[ad_1]
Although Alzheimer's disease affects tens of millions of people around the world, it is still difficult to discover at an early stage. But researchers dealing with artificial intelligence in medicine have discovered that technology can help early diagnosis of camp disease. The California team recently published a report on its study in Radiology and showed how once a trained neural network managed to accurately diagnose Alzheimer's disease in a limited number of patients based on the visualization of images in the brain, done in the course of the year before the concerned patients is diagnosed by a doctor.
The team uses brain imaging (FDG-PET imaging) to train and test their neural network. In the FDG, images of the patient's blood circulation are injected with a radioactive type of glucose, and then its body, including the brain, is pushed towards the surface. Scientists and doctors can then use a PET check to detect the metabolic activity of this tissue, depending on how much FDG is taking.
The FDG-PET method is used to diagnose Alzheimer's disease in patients in whom the disease usually exhibits lower levels of metabolic activity in some parts of the brain. However, experts need to analyze these images in order to find evidence of the disease, and this becomes very difficult because moderate cognitive impairment and Alzheimer's disease can lead to similar results in the scan.
Therefore, the team uses 2,109 FDG-PET images from 1002 patients, 90% train their neural network and test the remaining 10%. He also performs tests with a single set of 40 patients examined between 2006 and 2016, and then compares artificial intelligence findings with the results of a group of experts who analyze the same data.
With a separate set of test data, Artificial Intelligence can diagnose Alzheimer's patients with 100% precision and with an accuracy of 82% for those who do not suffer from pressure. Forecasts can also predict over an average of more than six years. Compared with a group of doctors who looked at the same scanned images, in 57% of patients with Alzheimer's disease and those without disease – in 91%. However, differences in hardware and human performance are not as noticeable when it comes to the diagnosis of mild cognitive disorders that are not typical of Alzheimer's disease.
Researchers have found that their research has several limitations, including a small amount of test data and limited types of training data.
[ad_2]
Source link
