Researchers develop AI algorithm to spot brain injuries

But they never tell us how fast it is but then doing a CT scan just by itself can take 30-60 minutes. So when time is brain you just might want your hospital to use these much faster diagnosis tools. Up to you if you want to save 2 million  neurons per minute.  In the 90 minutes it took for me to get to the hospital and get tPA I lost 171 million neurons. And because absolutely nothing was done to stop the neuronal cascade of death in the first week, my doctors killed off another 5.4 billion neurons.  With only 171 million dead neurons I could have easily recovered. 

Hats off to Helmet of Hope - stroke diagnosis in 30 seconds   February 2017

 

Microwave Imaging for Brain Stroke Detection and Monitoring using High Performance Computing in 94 seconds March 2017

 

New Device Quickly Assesses Brain Bleeding in Head Injuries - 5-10 minutes April 2017

The latest here:

Researchers develop AI algorithm to spot brain injuries

Researchers develop AI algorithm to spot brain injuries

London, May 16 (IANS) Researchers claim they have developed an artificial intelligence (AI) algorithm that can detect and identify different types of brain injuries.
The research team 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, published in the journal ''The 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.
"CT is an incredibly important diagnostic tool, but it''s rarely used quantitatively," said study co-senior author David Menon, Professor at Cambridge University in the UK.
"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," Menon added.
The researchers 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 team 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 the research questions we couldn''t answer before. We want to use it on large datasets to understand how much imaging can tell us about the prognosis of patients," said study researcher Virginia Newcombe.
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 said that it could have potential use in emergency rooms, helping get patients home sooner. Of all the patients who have a head injury, only between 10 and 15 per cent 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 authors wrote.