Related Experiment Video
Updated: Oct 5, 2025
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
Regional Radiomics Similarity Networks Reveal Distinct Subtypes and Abnormality Patterns in Mild Cognitive Impairment
Kun Zhao1,2, Qiang Zheng3, Martin Dyrba4
1Beijing Advanced Innovation Centre for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, 100191, China.
Abstract:
Individuals with mild cognitive impairment (MCI) of different subtypes show distinct alterations in network patterns. The first aim of this study is to identify the subtypes of MCI by employing a regional radiomics similarity network (R2SN). The second aim is to characterize the abnormality patterns associated with the clinical manifestations of each subtype. An individual-level R2SN is constructed for N = 605 normal controls (NCs), N = 766 MCI patients, and N = 283 Alzheimer's disease (AD) patients. MCI patients' R2SN profiles are clustered into two subtypes using nonnegative matrix factorization. The patterns of brain alterations, gene expression, and the risk of cognitive decline in each subtype are evaluated. MCI patients are clustered into "similar to the pattern of NCs" (N-CI, N = 252) and "similar to the pattern of AD" (A-CI, N = 514) subgroups. Significant differences are observed between the subtypes with respect to the following: 1) clinical measures; 2) multimodal neuroimaging; 3) the proportion of progression to dementia (61.54% for A-CI and 21.77% for N-CI) within three years; 4) enriched genes for potassium-ion transport and synaptic transmission. Stratification into the two subtypes provides new insight for risk assessment and precise early intervention for MCI patients.
Insights
Researchers identified two mild cognitive impairment (MCI) subtypes using radiomics networks. One subtype resembles normal cognition, while the other mirrors Alzheimer's disease patterns, impacting progression risk and intervention strategies.
Area of Science:
- Neuroscience
- Radiomics
- Biostatistics
Background:
- Mild cognitive impairment (MCI) encompasses heterogeneous patient groups with varying network alterations.
- Accurate subtyping of MCI is crucial for understanding distinct disease trajectories and developing targeted interventions.
Purpose of the Study:
- To identify distinct subtypes of mild cognitive impairment (MCI) using a regional radiomics similarity network (R2SN).
- To characterize the unique patterns of brain alterations, gene expression, and clinical progression associated with each MCI subtype.
Main Methods:
- Construction of individual-level R2SN for normal controls (NCs), MCI patients, and Alzheimer's disease (AD) patients.
- Clustering of MCI patients' R2SN profiles into two subtypes using nonnegative matrix factorization.
- Evaluation of brain alterations, gene expression, and dementia progression risk for each identified MCI subtype.
Main Results:
- MCI patients were stratified into two subtypes: N-CI (similar to NCs, N=252) and A-CI (similar to AD, N=514).
- Significant differences were observed between subtypes in clinical measures, multimodal neuroimaging, and gene expression (potassium-ion transport, synaptic transmission).
- The A-CI subtype exhibited a substantially higher proportion of progression to dementia (61.54%) compared to the N-CI subtype (21.77%) within three years.
Conclusions:
- Subtyping MCI based on R2SN provides critical insights into distinct pathological patterns.
- This stratification aids in more accurate risk assessment for cognitive decline and dementia progression.
- Identified subtypes offer a foundation for precise, early intervention strategies in individuals with MCI.
