Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease

Due to the incomplete nature of cognitive testing data and human subjective biases, accurately diagnosing mental disease using functional magnetic resonance imaging (fMRI) data poses a challenging task. In the clinical diagnosis of mental disorders, there often arises a problem of limited labeled da...

Full description

Saved in:
Bibliographic Details
Main Authors: Chang Hu, Yihong Dong, Shoubo Peng, Yuehan Wu
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/3/171
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850090419326550016
author Chang Hu
Yihong Dong
Shoubo Peng
Yuehan Wu
author_facet Chang Hu
Yihong Dong
Shoubo Peng
Yuehan Wu
author_sort Chang Hu
collection DOAJ
description Due to the incomplete nature of cognitive testing data and human subjective biases, accurately diagnosing mental disease using functional magnetic resonance imaging (fMRI) data poses a challenging task. In the clinical diagnosis of mental disorders, there often arises a problem of limited labeled data due to factors such as large data volumes and cumbersome labeling processes, leading to the emergence of unlabeled data with new classes, which can result in misdiagnosis. In the context of graph-based mental disorder classification, open-world semi-supervised learning for node classification aims to classify unlabeled nodes into known classes or potentially new classes, presenting a practical yet underexplored issue within the graph community. To improve open-world semi-supervised representation learning and classification in fMRI under low-label settings, we propose a novel open-world semi-supervised learning approach tailored for functional magnetic resonance imaging analysis, termed Open-World Semi-Supervised Learning for fMRI Analysis (OpenfMA). Specifically, we employ spectral augmentation self-supervised learning and dynamic concept contrastive learning to achieve open-world graph learning guided by pseudo-labels, and construct hard positive sample pairs to enhance the network’s focus on potential positive pairs. Experiments conducted on public datasets validate the superior performance of this method in the open-world psychiatric disease diagnosis domain.
format Article
id doaj-art-addf52fd05a24b639e85ebe1d8ef2c5b
institution DOAJ
issn 2078-2489
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-addf52fd05a24b639e85ebe1d8ef2c5b2025-08-20T02:42:34ZengMDPI AGInformation2078-24892025-02-0116317110.3390/info16030171Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric DiseaseChang Hu0Yihong Dong1Shoubo Peng2Yuehan Wu3Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, ChinaDue to the incomplete nature of cognitive testing data and human subjective biases, accurately diagnosing mental disease using functional magnetic resonance imaging (fMRI) data poses a challenging task. In the clinical diagnosis of mental disorders, there often arises a problem of limited labeled data due to factors such as large data volumes and cumbersome labeling processes, leading to the emergence of unlabeled data with new classes, which can result in misdiagnosis. In the context of graph-based mental disorder classification, open-world semi-supervised learning for node classification aims to classify unlabeled nodes into known classes or potentially new classes, presenting a practical yet underexplored issue within the graph community. To improve open-world semi-supervised representation learning and classification in fMRI under low-label settings, we propose a novel open-world semi-supervised learning approach tailored for functional magnetic resonance imaging analysis, termed Open-World Semi-Supervised Learning for fMRI Analysis (OpenfMA). Specifically, we employ spectral augmentation self-supervised learning and dynamic concept contrastive learning to achieve open-world graph learning guided by pseudo-labels, and construct hard positive sample pairs to enhance the network’s focus on potential positive pairs. Experiments conducted on public datasets validate the superior performance of this method in the open-world psychiatric disease diagnosis domain.https://www.mdpi.com/2078-2489/16/3/171graph neural networksopen-world semi-supervised learningfMRI analysiscontrastive learning
spellingShingle Chang Hu
Yihong Dong
Shoubo Peng
Yuehan Wu
Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease
Information
graph neural networks
open-world semi-supervised learning
fMRI analysis
contrastive learning
title Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease
title_full Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease
title_fullStr Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease
title_full_unstemmed Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease
title_short Open-World Semi-Supervised Learning for fMRI Analysis to Diagnose Psychiatric Disease
title_sort open world semi supervised learning for fmri analysis to diagnose psychiatric disease
topic graph neural networks
open-world semi-supervised learning
fMRI analysis
contrastive learning
url https://www.mdpi.com/2078-2489/16/3/171
work_keys_str_mv AT changhu openworldsemisupervisedlearningforfmrianalysistodiagnosepsychiatricdisease
AT yihongdong openworldsemisupervisedlearningforfmrianalysistodiagnosepsychiatricdisease
AT shoubopeng openworldsemisupervisedlearningforfmrianalysistodiagnosepsychiatricdisease
AT yuehanwu openworldsemisupervisedlearningforfmrianalysistodiagnosepsychiatricdisease