DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG
Major Depression Disorder (MDD) is a common yet destructive mental disorder that affects millions of people worldwide. Making early and accurate diagnosis of it is very meaningful. Recently, EEG, a non-invasive technique of recording spontaneous electrical activity of brains, has been widely used fo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10417777/ |
| _version_ | 1797305351360479232 |
|---|---|
| author | Yilin Wang Sha Zhao Haiteng Jiang Shijian Li Benyan Luo Tao Li Gang Pan |
| author_facet | Yilin Wang Sha Zhao Haiteng Jiang Shijian Li Benyan Luo Tao Li Gang Pan |
| author_sort | Yilin Wang |
| collection | DOAJ |
| description | Major Depression Disorder (MDD) is a common yet destructive mental disorder that affects millions of people worldwide. Making early and accurate diagnosis of it is very meaningful. Recently, EEG, a non-invasive technique of recording spontaneous electrical activity of brains, has been widely used for MDD diagnosis. However, there are still some challenges in data quality and data size of EEG: (1) A large amount of noise is inevitable during EEG collection, making it difficult to extract discriminative features from raw EEG; (2) It is difficult to recruit a large number of subjects to collect sufficient and diverse data for model training. Both of the challenges cause the overfitting problem, especially for deep learning methods. In this paper, we propose DiffMDD, a diffusion-based deep learning framework for MDD diagnosis using EEG. Specifically, we extract more noise-irrelevant features to improve the model’s robustness by designing the Forward Diffusion Noisy Training Module. Then we increase the size and diversity of data to help the model learn more generalized features by designing the Reverse Diffusion Data Augmentation Module. Finally, we re-train the classifier on the augmented dataset for MDD diagnosis. We conducted comprehensive experiments to test the overall performance and each module’s effectiveness. The framework was validated on two public MDD diagnosis datasets, achieving the state-of-the-art performance. |
| first_indexed | 2024-03-08T00:24:40Z |
| format | Article |
| id | doaj.art-32bc2f3a4b7147598c3702ae92bfa08a |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-08T00:24:40Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-32bc2f3a4b7147598c3702ae92bfa08a2024-02-16T00:00:09ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102024-01-013272873810.1109/TNSRE.2024.336046510417777DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEGYilin Wang0https://orcid.org/0000-0002-0776-6215Sha Zhao1https://orcid.org/0000-0003-4628-5198Haiteng Jiang2Shijian Li3Benyan Luo4https://orcid.org/0000-0002-9892-5778Tao Li5Gang Pan6https://orcid.org/0000-0003-4628-5198State Key Laboratory of Brain-Machine Intelligence, Zhejiang University, Hangzhou, ChinaState Key Laboratory of Brain-Machine Intelligence, Zhejiang University, Hangzhou, ChinaDepartment of Neurobiology, Affiliated Mental Health Center, and the Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaState Key Laboratory of Brain-Machine Intelligence, Zhejiang University, Hangzhou, ChinaState Key Laboratory of Brain-Machine Intelligence, Zhejiang University, Hangzhou, ChinaDepartment of Neurobiology, Affiliated Mental Health Center, and the Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaState Key Laboratory of Brain-Machine Intelligence, Zhejiang University, Hangzhou, ChinaMajor Depression Disorder (MDD) is a common yet destructive mental disorder that affects millions of people worldwide. Making early and accurate diagnosis of it is very meaningful. Recently, EEG, a non-invasive technique of recording spontaneous electrical activity of brains, has been widely used for MDD diagnosis. However, there are still some challenges in data quality and data size of EEG: (1) A large amount of noise is inevitable during EEG collection, making it difficult to extract discriminative features from raw EEG; (2) It is difficult to recruit a large number of subjects to collect sufficient and diverse data for model training. Both of the challenges cause the overfitting problem, especially for deep learning methods. In this paper, we propose DiffMDD, a diffusion-based deep learning framework for MDD diagnosis using EEG. Specifically, we extract more noise-irrelevant features to improve the model’s robustness by designing the Forward Diffusion Noisy Training Module. Then we increase the size and diversity of data to help the model learn more generalized features by designing the Reverse Diffusion Data Augmentation Module. Finally, we re-train the classifier on the augmented dataset for MDD diagnosis. We conducted comprehensive experiments to test the overall performance and each module’s effectiveness. The framework was validated on two public MDD diagnosis datasets, achieving the state-of-the-art performance.https://ieeexplore.ieee.org/document/10417777/Major depression disorderelectroencephalogrammental disorder diagnosisdeep learning |
| spellingShingle | Yilin Wang Sha Zhao Haiteng Jiang Shijian Li Benyan Luo Tao Li Gang Pan DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG IEEE Transactions on Neural Systems and Rehabilitation Engineering Major depression disorder electroencephalogram mental disorder diagnosis deep learning |
| title | DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG |
| title_full | DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG |
| title_fullStr | DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG |
| title_full_unstemmed | DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG |
| title_short | DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG |
| title_sort | diffmdd a diffusion based deep learning framework for mdd diagnosis using eeg |
| topic | Major depression disorder electroencephalogram mental disorder diagnosis deep learning |
| url | https://ieeexplore.ieee.org/document/10417777/ |
| work_keys_str_mv | AT yilinwang diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg AT shazhao diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg AT haitengjiang diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg AT shijianli diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg AT benyanluo diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg AT taoli diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg AT gangpan diffmddadiffusionbaseddeeplearningframeworkformdddiagnosisusingeeg |