Joint Pairing and Structured Mapping of Convolutional Brain Morphological Multiplexes for Early Dementia Diagnosis

Area of Science:

• Neuroscience
• Medical Imaging
• Machine Learning

Background:

• Early diagnosis of dementia, especially early mild cognitive impairment (eMCI), is crucial for timely intervention.
• Existing research primarily uses structural and functional connectomic data, leaving cortical morphological changes in early dementia largely unexplored.
• Investigating morphological alterations in brain connectivity can provide new insights into early dementia detection.

Purpose of the Study:

• To develop and validate a novel joint morphological brain multiplexes pairing and mapping strategy for enhanced detection of eMCI.
• To identify discriminative brain morphological networks and specific connections associated with eMCI.
• To explore the potential of these morphological features as biomarkers for eMCI diagnosis.

Main Methods:

• Proposed a joint morphological brain multiplexes pairing and mapping strategy.
• Utilized brain connectomic data focusing on cortical morphology.
• Employed machine learning for classification accuracy comparison with state-of-the-art methods.

Main Results:

• The proposed framework demonstrated superior classification accuracy in detecting eMCI compared to existing methods.
• Identified key discriminative brain morphological networks, including those derived from maximum principal curvature and sulcal depth (left hemisphere), and sulcal depth and average curvature (right hemisphere).
• Pinpointed highly correlated morphological connections (e.g., pericalcarine cortex, insula cortex, entorhinal cortex) as potential eMCI biomarkers.

Conclusions:

• The novel morphological brain mapping strategy is effective for eMCI detection.
• Specific morphological brain networks and connections show significant differences between eMCI patients and healthy controls.
• These findings suggest that morphological brain connections can serve as valuable biomarkers for early dementia diagnosis.