Supervised dictionary learning of EEG signals for mild cognitive impairment diagnosis

Abstract

Mild Cognitive Impairment (MCI) is an intermediate stage of memory decline between normal aging and Alzheimer's disease or other types of dementia. MCI diagnosis is instrumental in preventing Alzheimer's; however, its manifestations are complicated (i.e. distinguishing the symptoms is not easy) and MCI is often confused with the normal consequences of aging. To have an accurate and reliable Electroencephalogram (EEG)-based screening tool for MCI diagnosis, we are developing a new supervised dictionary-learning-based analysis of EEG signals, namely Correlation-based Label Consistent K-SVD (CLC-KSVD), which would solve the non-repeatability problem of conventional K-SVD. The proposed method is applied on both time and frequency domains, i.e. 1) the extracted patches from EEG signals recorded at resting state with eyes closed, and 2) the extracted spectral features from these EEG signals. The final label for each EEG signal (in different channels and zones) is obtained by voting between the labels of the whole of time and spectral patches. The evaluation results for the EEG signals of 61 subjects illustrate that CLC-KSVD outperforms other methods (the best accuracy of 88.9 was obtained in F7, T3 channels and the left temporal zone). Furthermore, the results are investigated using the volumetric analysis of Magnetic Resonance (MR) images, indicating that the most significant difference between healthy and MCI groups were in the superior temporal and pars triangularis in the left hemisphere. Such location matching between EEG and MR images demonstrates that the results of CLC-KSVD are anatomically interpretable. © 2019 Elsevier Ltd