Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data
Abstract Parkinson’s disease is a chronic and progressive movement disorder caused by the degeneration of dopamine-producing neurons in the substantia nigra of the brain. Currently, there is no specific diagnostic test available for Parkinson’s disease, and physicians rely on symptoms and medical hi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-08-01
|
| Series: | Journal of Engineering and Applied Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s44147-023-00236-2 |
| _version_ | 1797452499107446784 |
|---|---|
| author | Nair Ul Islam Ruqaiya Khanam Ashok Kumar |
| author_facet | Nair Ul Islam Ruqaiya Khanam Ashok Kumar |
| author_sort | Nair Ul Islam |
| collection | DOAJ |
| description | Abstract Parkinson’s disease is a chronic and progressive movement disorder caused by the degeneration of dopamine-producing neurons in the substantia nigra of the brain. Currently, there is no specific diagnostic test available for Parkinson’s disease, and physicians rely on symptoms and medical history for diagnosis. In this study, a 3D-CNN deep learning model is proposed for detecting Parkinson’s disease using 4D-fMRI data. The data is preprocessed using independent component analysis (ICA) and dual regression processes through MELODIC in FSL, which results in a sequence of 30 3D spatial maps, each with its unique time course. A reference network, referred to as an atlas, is then applied using the fslcc command in FSL to map the 3D spatial maps. Fourteen resting-state networks (RSNs) are identified successfully, while the remaining maps are rejected as noise or artifacts. The detected RSNs or 3D spatial maps are fed into the 3D-CNN model, which is trained with a 10-fold cross-validation method. The proposed model has an accuracy of 86.07% on average. |
| first_indexed | 2024-03-09T15:09:32Z |
| format | Article |
| id | doaj.art-2c2312c810ef44fb8ad4bea0893a816d |
| institution | Directory Open Access Journal |
| issn | 1110-1903 2536-9512 |
| language | English |
| last_indexed | 2024-03-09T15:09:32Z |
| publishDate | 2023-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Engineering and Applied Science |
| spelling | doaj.art-2c2312c810ef44fb8ad4bea0893a816d2023-11-26T13:27:46ZengSpringerOpenJournal of Engineering and Applied Science1110-19032536-95122023-08-0170111310.1186/s44147-023-00236-2Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI dataNair Ul Islam0Ruqaiya Khanam1Ashok Kumar2Department of Computer Science and Engineering, Sharda UniversityDepartment of Electronics and Communication Engineering, Center for AI in Medicine, Imaging and Forensic, Sharda UniversityCenter for AI in Medicine, Imaging and Forensic, Sharda UniversityAbstract Parkinson’s disease is a chronic and progressive movement disorder caused by the degeneration of dopamine-producing neurons in the substantia nigra of the brain. Currently, there is no specific diagnostic test available for Parkinson’s disease, and physicians rely on symptoms and medical history for diagnosis. In this study, a 3D-CNN deep learning model is proposed for detecting Parkinson’s disease using 4D-fMRI data. The data is preprocessed using independent component analysis (ICA) and dual regression processes through MELODIC in FSL, which results in a sequence of 30 3D spatial maps, each with its unique time course. A reference network, referred to as an atlas, is then applied using the fslcc command in FSL to map the 3D spatial maps. Fourteen resting-state networks (RSNs) are identified successfully, while the remaining maps are rejected as noise or artifacts. The detected RSNs or 3D spatial maps are fed into the 3D-CNN model, which is trained with a 10-fold cross-validation method. The proposed model has an accuracy of 86.07% on average.https://doi.org/10.1186/s44147-023-00236-2Parkinson’s diseaseDeep learningArtificial intelligenceMedical imagingHealthcareMRI |
| spellingShingle | Nair Ul Islam Ruqaiya Khanam Ashok Kumar Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data Journal of Engineering and Applied Science Parkinson’s disease Deep learning Artificial intelligence Medical imaging Healthcare MRI |
| title | Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data |
| title_full | Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data |
| title_fullStr | Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data |
| title_full_unstemmed | Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data |
| title_short | Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data |
| title_sort | using 3d cnn for classification of parkinson s disease from resting state fmri data |
| topic | Parkinson’s disease Deep learning Artificial intelligence Medical imaging Healthcare MRI |
| url | https://doi.org/10.1186/s44147-023-00236-2 |
| work_keys_str_mv | AT nairulislam using3dcnnforclassificationofparkinsonsdiseasefromrestingstatefmridata AT ruqaiyakhanam using3dcnnforclassificationofparkinsonsdiseasefromrestingstatefmridata AT ashokkumar using3dcnnforclassificationofparkinsonsdiseasefromrestingstatefmridata |