Modified VGG-19 Deep Learning Strategies for Parkinson's Disease Diagnosis - A Comprehensive Review and Novel Approach
Aruna Kokkula 1*, P. Chandra Sekhar 2, T. M. Praneeth Naidu 3
Journal of Angiotherapy 8(3) 1-11 https://doi.org/10.25163/angiotherapy.839559
Submitted: 10 January 2024 Revised: 01 March 2024 Published: 04 March 2024
Abstract
Background: The incidence of neurodegenerative diseases like Alzheimer's and Parkinson's is increasing among ageing populations in industrialized nations, highlighting the need for better and faster diagnostic tools for early detection. Advanced machine learning algorithms have emerged to assist in the categorization and preliminary risk evaluation of Parkinson's disease (PD) patients, leveraging publicly available data. This study aimed to enhance PD diagnosis using Magnetic Resonance Imaging (MRI) by examining deep learning architectures and evaluating their performance using various criteria. Methods: This study developed an accurate PD detection technique using MRI scans. A novel deep learning system was implemented, incorporating a Fully Connected (FC) layer and dropout, with a proposed VGG19 model that evolves through normalization and incrementing layers. These enhancements improve model normalization, ability, and task-specific flexibility. The training process utilized MRI scans from both healthy individuals and PD patients. Results: The network was tested on extensive MRI datasets for tasks including dementia grading, brain tumor classification, and disease classification, using 10-fold cross-validation. The Attention Feature Fusion VGG19 (AFF-VGG19) network achieved an accuracy of 0.984 in differentiating between three classes of brain tumors, 0.976 in distinguishing between Alzheimer's and Parkinson's diseases, and 0.977 in grading dementia cases. Conclusion: This research suggests that integrating attention modules, feature-fusion blocks, and baseline convolutional neural networks significantly enhances the performance of deep learning models in diagnosing neurodegenerative diseases using MRI scans.
Keywords: Deep learning, Parkinson's disease, VGG19, MRI images.
References
Basnin, N., Nahar, N., Anika, F.A., Hossain, M.S. and Andersson, K., (2021). Deep learning approach to classify Parkinson’s disease from MRI samples. In International conference on brain informatics, pp. 536-547. https://doi.org/10.1007/978-3-030-86993-9_48.
Camacho, M., Wilms, M., Mouches, P., Almgren, H., Souza, R., Camicioli, R., Ismail, Z., Monchi, O. and Forkert, N.D., (2023). Explainable classification of Parkinson’s disease using deep learning trained on a large multi-center database of T1-weighted MRI datasets. NeuroImage: Clinical, 38, pp. 103405. https://doi.org/10.1016/j.nicl.2023.103405.
Kaplan, E., Altunisik, E., Firat, Y.E., Barua, P.D., Dogan, S., Baygin, M., Demir, F.B., Tuncer, T., Palmer, E., Tan, R.S. and Yu, P., (2022). Novel nested patch-based feature extraction model for automated Parkinson's Disease symptom classification using MRI images. Computer Methods and Programs in Biome`dicine, 224, pp. 107030. https://doi.org/10.1016/j.cmpb.2022.107030.
Loh, H.W., Hong, W., Ooi, C.P., Chakraborty, S., Barua, P.D., Deo, R.C., Soar, J., Palmer, E.E. and Acharya, U.R., (2021). Application of deep learning models for automated identification of Parkinson’s disease: A review. Sensors, 21(21), pp. 1-25. https://doi.org/10.3390/s21217034.
Madan, Y., Veetil, I.K., Sowmya, V., Gopalakrishnan, E.A. and Soman, K.P., (2021). Deep learning-based approach for parkinson’s disease detection using region of interest. In Intelligent Sustainable Systems: Proceedings of ICISS, pp. 1-13. https://doi.org/10.1007/978-981-16-2422-3_1.
Noor, M.B.T., Zenia, N.Z., Kaiser, M.S., Mahmud, M. and Al Mamun, S., (2019). Detecting neurodegenerative disease from MRI: a brief review on a deep learning perspective. In Brain Informatics: 12th International Conference, BI, Proceedings 12, pp. 115-125. https://doi.org/10.1007/978-3-030-37078-7_12.
