Classification of recurrent major depressive disorder using a residual denoising autoencoder framework : Insights from large-scale multisite fMRI data
Copyright © 2024 Elsevier B.V. All rights reserved..
BACKGROUND AND OBJECTIVE: Recurrent major depressive disorder (rMDD) has a high recurrence rate, and symptoms often worsen with each episode. Classifying rMDD using functional magnetic resonance imaging (fMRI) can enhance understanding of brain activity and aid diagnosis and treatment of this disorder.
METHODS: We developed a Residual Denoising Autoencoder (Res-DAE) framework for the classification of rMDD. The functional connectivity (FC) was extracted from fMRI data as features. The framework addresses site heterogeneity by employing the Combat method to harmonize feature distribution differences. A feature selection method based on Fisher scores was used to reduce redundant information in the features. A data augmentation strategy using a Synthetic Minority Over-sampling Technique algorithm based on Extended Frobenius Norm measure was incorporated to increase the sample size. Furthermore, a residual module was integrated into the autoencoder network to preserve important features and improve the classification accuracy.
RESULTS: We tested our framework on a large-scale, multisite fMRI dataset, which includes 189 rMDD patients and 427 healthy controls. The Res-DAE achieved an average accuracy of 75.1 % (sensitivity = 69 %, specificity = 77.8 %) in cross-validation, thereby outperforming comparison methods. In a larger dataset that also includes first-episode depression (comprising 832 MDD patients and 779 healthy controls), the accuracy reached 70 %.
CONCLUSIONS: We proposed a deep learning framework that can effectively classify rMDD and 33 identify the altered FC associated with rMDD. Our study may reveal changes in brain function 34 associated with rMDD and provide assistance for the diagnosis and treatment of rMDD.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:247 |
---|---|
Enthalten in: |
Computer methods and programs in biomedicine - 247(2024) vom: 18. März, Seite 108114 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Dai, Peishan [VerfasserIn] |
---|
Links: |
---|
Themen: |
Autoencoder |
---|
Anmerkungen: |
Date Completed 18.03.2024 Date Revised 18.03.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.cmpb.2024.108114 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM369370767 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM369370767 | ||
003 | DE-627 | ||
005 | 20240318234622.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240307s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.cmpb.2024.108114 |2 doi | |
028 | 5 | 2 | |a pubmed24n1335.xml |
035 | |a (DE-627)NLM369370767 | ||
035 | |a (NLM)38447315 | ||
035 | |a (PII)S0169-2607(24)00110-X | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Dai, Peishan |e verfasserin |4 aut | |
245 | 1 | 0 | |a Classification of recurrent major depressive disorder using a residual denoising autoencoder framework |b Insights from large-scale multisite fMRI data |
264 | 1 | |c 2024 | |
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 18.03.2024 | ||
500 | |a Date Revised 18.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2024 Elsevier B.V. All rights reserved. | ||
520 | |a BACKGROUND AND OBJECTIVE: Recurrent major depressive disorder (rMDD) has a high recurrence rate, and symptoms often worsen with each episode. Classifying rMDD using functional magnetic resonance imaging (fMRI) can enhance understanding of brain activity and aid diagnosis and treatment of this disorder | ||
520 | |a METHODS: We developed a Residual Denoising Autoencoder (Res-DAE) framework for the classification of rMDD. The functional connectivity (FC) was extracted from fMRI data as features. The framework addresses site heterogeneity by employing the Combat method to harmonize feature distribution differences. A feature selection method based on Fisher scores was used to reduce redundant information in the features. A data augmentation strategy using a Synthetic Minority Over-sampling Technique algorithm based on Extended Frobenius Norm measure was incorporated to increase the sample size. Furthermore, a residual module was integrated into the autoencoder network to preserve important features and improve the classification accuracy | ||
520 | |a RESULTS: We tested our framework on a large-scale, multisite fMRI dataset, which includes 189 rMDD patients and 427 healthy controls. The Res-DAE achieved an average accuracy of 75.1 % (sensitivity = 69 %, specificity = 77.8 %) in cross-validation, thereby outperforming comparison methods. In a larger dataset that also includes first-episode depression (comprising 832 MDD patients and 779 healthy controls), the accuracy reached 70 % | ||
520 | |a CONCLUSIONS: We proposed a deep learning framework that can effectively classify rMDD and 33 identify the altered FC associated with rMDD. Our study may reveal changes in brain function 34 associated with rMDD and provide assistance for the diagnosis and treatment of rMDD | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Autoencoder | |
650 | 4 | |a Deep learning | |
650 | 4 | |a Functional connectivity | |
650 | 4 | |a Functional magnetic resonance imaging | |
650 | 4 | |a Recurrent major depressive disorder | |
650 | 4 | |a Residual network | |
700 | 1 | |a Shi, Yun |e verfasserin |4 aut | |
700 | 1 | |a Lu, Da |e verfasserin |4 aut | |
700 | 1 | |a Zhou, Ying |e verfasserin |4 aut | |
700 | 1 | |a Luo, Jialin |e verfasserin |4 aut | |
700 | 1 | |a He, Zhuang |e verfasserin |4 aut | |
700 | 1 | |a Chen, Zailiang |e verfasserin |4 aut | |
700 | 1 | |a Zou, Beiji |e verfasserin |4 aut | |
700 | 1 | |a Tang, Hui |e verfasserin |4 aut | |
700 | 1 | |a Huang, Zhongchao |e verfasserin |4 aut | |
700 | 1 | |a Liao, Shenghui |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Computer methods and programs in biomedicine |d 1993 |g 247(2024) vom: 18. März, Seite 108114 |w (DE-627)NLM012836133 |x 1872-7565 |7 nnns |
773 | 1 | 8 | |g volume:247 |g year:2024 |g day:18 |g month:03 |g pages:108114 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.cmpb.2024.108114 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 247 |j 2024 |b 18 |c 03 |h 108114 |