AD is a chronic neurodegenerative disease characterized by progressive dementia. Neuroimaging techniques such as magnetic resonance imaging (MRI) can help diagnose AD. Accurate data-driven methods that can classify and characterize the neural features of AD would be powerful clinical tools.

Researchers from the Institute of Automation of the Chinese Academy of Sciences and other collaborators found that hippocampal radiomic features can be a promising personalized biomarker for AD.

In their search for suitable biomarkers, researchers proposed a novel hippocampal radiomic biomarker derived from structural MRI and systematically validated its reliability using neuroimaging data from over 1,900 individuals, including more than 700 located at six sites in China and around 1,200 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.

The study showed that hippocampal radiomic features are related to the clinical features and changes in cognition ability. Long-term follow-up data in some hospitals demonstrated that the markers could be used to track the progression of the disease in high-risk subjects.

The research was published in the journal Science Bulletin.

Liu Yong, one of the researchers, said the research represents a large, interdisciplinary and interinstitutional effort between clinicians and researchers to develop and validate an AD neuroimaging biomarker.

The methodology can be extended to the study of other mental diseases. It has important clinical implications as the biomarker is promising for the early clinical diagnosis or prognostic follow-up in AD, Liu said.

Liu's team has dedicated itself to neuroimaging studies of AD that could provide relevant information to clinical practice.

The team is now focusing on further verification work among people with high risks of AD in more clinical centers, Liu added.