Leveraging Persistent Homology for Differential Diagnosis of Mild Cognitive Impairment

TL;DR

This paper introduces a novel topological data analysis approach using persistent homology and deep learning to improve the differential diagnosis of mild cognitive impairment and its sub-types from fMRI data, achieving high accuracy.

Contribution

The study develops a new method combining persistent homology with deep learning for classifying MCI and its sub-types, surpassing existing techniques.

Findings

Achieved up to 95% classification accuracy on ADNI dataset.

Successfully differentiated MCI sub-types with over 76% accuracy.

Outperformed current state-of-the-art methods in MCI classification.

Abstract

Mild cognitive impairment (MCI) is characterized by subtle changes in cognitive functions, often associated with disruptions in brain connectivity. The present study introduces a novel fine-grained analysis to examine topological alterations in neurodegeneration pertaining to six different brain networks of MCI subjects (Early/Late MCI). To achieve this, fMRI time series from two distinct populations are investigated: (i) the publicly accessible ADNI dataset and (ii) our in-house dataset. The study utilizes sliding window embedding to convert each fMRI time series into a sequence of 3-dimensional vectors, facilitating the assessment of changes in regional brain topology. Distinct persistence diagrams are computed for Betti descriptors of dimension-0, 1, and 2. Wasserstein distance metric is used to quantify differences in topological characteristics. We have examined both (i) ROI-specific inter-subject interactions and (ii) subject-specific inter-ROI interactions. Further, a new deep learning model is proposed for classification, achieving a maximum classification accuracy of 95% for the ADNI dataset and 85% for the in-house dataset. This methodology is further adapted for the differential diagnosis of MCI sub-types, resulting in a peak accuracy of 76.5%, 91.1% and 80% in classifying HC Vs. EMCI, HC Vs. LMCI and EMCI Vs. LMCI, respectively. We showed that the proposed approach surpasses current state-of-the-art techniques designed for classifying MCI and its sub-types using fMRI.