Artificial Intelligence Can Detect Alzheimer’s Disease in Brain Scans Six Years before a Diagnosis

Using a common brain scan, researchers used a machine-learning algorithm to diagnose Alzheimer’s in its early stage, about six months prior to a clinical diagnosis. This allows doctors to offer treatment.

Alzheimer’s has no known cure, but some drugs have been used in the recent years to help control the progression of this condition. However, to be effective these treatments should be given in Alzheimer’s early stages. This has motivated scientists to come up with ways of diagnosing the condition early.

The study:
  • A recent study by Jae Ho Sohn, UC San Francisco’s resident in the Department of Radiology and Biomedical Imaging, combined machine-learning with neuroimaging to predict whether a patient would get Alzheimer’s disease when they faced a memory impairment for the first time.
  • Sohn fed the algorithm with images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI)-a huge public database containing PET scans of patients diagnosed with no disorder, mild cognitive impairment or Alzheimer’s disease. Later on, the algorithm started learning on its own regarding the features that can predict Alzheimer’s disease and those that can’t.
  • After training the algorithm on 1921 scans, the researchers tested it on two other datasets to assess its performance. First, they used 188 images obtained from the same ADNI database, but were not introduced to the algorithm yet. Second, they took scans from 40 patients who had a possible cognitive impairment.
  • The results were excellent. The algorithm correctly identified 92% of patients who had Alzheimer’s disease in the first dataset and 98% in the second one.
  • The algorithm made correct predictions about 75.6 months (6.3 years) before patients received their diagnosis.
Sohn now wants to calibrate and set the algorithm on bigger and more diverse datasets from various countries and hospitals.

If it can withstand the tests, neurologists can use it as diagnostic and predictive equipment for Alzheimer’s disease. This can provide treatments to the patients sooner.

Location: Irving, TX, USA

Comments

Post a Comment

Popular posts from this blog

The Professionals Who Perform CT Scans at Centers in Texas

Computed Tomography scans use computer-enhanced X-rays to distinguish between tissue, bone, fat, fluid, and gas to get clear results that allow physicians to diagnose a problem and prescribe an appropriate course of treatment. CT scans are used for detecting and diagnosing brain tumors, blood clots, stroke, cancer, trauma, pancreatic disease, back problems, and enlarged lymph nodes. They provide a quick view inside the body to help doctors with the diagnosis. Computed tomography (CT) imaging requires team effort to provide the best results. The computed tomography patient care team in a full-service CT center is headed by a radiologist. The other members of the team include CT technologists and nurses who are specialists in administering injections. Each professional has important responsibilities for successful scan results. Here are the roles performed by board-certified clinical and CT professionals: • Clinical Radiologists – They are highly trained specialist medical doct
Read more

Cancer in Children Can Now Be Detected Faster

Generally, children find it difficult to sit still for long periods. This can make it difficult for doctors taking MRI/CT scans to get accurate results through conventional methods, the scan time averages an hour or longer. However, researchers from Stanford have found a way to reduce the time to 30 minutes or less per region. As an added bonus, this method also picks up more details. The patients in this study had leukemia, lymphoma, or sarcoma. • Ten participants: 10 pediatric cancer patients (5 boys and 5 girls) who had undergone chemotherapy, at an average of 18.7 months prior underwent PET/MR imaging . Head and joint MRI were performed at the same time with PET data acquisition being done as well, along with cardiac imaging, with and without enhancing the images. • Scanning time greatly reduced: The technicians were able to complete the brain scans in just 27 minutes, the bone scans in a time of 15 minutes as well as manage to do cardiac imaging within 19 minutes, a drast
Read more

Can CT Scans be used in Diagnosing COVID-19?

COVID-19 is often diagnosed through RT-PCR testing. Now some experts are arguing that CT scans can help to diagnose Covid-19 . But others disagree with them. The covid-19 epidemic continues to spread all over the world, killing many people as nations strive to find cure or vaccination. Diagnosing people with SARS-CoV-2 early is key to combating the spread of the disease. Once you are diagnosed, you can limit your physical contact with other people and slow down its spread. To many people, reverse transcriptase polymerase chain reaction (RT-PCR) is the gold standard for Covid-19 diagnosis. RT-PCR is a molecular biology technique that identifies material specific to the SARS-CoV-2 virus. However, RT-PCR does not provide 100% accuracy, which has raised concerns about the false-negative and false-positive results. So, is it possible that CT scans can serve as an adjunct to RT-PCR diagnosis? CT scans combine a series of images that reflect abnormal cells' metabolic activi
Read more