Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI
The long short-term memory network (LSTM) is widely used in time series data processing as a temporal recursive network. The resting-state functional magnetic resonance data shows that not only are there temporal variations in the resting state, but there are also interactions between brain regions....
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IMR Press
2022-03-01
|
Series: | Journal of Integrative Neuroscience |
Subjects: | |
Online Access: | https://www.imrpress.com/journal/JIN/21/2/10.31083/j.jin2102056 |
_version_ | 1811302650759610368 |
---|---|
author | Jiyun Li Binbin Song Chen Qian |
author_facet | Jiyun Li Binbin Song Chen Qian |
author_sort | Jiyun Li |
collection | DOAJ |
description | The long short-term memory network (LSTM) is widely used in time series data processing as a temporal recursive network. The resting-state functional magnetic resonance data shows that not only are there temporal variations in the resting state, but there are also interactions between brain regions. To integrate the temporal and spatial characteristics of brain regions, this paper proposes a model called feature weighted-LSTM (FW-LSTM). The feature weight is defined by spatial characteristics calculating the frequency of connectivity of each brain region and further integrated into the LSTM. Thus, it can comprehensively model both temporal and spatial changes in rs-fMRI brain regions. The FW-LSTM model on the Alzheimer's disease neuroimaging initiative (ADNI) dataset is used to extract the time-varying characteristics of 90 brain regions for Alzheimer's disease (AD) classification. The model performances are 77.80%, 76.41%, and 78.81% in accuracy, sensitivity, and specificity. It outperformed the one-dimensional convolutional neural networks (1D-CNN) model and LSTM model, which only used temporal features of brain regions. |
first_indexed | 2024-04-13T07:33:00Z |
format | Article |
id | doaj.art-e1beaaf8f2ea4ce3805eac77d88e327d |
institution | Directory Open Access Journal |
issn | 0219-6352 |
language | English |
last_indexed | 2024-04-13T07:33:00Z |
publishDate | 2022-03-01 |
publisher | IMR Press |
record_format | Article |
series | Journal of Integrative Neuroscience |
spelling | doaj.art-e1beaaf8f2ea4ce3805eac77d88e327d2022-12-22T02:56:19ZengIMR PressJournal of Integrative Neuroscience0219-63522022-03-0121205610.31083/j.jin2102056S0219-6352(22)00316-3Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRIJiyun Li0Binbin Song1Chen Qian2School of Computer Science and Technology, Donghua University, 201620 Shanghai, ChinaSchool of Computer Science and Technology, Donghua University, 201620 Shanghai, ChinaSchool of Computer Science and Technology, Donghua University, 201620 Shanghai, ChinaThe long short-term memory network (LSTM) is widely used in time series data processing as a temporal recursive network. The resting-state functional magnetic resonance data shows that not only are there temporal variations in the resting state, but there are also interactions between brain regions. To integrate the temporal and spatial characteristics of brain regions, this paper proposes a model called feature weighted-LSTM (FW-LSTM). The feature weight is defined by spatial characteristics calculating the frequency of connectivity of each brain region and further integrated into the LSTM. Thus, it can comprehensively model both temporal and spatial changes in rs-fMRI brain regions. The FW-LSTM model on the Alzheimer's disease neuroimaging initiative (ADNI) dataset is used to extract the time-varying characteristics of 90 brain regions for Alzheimer's disease (AD) classification. The model performances are 77.80%, 76.41%, and 78.81% in accuracy, sensitivity, and specificity. It outperformed the one-dimensional convolutional neural networks (1D-CNN) model and LSTM model, which only used temporal features of brain regions.https://www.imrpress.com/journal/JIN/21/2/10.31083/j.jin2102056rs-fmri datatemporal characteristicsspatial characteristicsfw-lstm |
spellingShingle | Jiyun Li Binbin Song Chen Qian Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI Journal of Integrative Neuroscience rs-fmri data temporal characteristics spatial characteristics fw-lstm |
title | Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI |
title_full | Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI |
title_fullStr | Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI |
title_full_unstemmed | Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI |
title_short | Diagnosis of Alzheimer's disease by feature weighted-LSTM: a preliminary study of temporal features in brain resting-state fMRI |
title_sort | diagnosis of alzheimer s disease by feature weighted lstm a preliminary study of temporal features in brain resting state fmri |
topic | rs-fmri data temporal characteristics spatial characteristics fw-lstm |
url | https://www.imrpress.com/journal/JIN/21/2/10.31083/j.jin2102056 |
work_keys_str_mv | AT jiyunli diagnosisofalzheimersdiseasebyfeatureweightedlstmapreliminarystudyoftemporalfeaturesinbrainrestingstatefmri AT binbinsong diagnosisofalzheimersdiseasebyfeatureweightedlstmapreliminarystudyoftemporalfeaturesinbrainrestingstatefmri AT chenqian diagnosisofalzheimersdiseasebyfeatureweightedlstmapreliminarystudyoftemporalfeaturesinbrainrestingstatefmri |