Influence of cognitive networks and task performance on fMRI-based state classification using DNN models

Abstract Deep neural networks (DNNs) excel at extracting insights from complex data across various fields, however, their application in cognitive neuroscience remains limited, largely due to the lack of approaches with interpretability. Here, we employ two different and complementary DNN models, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Murat Kucukosmanoglu, Javier O. Garcia, Justin Brooks, Kanika Bansal
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05690-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769354915217408
author Murat Kucukosmanoglu
Javier O. Garcia
Justin Brooks
Kanika Bansal
author_facet Murat Kucukosmanoglu
Javier O. Garcia
Justin Brooks
Kanika Bansal
author_sort Murat Kucukosmanoglu
collection DOAJ
description Abstract Deep neural networks (DNNs) excel at extracting insights from complex data across various fields, however, their application in cognitive neuroscience remains limited, largely due to the lack of approaches with interpretability. Here, we employ two different and complementary DNN models, a one-dimensional convolutional neural network (1D-CNN) and a bidirectional long short-term memory network (BiLSTM), to classify cognitive task states from fMRI data, focusing on the cognitive underpinnings of the classification. The 1D-CNN achieved an overall accuracy of 81% (Macro AUC = 0.96), while the BiLSTM reached 78% (Macro AUC = 0.95). Despite the architectural differences, both models demonstrated a robust relationship between prediction accuracy and individual cognitive performance (p < 0.05 for 1D-CNN, and p < 0.001 for BiLSTM), with lower classification accuracy observed in individuals with poorer task performance. Feature importance analysis highlighted the dominance of visual networks, suggesting that task-driven state differences are primarily encoded in visual processing. Attention and control networks also showed relatively high importance. We observed individual trait-based effects and subtle model-specific differences: 1D-CNN yielded slightly better overall performance, while BiLSTM showed better sensitivity for individual behavior. This study highlights the application of interpretable DNNs in revealing cognitive mechanisms associated with task performance and individual variability.
format Article
id doaj-art-09391eb8072a4d8f976389f71a3d4e5a
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-09391eb8072a4d8f976389f71a3d4e5a2025-08-20T03:03:27ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-05690-xInfluence of cognitive networks and task performance on fMRI-based state classification using DNN modelsMurat Kucukosmanoglu0Javier O. Garcia1Justin Brooks2Kanika Bansal3D-Prime LLCHumans in Complex Systems, US Army DEVCOM Army Research LaboratoryD-Prime LLCHumans in Complex Systems, US Army DEVCOM Army Research LaboratoryAbstract Deep neural networks (DNNs) excel at extracting insights from complex data across various fields, however, their application in cognitive neuroscience remains limited, largely due to the lack of approaches with interpretability. Here, we employ two different and complementary DNN models, a one-dimensional convolutional neural network (1D-CNN) and a bidirectional long short-term memory network (BiLSTM), to classify cognitive task states from fMRI data, focusing on the cognitive underpinnings of the classification. The 1D-CNN achieved an overall accuracy of 81% (Macro AUC = 0.96), while the BiLSTM reached 78% (Macro AUC = 0.95). Despite the architectural differences, both models demonstrated a robust relationship between prediction accuracy and individual cognitive performance (p < 0.05 for 1D-CNN, and p < 0.001 for BiLSTM), with lower classification accuracy observed in individuals with poorer task performance. Feature importance analysis highlighted the dominance of visual networks, suggesting that task-driven state differences are primarily encoded in visual processing. Attention and control networks also showed relatively high importance. We observed individual trait-based effects and subtle model-specific differences: 1D-CNN yielded slightly better overall performance, while BiLSTM showed better sensitivity for individual behavior. This study highlights the application of interpretable DNNs in revealing cognitive mechanisms associated with task performance and individual variability.https://doi.org/10.1038/s41598-025-05690-xCognitive state classificationFeature importanceBrain networksDeep neural networksExplainable AI
spellingShingle Murat Kucukosmanoglu
Javier O. Garcia
Justin Brooks
Kanika Bansal
Influence of cognitive networks and task performance on fMRI-based state classification using DNN models
Scientific Reports
Cognitive state classification
Feature importance
Brain networks
Deep neural networks
Explainable AI
title Influence of cognitive networks and task performance on fMRI-based state classification using DNN models
title_full Influence of cognitive networks and task performance on fMRI-based state classification using DNN models
title_fullStr Influence of cognitive networks and task performance on fMRI-based state classification using DNN models
title_full_unstemmed Influence of cognitive networks and task performance on fMRI-based state classification using DNN models
title_short Influence of cognitive networks and task performance on fMRI-based state classification using DNN models
title_sort influence of cognitive networks and task performance on fmri based state classification using dnn models
topic Cognitive state classification
Feature importance
Brain networks
Deep neural networks
Explainable AI
url https://doi.org/10.1038/s41598-025-05690-x
work_keys_str_mv AT muratkucukosmanoglu influenceofcognitivenetworksandtaskperformanceonfmribasedstateclassificationusingdnnmodels
AT javierogarcia influenceofcognitivenetworksandtaskperformanceonfmribasedstateclassificationusingdnnmodels
AT justinbrooks influenceofcognitivenetworksandtaskperformanceonfmribasedstateclassificationusingdnnmodels
AT kanikabansal influenceofcognitivenetworksandtaskperformanceonfmribasedstateclassificationusingdnnmodels