It is estimated that Alzheimer’s disease affects more than 5 million Americans, and that number is expected to grow to 16 million by 2050. Early intervention can help lessen the most debilitating symptoms, namely memory loss and problems with reading and organizing thoughts; but unfortunately, it remains one of the most challenging neurological disorders to detect. There is no specific test for Alzheimer’s disease.
Once again, we are seeing how modern technologies could help, with researchers at the University of California at Berkeley’s Radiology & Biomedical Imaging Department and the Big Data in Radiology group (BDRAD) describing in a newly published study an AI system that can predict Alzheimer’s disease from brain scans.
The paper, titled “A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease Using 18F-FDG PET of the Brain” was recently published in the journal Radiology.
“Differences in the pattern of glucose uptake in the brain are very subtle and diffuse,” according to Dr. Jae Ho Sohn, the study coauthor. “People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process.”
And so the team trained a deep learning algorithm on 18-F-fluorodeoxyglucose positron emission tomography (FDG-PET), a specialized imaging technique in which patients are injected with FDG, a radioactive glucose compound, which allows radiologists — and an AI system — to measure uptake in brain cells through PET scans. It’s an indicator of metabolic activity.
The researchers built a corpus from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), which contains more than 2,100 FDG-PET brain images from 1,002 patients. After training on the dataset, the AI system could track minute changes in glucose uptake in certain regions of the brain that would be, under normal circumstances, difficult to detect.
In tests on a separate set of 40 imaging exams from 40 patients, the researchers’ AI system achieved 100 percent sensitivity at detecting Alzheimer’s an average of more than six years prior to the final diagnosis.
“We were very pleased with the algorithm’s performance,” Dr. Sohn added. “It was able to predict every single case that advanced to Alzheimer’s disease.”
However, the team cautioned that this technology is still in its early days, and the test sample size was relatively small. It is nonetheless a promising study and the technology developed for it could eventually be used to complement the work of radiologists. Promising stuff, when you think about it.