Noor, M.B.T., Zenia, N.Z., Kaiser, M.S., Mamun, S.A. and Mahmud, M., (2020). Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia. Brain informatics, 7, pp. 1-21. https://doi.org/10.1186/s40708-020-00112-2.
Pahuja, G. and Prasad, B., (2022). Deep learning architectures for Parkinson's disease detection by using multi-modal features. Computers in Biology and Medicine, 146, pp. 105610. https://doi.org/10.1016/j.compbiomed.2022.105610.
Pourzinal, D., Yang, J., Lawson, R.A., McMahon, K.L., Byrne, G.J. and Dissanayaka, N.N., (2022). Systematic review of data-driven cognitive subtypes in Parkinson disease. European journal of neurology, 29(11), pp. 3395-3417. https://doi.org/10.1111/ene.15481.
Rajanbabu, K., Veetil, I.K., Sowmya, V., Gopalakrishnan, E.A. and Soman, K.P., (2022). Ensemble of deep transfer learning models for parkinson's disease classification. In Soft Computing and Signal Processing: Proceedings of 3rd ICSCSP, 2, pp. 135-143. https://doi.org/10.1007/978-981-16-1249-7_14.
Sahu, L., Sharma, R., Sahu, I., Das, M., Sahu, B. and Kumar, R., (2022). Efficient detection of Parkinson's disease using deep learning techniques over medical data. Expert Systems, 39(3), p.e12787. https://doi.org/10.1111/exsy.12787.
Sailaja, B. and VenuGopal, T., (2023). Brain MRI Image Classification and Analysis Using Modified ResNet50V2 for Parkinson’s Disease Detection. SN Computer Science, 4(6), pp. 854. https://doi.org/10.1007/s42979-023-02313-y.
Shu, Z.Y., Cui, S.J., Wu, X., Xu, Y., Huang, P., Pang, P.P. and Zhang, M., (2021). Predicting the progression of Parkinson's disease using conventional MRI and machine learning: An application of radiomic biomarkers in whole-brain white matter. Magnetic resonance in medicine, 85(3), pp. 1611-1624. https://doi.org/10.1002/mrm.28522.
Sivaranjini, S. and Sujatha, C.M., 2020. Deep learning based diagnosis of Parkinson’s disease using convolutional neural network. Multimedia tools and applications, 79(21), pp. 15467-15479.https://doi.org/10.1007/s11042-019-7469-8.
Solana-Lavalle, G. and Rosas-Romero, R., (2021). Classification of PPMI MRI scans with voxel-based morphometry and machine learning to assist in the diagnosis of Parkinson’s disease. Computer Methods and Programs in Biomedicine, 198, pp. 105793. https://doi.org/10.1016/j.cmpb.2020.105793.
Vyas, T., Yadav, R., Solanki, C., Darji, R., Desai, S. and Tanwar, S., (2022). Deep learning-based scheme to diagnose Parkinson's disease. Expert Systems, 39(3), pp. e12739. https://doi.org/10.1111/exsy.12739.
Wang, Y., He, N., Zhang, C., Zhang, Y., Wang, C., Huang, P., Jin, Z., Li, Y., Cheng, Z., Liu, Y. and Wang, X., 2023. An automatic interpretable deep learning pipeline for accurate Parkinson's disease diagnosis using quantitative susceptibility mapping and T1-weighted images, 44(12), pp. 4426-4438. https://doi.org/10.1002/hbm.26399.
Wingate, J., Kollia, I., Bidaut, L. and Kollias, S., (2020). Unified deep learning approach for prediction of Parkinson's disease. IET Image Processing, 14(10), pp. 1980-1989. https://doi.org/10.1049/iet-ipr.2019.1526.
Zhao, H., Tsai, C.C., Zhou, M., Liu, Y., Chen, Y.L., Huang, F., Lin, Y.C. and Wang, J.J., (2022). Deep learning based diagnosis of Parkinson’s Disease using diffusion magnetic resonance imaging. Brain imaging and behavior, 16(4), pp. 1749-1760. https://doi.org/10.1007/s11682-022-00631-y.
View Dimensions
View Altmetric
Save
Citation
View
Share