrous oxide safe, side effects rare
US maternal health spending varies by state, driven by cost of childbirth
Problems with alcohol? 29 gene variants may explain why
Surgery and radiation do not extend survival in newly diagnosed metastatic breast cancer
Russia reports record high daily virus death toll
Europe reopens widely; China gives $2 billion to virus fight
Lagerungsschwindel – Einfache Frage zur Diagnose?
Sleep-wake disturbances can predict recurrent events in stroke survivors
Defects in developing frog brain can be prevented or repaired with bioelectric drugs

Leave a Reply

Your email address will not be published. Required fields are marked *

Next Post

First-of-its-kind-study reveals that eating prior to cardiac catheterization is non-inferior to fast

Fri May 15 , 2020
Patients undergoing cardiac catheterization are traditionally instructed to follow nothing by mouth, or nil per os (NPO), as there are no current standardized fasting protocols. The single center, randomized study presented today as late-breaking science during the SCAI 2020 Scientific Sessions Virtual Conference aimed to compare safety and clinical outcomes […]