A deep learning method for autism spectrum disorder identification based on interactions of hierarchical brain networks
Copyright © 2023 Elsevier B.V. All rights reserved..
BACKGROUND: It has been recently shown that deep learning models exhibited remarkable performance of representing functional Magnetic Resonance Imaging (fMRI) data for the understanding of brain functional activities. With hierarchical structure, deep learning models can infer hierarchical functional brain networks (FBN) from fMRI. However, the applications of the hierarchical FBNs have been rarely studied.
METHODS: In this work, we proposed a hierarchical recurrent variational auto-encoder (HRVAE) to unsupervisedly model the fMRI data. The trained HRVAE encoder can predict hierarchical temporal features from its three hidden layers, and thus can be regarded as a hierarchical feature extractor. Then LASSO (least absolute shrinkage and selection operator) regression was applied to estimate the corresponding hierarchical FBNs. Based on the hierarchical FBNs from each subject, we constructed a novel classification framework for brain disorder identification and test it on the Autism Brain Imaging Data Exchange (ABIDE) dataset, a world-wide multi-site database of autism spectrum disorder (ASD). We analyzed the hierarchy organization of FBNs, and finally used the overlaps of hierarchical FBNs as features to differentiate ASD from typically developing controls (TDC).
RESULTS: The experimental results on 871 subjects from ABIDE dataset showed that the HRVAE model can effectively derive hierarchical FBNs including many well-known resting state networks (RSN). Moreover, the classification result improved the state-of-the-art by achieving a very high accuracy of 82.1 %.
CONCLUSIONS: This work presents a novel data-driven deep learning method using fMRI data for ASD identification, which could provide valuable reference for clinical diagnosis. The classification results suggest that the interactions of hierarchical FBNs have association with brain disorder, which promotes the understanding of FBN hierarchy and could be applied to other brain disorder analysis.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:452 |
---|---|
Enthalten in: |
Behavioural brain research - 452(2023) vom: 24. Aug., Seite 114603 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Qiang, Ning [VerfasserIn] |
---|
Links: |
---|
Themen: |
Autism spectrum disorder |
---|
Anmerkungen: |
Date Completed 14.08.2023 Date Revised 14.08.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.bbr.2023.114603 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM360160743 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM360160743 | ||
003 | DE-627 | ||
005 | 20231226082424.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.bbr.2023.114603 |2 doi | |
028 | 5 | 2 | |a pubmed24n1200.xml |
035 | |a (DE-627)NLM360160743 | ||
035 | |a (NLM)37516208 | ||
035 | |a (PII)S0166-4328(23)00321-2 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Qiang, Ning |e verfasserin |4 aut | |
245 | 1 | 2 | |a A deep learning method for autism spectrum disorder identification based on interactions of hierarchical brain networks |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 14.08.2023 | ||
500 | |a Date Revised 14.08.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 Elsevier B.V. All rights reserved. | ||
520 | |a BACKGROUND: It has been recently shown that deep learning models exhibited remarkable performance of representing functional Magnetic Resonance Imaging (fMRI) data for the understanding of brain functional activities. With hierarchical structure, deep learning models can infer hierarchical functional brain networks (FBN) from fMRI. However, the applications of the hierarchical FBNs have been rarely studied | ||
520 | |a METHODS: In this work, we proposed a hierarchical recurrent variational auto-encoder (HRVAE) to unsupervisedly model the fMRI data. The trained HRVAE encoder can predict hierarchical temporal features from its three hidden layers, and thus can be regarded as a hierarchical feature extractor. Then LASSO (least absolute shrinkage and selection operator) regression was applied to estimate the corresponding hierarchical FBNs. Based on the hierarchical FBNs from each subject, we constructed a novel classification framework for brain disorder identification and test it on the Autism Brain Imaging Data Exchange (ABIDE) dataset, a world-wide multi-site database of autism spectrum disorder (ASD). We analyzed the hierarchy organization of FBNs, and finally used the overlaps of hierarchical FBNs as features to differentiate ASD from typically developing controls (TDC) | ||
520 | |a RESULTS: The experimental results on 871 subjects from ABIDE dataset showed that the HRVAE model can effectively derive hierarchical FBNs including many well-known resting state networks (RSN). Moreover, the classification result improved the state-of-the-art by achieving a very high accuracy of 82.1 % | ||
520 | |a CONCLUSIONS: This work presents a novel data-driven deep learning method using fMRI data for ASD identification, which could provide valuable reference for clinical diagnosis. The classification results suggest that the interactions of hierarchical FBNs have association with brain disorder, which promotes the understanding of FBN hierarchy and could be applied to other brain disorder analysis | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Autism spectrum disorder | |
650 | 4 | |a Deep learning | |
650 | 4 | |a Functional brain network | |
650 | 4 | |a Hierarchy organization | |
650 | 4 | |a fMRI | |
700 | 1 | |a Gao, Jie |e verfasserin |4 aut | |
700 | 1 | |a Dong, Qinglin |e verfasserin |4 aut | |
700 | 1 | |a Li, Jin |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Shu |e verfasserin |4 aut | |
700 | 1 | |a Liang, Hongtao |e verfasserin |4 aut | |
700 | 1 | |a Sun, Yifei |e verfasserin |4 aut | |
700 | 1 | |a Ge, Bao |e verfasserin |4 aut | |
700 | 1 | |a Liu, Zhengliang |e verfasserin |4 aut | |
700 | 1 | |a Wu, Zihao |e verfasserin |4 aut | |
700 | 1 | |a Liu, Tianming |e verfasserin |4 aut | |
700 | 1 | |a Yue, Huiji |e verfasserin |4 aut | |
700 | 1 | |a Zhao, Shijie |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Behavioural brain research |d 1993 |g 452(2023) vom: 24. Aug., Seite 114603 |w (DE-627)NLM012632252 |x 1872-7549 |7 nnns |
773 | 1 | 8 | |g volume:452 |g year:2023 |g day:24 |g month:08 |g pages:114603 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.bbr.2023.114603 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 452 |j 2023 |b 24 |c 08 |h 114603 |