Alzheimer’s disease (AD) is a chronic neurodegenerative disease characterized by progressive dementia. Approximately 50 million people have AD and related forms of dementia, and someone in the world is diagnosed with dementia every 3 seconds ("World Alzheimer Report -The state of the art of dementia research: new frontiers," 2018). AD causes substantial pain to patients and their families and imposes an extraordinary financial burden, with global estimates for costs attributed to dementia of approximately $2.54 trillion in 2030 and $9.12 trillion in 2050.
Despite its prevalence, however, AD has remained a mystery. Thus, accurate data-driven methods that can classify and characterize the neural features of AD would be powerful clinical tools.
Recently, the Brainnetome Research Center of the Institute of Automation of the Chinese Academy of Sciences has led the development of a research framework for early detection of AD based on hippocampal radiomics. The study, published in Science Bulletin on April 3, shows that hippocampal radiomic features can be a promising stable, effective and generalizable biomarker for the diagnosis of AD and study the progression of high risk people-mild cognitive impairment (MCI). The corresponding methods can be extended to the study of other mental diseases.
Hippocampal morphological change is one of the main hallmarks of AD. However, whether hippocampal radiomic features are reproducible and robust as predictors of progression from MCI to AD dementia and provide a neurobiological foundation remains unclear.
In their search for suitable biomarkers, the scientists collected multimodal neuroimaging data for more than 1900 individuals with AD, MCI and healthy controls from six centers and ADNI. Multivariate classifier-based SVM analysis provided individual-level predictions for distinguishing AD patients from normal controls with accuracy = 88.21% with inter-site cross-validation.
After combining different levels of data, the researchers suggested that hippocampal radiomic features is related to the clinical features (e.g., apolipoprotein E (APOE) genotype, polygenic risk scores, cerebrospinal fluid (CSF) Aβ, CSF Tau), and longitudinal changes in cognition ability; more importantly, the features have a consistently altered pattern with changes in the cognitive scores over 5 years of follow-up.
The study also evaluated using this biomarker to predict diagnostic labels can be cross validated with different hospitals.
These comprehensive results suggest that hippocampal radiomic features can serve as a robust biomarker for clinical applications in AD/MCI, further provide evidence for predicting whether MCI subject would convert to AD or not based on hippocampus, without doubt has significantly meaning for early diagnosis of AD/MCI.
Website of the research tool for calculating hippocampus radiomic features is as follows: https://github.com/YongLiulab
The research was supported by the National Basic Research Program of China, the National Key Research and Development Program, the Leading Projects Program of the Chinese Academy of Sciences and the Natural Science Foundation of China, also the open project from National Laboratory of Pattern Recognition.
Full Text：
https://doi.org/10.1016/j.scib.2020.04.003
Contact:
ZHANG Xiaohan, PIO, Institute of Automation, Chinese Academy of Sciences
Email: xiaohan.zhang@ia.ac.cn