Stage detection of mild cognitive impairment via fMRI using Hilbert Huang transform based classification framework

Abstract

This work aims to establish a classification framework for the diagnosis of mild cognitive impairment (MCI) at different stages (early MCI and late MCI) through direct analysis of restingstate functional magnetic resonance imaging (rs-fMRI) signals and using the accuracy (total correct rate), specificity (correct rate of late MCI) and sensitivity (correct rate of early MCI) to validate its classification performance. Methods: All fMR images of subjects were parcellated into 116 regions of interest (ROIs) by applying the Anatomical Automatic Labeling (AAL) template, and the average rs-fMRI signals of each ROI were extracted. The Hilbert-Huang transform (HHT) was introduced into the framework to decompose each rs-fMRI signal into a series of intrinsic mode functions (IMFs) and to analyze these nonstationary and nonlinear time-series from the perspective of multiresolution. After obtaining the instantaneous frequencies and amplitudes of all IMFs of a signal, the Hilbert weighted frequencies (HWFs) were calculated and combined into a vector as the feature of the corresponding ROI. Support Vector Machine (SVM) was implemented to classify MCI at different stages. We used the independent two-sample t-test as the feature selection method and measured the classification performance through the leave-one-out cross-validation (LOOCV) method. Results: Results on 77 early MCI (eMCI) and 64 late MCI (lMCI) with baseline rs-fMRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) yielded 87.94% classification accuracy. Some of the brain regions with significant differences found by previous studies have been confirmed in this work. We found that HWF characteristics exhibited a significant downward trend in all cerebellar regions. The rs-fMRI signals in differential brain regions have not changed completely, but only altered in some narrow frequency bands. The analysis results showed that during the progress of MCI, the main changes of rs-fMRI were concentrated in IMF3, while IMFs with other indexes also contained HWF features with high SVM weights, such as Orbitofrontal superior frontal gyrus in IMF2, Insula in IMF4, and Lobule Ⅲ of vermis in IMF5, indicating that other IMFs provide important information for the diagnosis of MCI as well. Conclusions: This work confirmed the classification ability of HHT-based classification framework in classification of at different stages of MCI. Through the analysis, we found that during the progress of MCI the main changes of rs-fMRI were concentrated in IMF3, and HWF characteristics showed a significant downward trend in all cerebellar regions.

Functional Integrity of Executive Control Network Contributed to Retained Executive Abilities in Mild Cognitive Impairment

“…Contrastingly, the fALFF in the left MFG in the MCI-lowEF group is lower compared to HC, while fALFF of the cerebellar vermis is higher than HC. The majority of regions have been reported in prior MCI or AD studies (Cai et al, 2018;Long et al, 2018;Shi and Liu, 2020;Wang et al, 2021c). Compared to HC, the two groups all demonstrated significant fALFF differences in the left MFG.…”

Surface-Based Falff: A Potential Novel Biomarker for Prediction of Radiation Encephalopathy in Patients With Nasopharyngeal Carcinoma

“…The procedure was repeated until every enrolled subject was used as the test set. Then, we calculated the classification accuracy (Shi and Liu, 2020 ).…”

Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data

“…Zhang et al also used multiple brain network features and conducted feature selection by three different algorithms 8 . Shi and Liu extracted features by calculating the Hilbert weighted frequencies (HWFs) from decomposed rs-fMRI signals, with independent two-sample t -test as feature selection method for SVM 25 . Collectively, these results suggest the optimal feature selection from multi-modal MRI data might be critical to improve classification performance.…”

“…Nozadi et al also used PET images for classification, comparing FDG and Amyloid ( AV-45) PET biomarkers 24 . Shi and Liu extracted features from rs-fMRI signals 25 , and Sheng et al processed thousands of brain network features by graph theory for classification 26 . Wee et al have indicated the multi-modal neuroimaging approach with structural and functional connectivity analyses significantly improves the identification accuracy of MCI 27 .…”