The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications
The last decade has witnessed a notable surge in deep learning applications for electroencephalography (EEG) data analysis, showing promising improvements over conventional statistical techniques. However, deep learning models can underperform if trained with bad processed data. Preprocessing is cru...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10909332/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850068468088438784 |
|---|---|
| author | Federico Del Pup Andrea Zanola Louis Fabrice Tshimanga Alessandra Bertoldo Manfredo Atzori |
| author_facet | Federico Del Pup Andrea Zanola Louis Fabrice Tshimanga Alessandra Bertoldo Manfredo Atzori |
| author_sort | Federico Del Pup |
| collection | DOAJ |
| description | The last decade has witnessed a notable surge in deep learning applications for electroencephalography (EEG) data analysis, showing promising improvements over conventional statistical techniques. However, deep learning models can underperform if trained with bad processed data. Preprocessing is crucial for EEG data analysis, yet there is no consensus on the optimal strategies in deep learning scenarios, leading to uncertainty about the extent of preprocessing required for optimal results. This study is the first to thoroughly investigate the effects of EEG preprocessing in deep learning applications, drafting guidelines for future research. It evaluates the effects of varying preprocessing levels, from raw and minimally filtered data to complex pipelines with automated artifact removal algorithms. Six classification tasks (eye blinking, motor imagery, Parkinson’s, Alzheimer’s disease, sleep deprivation, and first episode psychosis) and four established EEG architectures were considered for the evaluation. The analysis of 4800 trained models revealed statistical differences between preprocessing pipelines at the intra-task level for each model and at the inter-task level for the largest model. Models trained on raw data consistently performed poorly, always ranking last in average scores. In addition, models seem to benefit more from minimal pipelines without artifact handling methods. These findings suggest that EEG artifacts may affect the performance and generalizability of deep neural networks. |
| format | Article |
| id | doaj-art-35aa6bad2ac249cbbce9c6319b2e6f7f |
| institution | DOAJ |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-35aa6bad2ac249cbbce9c6319b2e6f7f2025-08-20T02:48:03ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01331061107010.1109/TNSRE.2025.354761610909332The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning ApplicationsFederico Del Pup0https://orcid.org/0009-0004-0698-962XAndrea Zanola1Louis Fabrice Tshimanga2https://orcid.org/0009-0002-1240-4830Alessandra Bertoldo3https://orcid.org/0000-0002-6262-6354Manfredo Atzori4Department of Information Engineering, University of Padua, Padua, ItalyPadova Neuroscience Center, University of Padova, Padua, ItalyPadova Neuroscience Center, University of Padova, Padua, ItalyDepartment of Information Engineering, University of Padua, Padua, ItalyPadova Neuroscience Center, University of Padova, Padua, ItalyThe last decade has witnessed a notable surge in deep learning applications for electroencephalography (EEG) data analysis, showing promising improvements over conventional statistical techniques. However, deep learning models can underperform if trained with bad processed data. Preprocessing is crucial for EEG data analysis, yet there is no consensus on the optimal strategies in deep learning scenarios, leading to uncertainty about the extent of preprocessing required for optimal results. This study is the first to thoroughly investigate the effects of EEG preprocessing in deep learning applications, drafting guidelines for future research. It evaluates the effects of varying preprocessing levels, from raw and minimally filtered data to complex pipelines with automated artifact removal algorithms. Six classification tasks (eye blinking, motor imagery, Parkinson’s, Alzheimer’s disease, sleep deprivation, and first episode psychosis) and four established EEG architectures were considered for the evaluation. The analysis of 4800 trained models revealed statistical differences between preprocessing pipelines at the intra-task level for each model and at the inter-task level for the largest model. Models trained on raw data consistently performed poorly, always ranking last in average scores. In addition, models seem to benefit more from minimal pipelines without artifact handling methods. These findings suggest that EEG artifacts may affect the performance and generalizability of deep neural networks.https://ieeexplore.ieee.org/document/10909332/EEGpreprocessingdeep learningmotor imagerydisease classification |
| spellingShingle | Federico Del Pup Andrea Zanola Louis Fabrice Tshimanga Alessandra Bertoldo Manfredo Atzori The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications IEEE Transactions on Neural Systems and Rehabilitation Engineering EEG preprocessing deep learning motor imagery disease classification |
| title | The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications |
| title_full | The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications |
| title_fullStr | The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications |
| title_full_unstemmed | The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications |
| title_short | The More, the Better? Evaluating the Role of EEG Preprocessing for Deep Learning Applications |
| title_sort | more the better evaluating the role of eeg preprocessing for deep learning applications |
| topic | EEG preprocessing deep learning motor imagery disease classification |
| url | https://ieeexplore.ieee.org/document/10909332/ |
| work_keys_str_mv | AT federicodelpup themorethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT andreazanola themorethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT louisfabricetshimanga themorethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT alessandrabertoldo themorethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT manfredoatzori themorethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT federicodelpup morethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT andreazanola morethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT louisfabricetshimanga morethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT alessandrabertoldo morethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications AT manfredoatzori morethebetterevaluatingtheroleofeegpreprocessingfordeeplearningapplications |