Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation
Parkinson's disease is one of the types of neurological diseases that is caused by the destruction of brain cells that produce dopamine. Early detection of Parkinson's disease is an important factor in slowing the progression of the disease. In this study, a Convolutional Neural Network (C...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
University of Qom
2024-09-01
|
| Series: | مدیریت مهندسی و رایانش نرم |
| Subjects: | |
| Online Access: | https://jemsc.qom.ac.ir/article_3048_7cf9cbcc4c7b5f32d1ac349f6c06be46.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832577571213017088 |
|---|---|
| author | Reyhaneh Dehghan Marjan Naderan Seyed Enayatallah Alavi |
| author_facet | Reyhaneh Dehghan Marjan Naderan Seyed Enayatallah Alavi |
| author_sort | Reyhaneh Dehghan |
| collection | DOAJ |
| description | Parkinson's disease is one of the types of neurological diseases that is caused by the destruction of brain cells that produce dopamine. Early detection of Parkinson's disease is an important factor in slowing the progression of the disease. In this study, a Convolutional Neural Network (CNN) namely ConvNet, is used to discriminate Parkinson's patients based on Single Photon Emission Computed Tomography (SPECT) images acquired from the PPMI database. Since the dataset is limited, after a pre-processing stage, two data augmentation techniques are used. Finally, the Grad-CAM technique is used to obtain visual interpretation from the predictions of the proposed CNN. To evaluate the proposed method, different measures such as accuracy, sensitivity (recall) and f1-score are used. Simulation results according to the measures shows that when the classic data augmentation method is used accuracy is increased to 98.50% and more efficient classification is performed. |
| format | Article |
| id | doaj-art-f9afb81163174c88bf16eb13a3a9cb77 |
| institution | Kabale University |
| issn | 2538-6239 2538-2675 |
| language | fas |
| publishDate | 2024-09-01 |
| publisher | University of Qom |
| record_format | Article |
| series | مدیریت مهندسی و رایانش نرم |
| spelling | doaj-art-f9afb81163174c88bf16eb13a3a9cb772025-01-30T20:19:19ZfasUniversity of Qomمدیریت مهندسی و رایانش نرم2538-62392538-26752024-09-0110111310.22091/jemsc.2024.10828.11803048Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual ExplanationReyhaneh Dehghan0Marjan Naderan1Seyed Enayatallah Alavi2Department of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, IranDepartment of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, IranDepartment of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, IranParkinson's disease is one of the types of neurological diseases that is caused by the destruction of brain cells that produce dopamine. Early detection of Parkinson's disease is an important factor in slowing the progression of the disease. In this study, a Convolutional Neural Network (CNN) namely ConvNet, is used to discriminate Parkinson's patients based on Single Photon Emission Computed Tomography (SPECT) images acquired from the PPMI database. Since the dataset is limited, after a pre-processing stage, two data augmentation techniques are used. Finally, the Grad-CAM technique is used to obtain visual interpretation from the predictions of the proposed CNN. To evaluate the proposed method, different measures such as accuracy, sensitivity (recall) and f1-score are used. Simulation results according to the measures shows that when the classic data augmentation method is used accuracy is increased to 98.50% and more efficient classification is performed.https://jemsc.qom.ac.ir/article_3048_7cf9cbcc4c7b5f32d1ac349f6c06be46.pdfparkinson's disease (pd)convolutional neural network (cnn)spect imagesdata augmentationgrad-cam |
| spellingShingle | Reyhaneh Dehghan Marjan Naderan Seyed Enayatallah Alavi Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation مدیریت مهندسی و رایانش نرم parkinson's disease (pd) convolutional neural network (cnn) spect images data augmentation grad-cam |
| title | Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation |
| title_full | Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation |
| title_fullStr | Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation |
| title_full_unstemmed | Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation |
| title_short | Combining Convolutional Neural Network (CNN) and Grad-CAM for Parkinson’s Disease Prediction and Visual Explanation |
| title_sort | combining convolutional neural network cnn and grad cam for parkinson s disease prediction and visual explanation |
| topic | parkinson's disease (pd) convolutional neural network (cnn) spect images data augmentation grad-cam |
| url | https://jemsc.qom.ac.ir/article_3048_7cf9cbcc4c7b5f32d1ac349f6c06be46.pdf |
| work_keys_str_mv | AT reyhanehdehghan combiningconvolutionalneuralnetworkcnnandgradcamforparkinsonsdiseasepredictionandvisualexplanation AT marjannaderan combiningconvolutionalneuralnetworkcnnandgradcamforparkinsonsdiseasepredictionandvisualexplanation AT seyedenayatallahalavi combiningconvolutionalneuralnetworkcnnandgradcamforparkinsonsdiseasepredictionandvisualexplanation |