Deep Learning-Based Multilevel Classification of Alzheimer’s Disease Using Non-invasive Functional Near-Infrared Spectroscopy

Abstract

The timely diagnosis of Alzheimer’s disease (AD) and its prodromal stages is critically important for the patients, who manifest different neurodegenerative severity and progression risks, to take intervention and early symptomatic treatments before the brain damage is shaped. As one of the promising techniques, functional near-infrared spectroscopy (fNIRS) has been widely employed to support early-stage AD diagnosis. This study aims to validate the capability of fNIRS coupled with Deep Learning (DL) models for AD multi-class classification. First, a comprehensive experimental design, including the resting, cognitive, memory, and verbal tasks was conducted. Second, to precisely evaluate the AD progression, we thoroughly examined the change of hemodynamic responses measured in the prefrontal cortex among four subject groups and among genders. Then, we adopted a set of DL architectures on an extremely imbalanced fNIRS dataset. The results indicated that the statistical difference between subject groups did exist during memory and verbal tasks. This presented the correlation of the level of hemoglobin activation and the degree of AD severity. There was also a gender effect on the hemoglobin changes due to the functional stimulation in our study. Moreover, we demonstrated the potential of distinguished DL models, which boosted the multi-class classification performance. The highest accuracy was achieved by Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) using the original dataset of three hemoglobin types (0.909 ± 0.012 on average). Compared to conventional machine learning algorithms, DL models produced a better classification performance. These findings demonstrated the capability of DL frameworks on the imbalanced class distribution analysis and validated the great potential of fNIRS-based approaches to be further contributed to the development of AD diagnosis systems.

Use of Hypoxic Respiratory Challenge for Differentiating Alzheimer’s Disease and Wild-Type Mice Non-Invasively: A Diffuse Optical Spectroscopy Study

“…The unit of hemoglobin concentration was set to be mM/DPF, which is equivalent to setting DPF as 1 at different wavelengths [ 24 ]. Note that considering DPF as a part of the unit of hemoglobin concentration is one of the widely accepted approaches [ 12 , 24 , 25 , 28 ]. In this study, 808 nm was selected because it is known as one of the isosbestic points of the extinction coefficients of and [ 29 ].…”

“…Among various optical techniques, diffuse optical spectroscopy (DOS), also known as near-infrared spectroscopy (NIRS) in biomedical engineering, is frequently used in AD studies due to its relatively high temporal resolution, low cost, portability, and non-invasiveness. In most NIRS-based AD studies, experimental protocols, including the verbal fluency test [ 7 , 8 , 9 , 10 , 11 , 12 ], N-back test (including 1-back) [ 10 , 11 , 12 , 13 ], oddball test [ 11 , 12 ], and Stroop test [ 10 ], are used as stimuli to the brain. Such approaches aim to test neurovascular coupling to hypothesize differences in the responses of an AD group and a normal group.…”

“…While many AD studies using optical techniques performed relatively simple analyses including statistical tests and comparison of signal correlations [ 7 , 8 , 9 , 11 , 13 ], thanks to the rapid development of artificial intelligence (AI) techniques such as machine learning (ML) and deep learning (DL), recent AD studies using optical techniques tend to perform more advanced analyses of acquired signals [ 10 , 12 ]. It is well known that AI techniques extract ‘hidden’ information that cannot be found by conventional analytical methods, thus it is believed that a wide range of medical fields will benefit from adopting AI techniques.…”

Deep learning in fNIRS: a review

“…Ho et al. 83 attempted to use fNIRS and DL techniques to distinguish not only between healthy and prodromal Alzheimer’s afflicted subjects but also subjects with asymptomatic Alzheimer’s disease and dementia due to Alzheimer’s disease. Not only did this study try to distinguish between different stages of Alzheimer’s disease, the study used a notably large sample size of 140 participants, which was larger than any other study reported in this review as shown in Table 2 .…”

“…Using resting state fNIRS data, the network with the highest accuracy, VGG19, achieved an accuracy of 97.01% when connectivity maps were used as the input, outperforming the conventional machine learning techniques, with LDA classifier reporting the highest accuracy of 67.00%. Ho et al 83 attempted to use fNIRS and DL techniques to distinguish not only between healthy and prodromal Alzheimer's afflicted subjects but also subjects with asymptomatic Alzheimer's disease and dementia due to Alzheimer's disease. Not only did this study try to distinguish between different stages of Alzheimer's disease, the study used a notably large sample size of 140 participants, which was larger than any other study reported in this review as shown in Table 2.…”