Credit: Radiological Society of North America
Example of fluorine 18 fluorodeoxyglucose PET images from Alzheimer’s Disease Neuroimaging Initiative set preprocessed with the grid method for patients with Alzheimer disease (AD). One representative zoomed-in section was provided for each of three example patients: A, 76-year-old man with AD, B, 83-year-old woman with mild cognitive impairment (MCI), and, C, 80-year-old man with non-AD/MCI. In this example, the patient with AD presented slightly less gray matter than did the patient with non-AD/MCI. The difference between the patient with MCI and the patient with non-AD/MCI appeared minimal to the naked eyes.

A new study published in Radiology showed that a deep learning model predicted Alzheimer’s disease with 82% specificity and 100% sensitivity about 6 years before diagnosis by using fluorine 18 fluorodeoxyglucose PET imaging studies of the brain.


According to the study published in the journal Radiology, artificial intelligence can help predict Alzheimer’s disease, a disease where early diagnosis can be pivotal for the introduction of treatments and interventions.

Timely diagnosis of Alzheimer’s disease is extremely important, as treatments and interventions are more effective early in the course of the disease. However, early diagnosis has proven to be very challenging.

“There is wide recognition that deep learning may assist in addressing the increasing complexity and volume of imaging data, as well as the varying expertise of trained imaging physicians. The application of machine learning technology to complex patterns of findings, such as those found at functional PET imaging of the brain, is only beginning to be explored. We hypothesized that the deep learning algorithm could detect features or patterns that are not evident on standard clinical review of images and thereby improve the final diagnostic classification of individuals.”

The team of researchers examined whether a deep learning algorithm could predict the final diagnosis of Alzheimer’s disease among patients who underwent so-called ‘Positron Emission Tomography’ (PET) of the brain, a sort of scanning imaging technology.

With previous research that 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.

After a process of developing a deep learning algorithm, the researchers tested the algorithm on a set of 40 imaging exams from 40 patients the AI never studied before. The AI achieved 100% accuracy at detecting the disease more or less six years prior to the diagnosis by detecting differences in glucose uptake in certain regions of the brain.

The researchers say that the algorithm could be a useful tool to complement the work of radiologists in the future, especially in conjunction with other biochemical and imaging tests, to provide an opportunity for early therapeutic intervention.