Metabolic brain changes can be identified earlier leading to timely diagnosis and intervention.
Artificial intelligence (AI) improves the ability of brain imaging to predict Alzheimer’s disease (AD), according to a study published in Radiology.
While timely diagnosis of AD is extremely important,early diagnosis has proven to be challenging. Research has linked the disease process to changes in metabolism, as shown by glucose uptake in certain regions of the brain, but these changes can be difficult to recognize.
“Differences in the pattern of glucose uptake in the brain are very subtle and diffuse,” said study co-author Jae Ho Sohn, MD, from the Radiology & Biomedical Imaging Department at the University of California in San Francisco (UCSF). “People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process.”
The study’s senior author, Benjamin Franc, MD, from UCSF, approached Dr. Sohn and University of California, Berkeley, undergraduate student Yiming Ding through the Big Data in Radiology (BDRAD) research group, a multidisciplinary team of physicians and engineers focusing on radiological data science. Dr. Franc was interested in applying deep learning (DL) to find changes in brain metabolism predictive of AD.
The researchers trained the DL algorithm using an 18-F-fluorodeoxyglucose PET (FDG-PET) scan.
The researchers had access to data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), a major multi-site study focused on clinical trials to improve prevention and treatment of this disease. The ADNI dataset included more than 2,100 FDG-PET brain images from 1,002 patients. Researchers trained the DL algorithm on 90 percent of the dataset and then tested it on the remaining 10 percent of the dataset.
Finally, the researchers tested the algorithm on an independent set of 40 imaging exams from 40 patients that it had never studied. The algorithm achieved 100 percent sensitivity at detecting the disease an average of more than six years prior to the final diagnosis.
“We were very pleased with the algorithm’s performance,” Dr. Sohn said. “It was able to predict every single case that advanced to Alzheimer’s disease.”
Algorithm Could Aid Radiologists
Although he cautioned that their independent test set was small and needs further validation with a larger multi-institutional prospective study, Dr. Sohn said that the algorithm could be a useful tool to complement the work of radiologists — especially in conjunction with other biochemical and imaging tests — in providing an opportunity for early therapeutic intervention.
“If we diagnose Alzheimer’s disease when all the symptoms have manifested, the brain volume loss is so significant that it’s too late to intervene,” he said. “If we can detect it earlier, that’s an opportunity for investigators to potentially find better ways to slow down or even halt the disease process.”
Future research directions include training the DL algorithm to look for patterns associated with the accumulation of beta-amyloid and tau proteins, abnormal protein clumps and tangles in the brain that are markers specific to AD.
Learn more: AI Predicts Alzheimers Years Before Diagnosis
Receive an email update when we add a new ARTIFICIAL INTELLIGENCE DIAGNOSTICS article.
The Latest on: Artificial intelligence diagnostics
via Google News
The Latest on: Artificial intelligence diagnostics
- Opinion: Is artificial intelligence helping or hurting us? on November 12, 2018 at 5:03 pm
and even though it is beneficial now, it won’t be later on. Kaitlyn McKinney is a freshman medical diagnostics major at the university. Kaitlyn can be reached at [email protected] […]
- Artificial intelligence in medicine: The computer knows what you need on November 12, 2018 at 6:37 am
Artificial intelligence could help through automatic pain recognition ... Several rare defects can be diagnosed by the shape of the head or the position of a child's eyes. Diagnostic mistakes can be f... […]
- Anixa Biosciences Presents Positive Data from its Artificial Intelligence Powered Liquid Biopsy for Prostate Cancer at SITC Conference on November 12, 2018 at 3:00 am
Anixa is developing both diagnostics and therapeutics to detect cancer early ... http://www.prnewswire.com/news-releases/anixa-biosciences-presents-positive-data-from-its-artificial-intelligence-power... […]
- Aberdeen academics to play part in £15.8 million artificial intelligence health research centre on November 11, 2018 at 5:12 am
A £10m funding boost was announced this week for the Industrial Centre for Artificial Intelligence Research in Digital Diagnostics (iCAIRD) by Greg Clark, UK Secretary of State for Business, Energy an... […]
- Artificial intelligence improves wrist fracture detection on November 10, 2018 at 11:07 am
Missed fractures are a common category of diagnostic errors and can cause malunion ... scored each image for the presence of fractures and used neural network artificial intelligence (AI) techniques t... […]
- DeepRadiology Wins International RSNA Medical Artificial Intelligence Challenge on November 8, 2018 at 8:50 am
DeepRadiology Educational Services are for educational purposes only and not for diagnostic or clinical use. Please contact us if you are interested in our program. DeepRadiology is a medical deep lea... […]
- The Diagnostic Artificial Intelligence Speedbump Nobody’s Mentioning on November 8, 2018 at 6:12 am
The 21st Century Cures Act is noteworthy as the first legislative attempt at regulating artificial intelligence (“AI”) in the medical field. The Act added this provision to the FDCA: (o) Regulation of ... […]
- MaxQ AI Receives FDA Clearance for Accipio Ix™ Intracranial Hemorrhage Diagnostics Intelligence Platform on November 7, 2018 at 5:14 am
510(k) clearance for artificial intelligence software ... Nov. 7, 2018 /PRNewswire/ -- MaxQ AI, a clinical diagnostics intelligence platform company, today announced that its revolutionary Accipio ... […]
- St Andrews at forefront of new £15.8m artificial intelligence centre on November 6, 2018 at 4:06 pm
The Industrial Centre for Artificial Intelligence Research in Digital Diagnostics, to be known as iCAIRD, brings together 15 partners from across academia, the NHS, and industry. The project will be b... […]
via Bing News