Artificial intelligence automatically detects types of brain injuries. Researchers note that the tool can open new forms of their therapy.
The new Artificial intelligence tool automatically detects different types of brain injuries by analyzing the results of a CT scan. The system uses a machine-learning algorithm to identify types of brain lesions and areas of tissue damaged by trauma or disease.
The differences it detects can help develop personalized treatment for brain injuries that affect up to 60 million people annually. This will save time: patients with brain injuries are usually sent for a CT scan. Radiologists then review the images to decide which drugs or operations are best to use for treatment.
The system is based on a neural network developed by researchers at Imperial College London. Scientists have trained the tool on more than 600 computer images with different types of brain lesions. They found that Artificial intelligence successfully classified individual parts of each image.
The researchers note that the tool can show how head injuries develop, revealing subtle changes that even doctors may miss. The developers believe that Artificial intelligence will even allow for new interpretations of brain injuries and help develop forms of their treatment.
“So far, we have been using this Artificial intelligence only for research, but it can also be incorporated into medical procedures when further developed. We can start with countries with limited resources and few radiologists,” said Miguel Monteiro, co-author of the study.