MRI Image Technique Predicts Early Onset Of Alzheimer's Disease In Patients With Mild Memory Problems

Armen Hareyan's picture

MRI Image Technique

Using new MRI techniques to analyze tissue composition and structure in the brain, researchers detected mild cognitive disorder, a condition in which patients suffer mild memory problems and is often an early symptom of Alzheimer's disease.

"This is important because detecting this kind of brain abnormality in its early stages with these techniques could have pivotal importance for the early detection and management of AD," said lead author of the study Cristos Davatzikos, MD, Chief of the Biomedical Image Analysis Section in Penn's Department of Radiology. "The diagnostic power of this technique could work hand-in-hand with the new drugs currently under development that target the early stages of AD before irreversible brain tissue damage sets in."

In the first-of-its-kind study, researchers created a unique picture of patients' brains by combining and analyzing MRI images measuring the density and volume of various different tissues and their spatial distribution within the brain. From these images patterns associated with MCI were detected. Using this technique, researchers were able to not only to detect, with 100 % accuracy, those patients in the study with cognitive impairment from those with normal cognitive function, but also those predicted, with 90 percent accuracy, those patients with increasing onset of MCI, thereby demonstrating the diagnostic power of the new tool.


Up to now, the predictive power of MRI images relative to MCI and AD have been limited because they compared region-by-region evaluations over time and were not able to be applied on an individual patient basis. The technique designed by the researchers provides, for the first time, the sensitivity and specificity for individual patient diagnosis of MCI leading to AD. Not only are the abnormalities in the MCI brain detected earlier than other imaging techniques, but can be identified and measured even before the patient's mental processes deteriorate to the point of clinical symptoms.

The ability to accurately classify even mildly impaired individuals from a single cross-sectional MRI is significant because it contrasts with prevailing thinking that effective prediction of early stages of AD will require measurement of longitudinal brain changes. Frequent follow-up is often difficult and expensive in a clinical setting. This study demonstrated that an accurate diagnosis can be made from a single MRI image.

"Our study is the first to show that by using MRI techniques to classify tissue patterns in the brain provides very high diagnostic accuracy on an individual basis," added Davatzikos.

Prevalence of AD doubles every 5 years of life after the age of 60, with more than four million Americans affected. Definitive diagnosis requires postmortem identification of amyloid plaques and neurofibrillary tangles linked to the disease. Patients with MCI, which include memory problems that do not meet criteria for dementia, convert to AD with rates of 6-15% annually. This new method of analysis using MRI imaging to detect tissue patterns, promises to aid in the early diagnosis and monitoring of MCI and AD.

PENN Medicine is a $2.9 billion enterprise dedicated to the related missions of medical education, biomedical research, and high-quality patient care. PENN Medicine consists of the University of Pennsylvania School of Medicine (founded in 1765 as the nation's first medical school) and the University of Pennsylvania Health System.

Penn's School of Medicine is ranked #2 in the nation for receipt of NIH research funds; and ranked #3 in the nation in U.S. News & World Report's most recent ranking of top research-oriented medical schools. Supporting 1,400 fulltime faculty and 700 students, the School of Medicine is recognized worldwide for its superior education and training of the next generation of physician-scientists and leaders of academic medicine.