Measuring brain age in seconds, or bringing new clinical treatments for diabetes and schizophrenia December 23, 2016 Source: Arterial Network Using MRI scans to determine brain age has been a very time consuming process. Now, the AI ​​machine only takes a few seconds to complete the test. Human cognitive ability declines with age. Neuroscientists have long discovered that this decline is related to changes in brain anatomy. There is no doubt that brain MRI images do not indicate signs of aging, let alone determine "brain age." Differences between brain age and chronological age can reveal the onset of conditions such as dementia. Get accurate brain age data in seconds However, MRI image analysis is a lengthy process because MRI data must be processed extensively to be used to analyze natural aging. Pre-processing involves removing non-brain tissue such as skulls from the image; distinguishing between white matter, gray matter, and other tissues; and removing image artifacts and various data smoothing techniques. All of this data can be processed for more than 24 hours, making it difficult for doctors to incorporate the patient's brain age into clinical diagnosis. All of this is due to Giovanni Montana and his team's research at King's College London. The team is using raw data from MRI scanners to train deep learning machines to measure brain age. With deep learning techniques, clinicians can get accurate brain age data in seconds. Sometimes the patient has not withdrawn from the scanner and the results are coming out. The method is based on a standard deep learning technique. In the process of training the deep learning machine, Montana used MRI brain scan images of more than 2,000 normal people. These people are between the ages of 18 and 90 and do not have any neurological diseases that may affect the age of the brain. So their brain age should match their chronological age. All scan results are standard T1-weighted scans performed by modern MRI scanners. The patient's chronological age is indicated on each scan. The team used 80% of the images to train a convolutional neural network to measure a person's age and scan his brain. Then they used another 200 images to verify the process. Finally, they tested the brain ageing effects of neural networks with images that were not yet learned from 200 machines. At the same time, the team also compared deep learning methods with conventional brain age determination methods. This requires a lot of image processing to identify white matter and gray matter in the brain, and then use Gaussian process regression for statistical analysis. The comparison results are very interesting. By analyzing the pre-processed data, both deep learning and Gaussian process regression accurately yielded the patient's chronological age. Both methods have errors of less than five years. Rapid measurement of brain aging may improve diabetes and schizophrenia therapy Despite this, in-depth learning has shown significant advantages when analyzing raw MRI data. It yields the correct brain age with an average error of only 4.66 years. In contrast, the standard method of Gaussian process regression performed poorly in this test, giving only a rough brain age with an average error of about 12 years. In addition, deep learning analysis can be completed in a matter of seconds compared to the 24-hour pretreatment time required for standard methods. The data processing work performed by the deep learning machine is only to ensure the consistency of image orientation and voxel size between images. This has had a major impact on doctors. Montana and colleagues said: "This software can help clinicians obtain age data based on brain age prediction during MRI scans." The team also compared images from different scanners to prove that the technology can be applied to images taken by different scanners around the world. By comparing the brain ages of twins, they also studied the correlation between brain age and genetic factors. Interestingly, the results show that correlations decrease with age and the effects of environmental factors become more pronounced over time. This also proposes a new research direction. Such an impressive study is likely to have a huge impact on the clinician's diagnostic approach. Numerous studies have shown that conditions such as diabetes, schizophrenia and traumatic brain injury are associated with accelerated brain aging. Therefore, a rapid and accurate measure of brain aging may have a major impact on the clinical treatment of these diseases. Montan and colleagues said: "The brain predicts age to represent an accurate, reliable, and genetically valid phenotype that may be used as a biomarker for brain aging." Halal Empty Capsule Size 00,Empty Gelatin Halal Capsule,Halal Empty Gelatin Capsule,Halal Gelatin Capsule Empty Ningbo Jiangnan Capsule Co., Ltd. , https://www.ningbocapsule.com
Measuring brain age in seconds, or bringing new clinical treatments for diabetes and schizophrenia