scholarly journals Quantitative Assessment of Resting-State for Mild Cognitive Impairment Detection: A Functional Near-Infrared Spectroscopy and Deep Learning Approach

2021 ◽  
pp. 1-17
Author(s):  
Dalin Yang ◽  
Keum-Shik Hong
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Infrared Spectroscopy ◽  
Resting State ◽  
Near Infrared ◽  
Feature Representation ◽  
Learning Approach ◽  
Theory Analysis ◽  
Functional Near Infrared Spectroscopy ◽  
Graph Theory Analysis

Background: Mild cognitive impairment (MCI) is considered a prodromal stage of Alzheimer’s disease. Early diagnosis of MCI can allow for treatment to improve cognitive function and reduce modifiable risk factors. Objective: This study aims to investigate the feasibility of individual MCI detection from healthy control (HC) using a minimum duration of resting-state functional near-infrared spectroscopy (fNIRS) signals. Methods: In this study, nine different measurement durations (i.e., 30, 60, 90, 120, 150, 180, 210, 240, and 270 s) were evaluated for MCI detection via the graph theory analysis and traditional machine learning approach, such as linear discriminant analysis, support vector machine, and K-nearest neighbor algorithms. Moreover, feature representation- and classification-based transfer learning (TL) methods were applied to identify MCI from HC through the input of connectivity maps with 30 and 90 s duration. Results: There was no significant difference among the nine various time windows in the machine learning and graph theory analysis. The feature representation-based TL showed improved accuracy in both 30 and 90 s cases (i.e., 30 s: 81.27% % and 90 s: 76.73%). Notably, the classification-based TL method achieved the highest accuracy of 95.81% using the pre-trained convolutional neural network (CNN) model with the 30 s interval functional connectivity map input. Conclusion: The results indicate that a 30 s measurement of the resting-state with fNIRS could be used to detect MCI. Moreover, the combination of neuroimaging (e.g., functional connectivity maps) and deep learning methods (e.g., CNN and TL) can be considered as novel biomarkers for clinical computer-assisted MCI diagnosis.

scholarly journals Quantitative Assessment of Resting State for Mild Cognitive Impairment Detection: A Functional Near-Infrared Spectroscopy and Deep Learning Approach

2020 ◽  
Author(s):  
Dalin Yang ◽  
Keum-Shik Hong
Keyword(s):  
Machine Learning ◽  
Resting State ◽  
Near Infrared ◽  
Feature Representation ◽  
Learning Approach ◽  
Theory Analysis ◽  
Learning Methods ◽  
Functional Near Infrared Spectroscopy ◽  
Machine Learning Methods ◽  
Graph Theory Analysis

Abstract Background: Mild cognitive impairment (MCI) is considered a prodromal stage of Alzheimer’s disease, which is the sixth leading cause of death in the United State. Early diagnosis of MCI can allow for treatment to improve cognitive function and reduce modifiable risk factors. Currently, the combination of machine learning and neuroimaging plays a role in identifying and understanding neuropathological diseases. However, some challenges still remain, and these limitations need to be optimized for clinical MCI diagnosis. Methods: In this study, for stable identification with functional near-infrared spectroscopy (fNIRS) using the minimum resting-state time, nine different measurement durations (i.e., 30, 60, 90, 120, 150, 180, 210, 240, and 270 s) were evaluated based on 30 s intervals using a traditional machine learning approach and graph theory analysis. The machine learning methods were trained using temporal features of the resting-state fNIRS signal and included linear discriminant analysis (LDA), support vector machine, and K-nearest neighbor (KNN) algorithms. To enhance the diagnostic accuracy, feature representation- and classification-based transfer learning (TL) methods were used to detect MCI from the healthy controls through the input of connectivity maps with 30 and 90 s durations. Results: As in the results of the traditional machine learning and graph theory analysis, there was no significant difference among the different time windows. The accuracy of the conventional machine learning methods ranged from 55.76% (KNN, 120 s) to 67.00% (LDA, 90 s). The feature representation-based TL showed improved accuracy in both the 30 and 90 s cases (i.e., mean accuracy of 30 s: 79.37%, mean accuracy of 30 s: 74.05%). Notably, the classification-based TL method achieved the highest accuracy of 97.01% using the VGG19 pre-trained CNN model trained with the 30 s duration connectivity map. Conclusion: The results indicate that a 30 s measurement of the resting state with fNIRS could be used to detect MCI. Moreover, the combination of neuroimaging (e.g., functional connectivity maps) and deep learning methods (e.g., CNN and TL) may be considered as novel biomarkers for clinical computer-assisted MCI diagnosis.

scholarly journals Objective measurement of tinnitus using functional near-infrared spectroscopy and machine learning

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0241695 ◽  
Author(s):  
Mehrnaz Shoushtarian ◽  
Roohallah Alizadehsani ◽  
Abbas Khosravi ◽  
Nicola Acevedo ◽  
Colette M. McKay ◽  
...  
Keyword(s):  
Machine Learning ◽  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Resting State ◽  
Near Infrared ◽  
Objective Measure ◽  
Chronic Tinnitus ◽  
Subjective Ratings ◽  
Functional Near Infrared Spectroscopy ◽  
Auditory Evoked Responses

Chronic tinnitus is a debilitating condition which affects 10–20% of adults and can severely impact their quality of life. Currently there is no objective measure of tinnitus that can be used clinically. Clinical assessment of the condition uses subjective feedback from individuals which is not always reliable. We investigated the sensitivity of functional near-infrared spectroscopy (fNIRS) to differentiate individuals with and without tinnitus and to identify fNIRS features associated with subjective ratings of tinnitus severity. We recorded fNIRS signals in the resting state and in response to auditory or visual stimuli from 25 individuals with chronic tinnitus and 21 controls matched for age and hearing loss. Severity of tinnitus was rated using the Tinnitus Handicap Inventory and subjective ratings of tinnitus loudness and annoyance were measured on a visual analogue scale. Following statistical group comparisons, machine learning methods including feature extraction and classification were applied to the fNIRS features to classify patients with tinnitus and controls and differentiate tinnitus at different severity levels. Resting state measures of connectivity between temporal regions and frontal and occipital regions were significantly higher in patients with tinnitus compared to controls. In the tinnitus group, temporal-occipital connectivity showed a significant increase with subject ratings of loudness. Also in this group, both visual and auditory evoked responses were significantly reduced in the visual and auditory regions of interest respectively. Naïve Bayes classifiers were able to classify patients with tinnitus from controls with an accuracy of 78.3%. An accuracy of 87.32% was achieved using Neural Networks to differentiate patients with slight/ mild versus moderate/ severe tinnitus. Our findings show the feasibility of using fNIRS and machine learning to develop an objective measure of tinnitus. Such a measure would greatly benefit clinicians and patients by providing a tool to objectively assess new treatments and patients’ treatment progress.

Sign in / Sign up

Export Citation Format

Share Document