Structural Brain Imaging Phenotypes of Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD) Found by Hierarchical Clustering
Related Experiment Video
Updated: Nov 26, 2025
Symmetric Bihemispheric Postmortem Brain Cutting to Study Healthy and Pathological Brain Conditions in Humans
Published on: December 18, 2016
Mikko Kärkkäinen1, Mithilesh Prakash1, Marzieh Zare2
1A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland.
Abstract:
A hierarchical clustering algorithm was applied to magnetic resonance images (MRI) of a cohort of 751 subjects having a mild cognitive impairment (MCI), 282 subjects having received Alzheimer's disease (AD) diagnosis, and 428 normal controls (NC). MRIs were preprocessed to gray matter density maps and registered to a stereotactic space. By first rendering the gray matter density maps comparable by regressing out age, gender, and years of education, and then performing the hierarchical clustering, we found clusters displaying structural features of typical AD, cortically-driven atypical AD, limbic-predominant AD, and early-onset AD (EOAD). Among these clusters, EOAD subjects displayed marked cortical gray matter atrophy and atrophy of the precuneus. Furthermore, EOAD subjects had the highest progression rates as measured with ADAS slopes during the longitudinal follow-up of 36 months. Striking heterogeneities in brain atrophy patterns were observed with MCI subjects. We found clusters of stable MCI, clusters of diffuse brain atrophy with fast progression, and MCI subjects displaying similar atrophy patterns as the typical or atypical AD subjects. Bidirectional differences in structural phenotypes were found with MCI subjects involving the anterior cerebellum and the frontal cortex. The diversity of the MCI subjects suggests that the structural phenotypes of MCI subjects would deserve a more detailed investigation with a significantly larger cohort. Our results demonstrate that the hierarchical agglomerative clustering method is an efficient tool in dividing a cohort of subjects with gray matter atrophy into coherent clusters manifesting different structural phenotypes.
Insights
Hierarchical clustering of brain MRIs revealed distinct Alzheimer's disease (AD) subtypes and diverse patterns in mild cognitive impairment (MCI). This method effectively categorizes individuals based on brain atrophy, aiding in understanding disease progression.
Area of Science:
- Neuroimaging
- Neurology
- Computational Biology
Background:
- Alzheimer's disease (AD) and mild cognitive impairment (MCI) exhibit significant heterogeneity.
- Understanding structural brain differences is crucial for diagnosis and prognosis.
Purpose of the Study:
- To apply hierarchical clustering to magnetic resonance imaging (MRI) data to identify distinct structural phenotypes in subjects with MCI, AD, and normal controls (NC).
- To investigate the relationship between identified clusters and disease progression.
Main Methods:
- Hierarchical clustering algorithm applied to preprocessed gray matter density maps from 751 MCI, 282 AD, and 428 NC subjects.
- Gray matter density maps were adjusted for age, gender, and education before clustering.
- Longitudinal follow-up data (36 months) including ADAS slopes were used to assess progression rates.
Main Results:
- Identified clusters corresponding to typical AD, atypical AD, limbic-predominant AD, and early-onset AD (EOAD).
- EOAD subjects showed significant cortical gray matter atrophy, precuneus atrophy, and the highest progression rates.
- MCI subjects displayed marked heterogeneity, including stable MCI, rapidly progressing diffuse atrophy, and patterns mimicking AD subtypes.
- Bidirectional structural differences were observed in MCI subjects involving the anterior cerebellum and frontal cortex.
Conclusions:
- Hierarchical agglomerative clustering is an effective tool for stratifying subjects with gray matter atrophy into clinically relevant structural phenotypes.
- The observed diversity in MCI structural phenotypes warrants further investigation with larger cohorts.
- This approach can aid in a more nuanced understanding of neurodegenerative disease progression.
More Related Videos
09:38Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
Published on: November 14, 2017
12:28Abbiategrasso Brain Bank Protocol for Collecting, Processing and Characterizing Aging Brains
Published on: June 3, 2020
