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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |