Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning
Although attention-deficit/hyperactivity disorder (ADHD) is a common psychiatric disorder, it is difficult to develop an accurate diagnostic method. Recently, studies to classify ADHD using resting-state functional magnetic resonance (rs-fMRI) imaging data have been conducted with the development of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10286029/ |
| _version_ | 1797635420877488128 |
|---|---|
| author | Byunggun Kim Jaeseon Park Taehun Kim Younghun Kwon |
| author_facet | Byunggun Kim Jaeseon Park Taehun Kim Younghun Kwon |
| author_sort | Byunggun Kim |
| collection | DOAJ |
| description | Although attention-deficit/hyperactivity disorder (ADHD) is a common psychiatric disorder, it is difficult to develop an accurate diagnostic method. Recently, studies to classify ADHD using resting-state functional magnetic resonance (rs-fMRI) imaging data have been conducted with the development of computing resources and machine learning techniques. Most of them use the entire brain’s regions when training the models. As opposed to the common approach, we conducted a study to classify ADHD by selecting essential areas for using a deep learning model. The experiment used rs-fMRI data from the ADHD-200 global competition. To obtain an integrated result from the multiple sites, each region of the brain is evaluated using ’leave- one-site-out’ cross-validation. As a result, when we only used 15 important regions of interest (ROIs) for training, 70.6% accuracy was obtained, significantly exceeding the existing results of 68.6% from all ROIs. Additionally, to explore the new structure based on SCCNN-RNN, we performed the same experiment with three modified models: (1) separate channel CNN - RNN with attention (ASCRNN), (2) separate channel dilate CNN - RNN with attention (ASDRNN), (3) separate channel CNN - slicing RNN with attention (ASSRNN). The ASSRNN model provides a high accuracy of 70.46% when trained with only 13 important ROIs. These results show that using deep learning to identify the crucial parts of the brain in diagnosing ADHD yields better results than using every area. |
| first_indexed | 2024-03-11T12:20:55Z |
| format | Article |
| id | doaj.art-89a1f0d171f6459b80225d4deca71154 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T12:20:55Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-89a1f0d171f6459b80225d4deca711542023-11-07T00:02:37ZengIEEEIEEE Access2169-35362023-01-011111606511607510.1109/ACCESS.2023.332467010286029Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep LearningByunggun Kim0https://orcid.org/0000-0001-5655-7295Jaeseon Park1Taehun Kim2Younghun Kwon3https://orcid.org/0000-0001-9086-1127Department of Applied Artificial Intelligence, Hanyang University, ERICA Campus, Ansan, Republic of KoreaDepartment of Applied Artificial Intelligence, Hanyang University, ERICA Campus, Ansan, Republic of KoreaDepartment of Applied Artificial Intelligence, Hanyang University, ERICA Campus, Ansan, Republic of KoreaDepartment of Applied Artificial Intelligence, Hanyang University, ERICA Campus, Ansan, Republic of KoreaAlthough attention-deficit/hyperactivity disorder (ADHD) is a common psychiatric disorder, it is difficult to develop an accurate diagnostic method. Recently, studies to classify ADHD using resting-state functional magnetic resonance (rs-fMRI) imaging data have been conducted with the development of computing resources and machine learning techniques. Most of them use the entire brain’s regions when training the models. As opposed to the common approach, we conducted a study to classify ADHD by selecting essential areas for using a deep learning model. The experiment used rs-fMRI data from the ADHD-200 global competition. To obtain an integrated result from the multiple sites, each region of the brain is evaluated using ’leave- one-site-out’ cross-validation. As a result, when we only used 15 important regions of interest (ROIs) for training, 70.6% accuracy was obtained, significantly exceeding the existing results of 68.6% from all ROIs. Additionally, to explore the new structure based on SCCNN-RNN, we performed the same experiment with three modified models: (1) separate channel CNN - RNN with attention (ASCRNN), (2) separate channel dilate CNN - RNN with attention (ASDRNN), (3) separate channel CNN - slicing RNN with attention (ASSRNN). The ASSRNN model provides a high accuracy of 70.46% when trained with only 13 important ROIs. These results show that using deep learning to identify the crucial parts of the brain in diagnosing ADHD yields better results than using every area.https://ieeexplore.ieee.org/document/10286029/ADHDdeep learningrs-fMRIAAL116ROI |
| spellingShingle | Byunggun Kim Jaeseon Park Taehun Kim Younghun Kwon Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning IEEE Access ADHD deep learning rs-fMRI AAL116 ROI |
| title | Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning |
| title_full | Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning |
| title_fullStr | Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning |
| title_full_unstemmed | Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning |
| title_short | Finding Essential Parts of the Brain in rs-fMRI Can Improve ADHD Diagnosis Using Deep Learning |
| title_sort | finding essential parts of the brain in rs fmri can improve adhd diagnosis using deep learning |
| topic | ADHD deep learning rs-fMRI AAL116 ROI |
| url | https://ieeexplore.ieee.org/document/10286029/ |
| work_keys_str_mv | AT byunggunkim findingessentialpartsofthebraininrsfmricanimproveadhddiagnosisusingdeeplearning AT jaeseonpark findingessentialpartsofthebraininrsfmricanimproveadhddiagnosisusingdeeplearning AT taehunkim findingessentialpartsofthebraininrsfmricanimproveadhddiagnosisusingdeeplearning AT younghunkwon findingessentialpartsofthebraininrsfmricanimproveadhddiagnosisusingdeeplearning |