Document Type : Reseach Article

Authors

School of Computer Science and Engineering, VIT-AP University, Guntur, AP, INDIA

Abstract

Parkinson's Disease (PD) is a neurological disorder that causes progressive loss of brain cells. Despite the fact that there is no known cure for this neurodegenerative disease at present, early diagnosis and treatment may improve the quality of life. Magnetic Resonance Imaging (MRI) detects structural changes related to dopamine deficiency in PD. To categorize MRI scans as Healthy Control (HC) or PD, this study proposes an ensemble of Deep Convolution Neural Network (DCNN) models. Initially, we have used DCNN models using augmentation and transfer learning, to classify as PD or HC. In the next stage, we applied a classifier fusion ensemble approach to enhance the overall result of the classification model. The proposed model is trained using the data collected from PPMI database, while assessed on custom dataset which is created using the data collected from Lalitha Super Specialty Hospital (LSSH). Finally, it was observed that the developed ensemble model produced an outstanding performance by plotting an overall accuracy of 99%, while the transfer learned EfficientNet B1 DCNN model stood in the second position, achieving a remarkable accuracy of 98%. This study serves as a significant step forward, providing valuable insights for researchers and clinicians engaged in the domain of clinical image assessment using deep learning techniques.

Keywords

  • [1] Poewe, K. Seppi, et al., "Parkinson Disease," Nat Rev Dis Primers, vol. 3, p. 17013, 2017.
  • [2] R. Chaudhuri, A. H. Schapira, et al., "non-motor symptoms of Parkinson's disease: Dopaminergic pathophysiology and treatment," Lancet Neurol, vol. 8, no. 5, pp. 464-474, 2009.
  • [3] Xu, M. Zhang, "Use of magnetic resonance imaging and artificial intelligence in studies of diagnosis of PD," ACS Chem Neurosci, vol. 10, no. 1, pp. 445-449, 2019.
  • [4] Soltaninejad, I. Cheng, A. Basu, "Towards the identification of PD using only T1 MR images," ArXiv, abs/1806.07489, 2018.
  • [5] Naseer, M. Rani, "Refining Parkinson's neurological disorder identification through deep transfer learning," Neural Comput Appl, vol. 31, no. 5, pp. 1751-1762, 2019.
  • [6] Adeli, F. Shi, "Joint Feature-Sample Selection and Robust Diagnosis of Parkinson's Disease from MRI Data," NeuroImage, vol. 141, pp. 206-219, 2016.
  • [7] Amoroso, M. L. Rocca, A. Monaco, R. Bellotti, S. Tangaro, "Complex networks reveal early MRI markers of Parkinson's disease," Med. Image Anal, vol. 48, 12-24, 2018.
  • [8] Sivaranjini, C. M. Sujatha, "Deep learning-based diagnosis of Parkinson's disease using a convolutional neural network," Multimed Tools Appl, vol. 78, no. 1, 2019.
  • [9] Lei, Y. Zhao, Y. Wen, Q. Luo, Y. Cai, G. Liu, B. Lei, "Sparse feature learning for multi-class Parkinson's disease classification," Technol. Health Care, vol. 26, no. 1, pp. 193-203, 2018.
  • Salvatore, A. Cerasa, I. Castiglioni, F. Gallivanone, A. Augimeri, M. Lopez, G. Arabia, M. Morelli, M. C. Gilardi, A. Quattrone, "Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy," J. Neurosci. Methods, vol. 222, pp. 230-237, 2014.
  • Brahim, L. Khedher, J.M. Górriz, J. Ramírez, H. Toumi, E. Lespessailles, R. Jennane, M. El Hassouni, "A proposed computer-aided diagnosis system for Parkinson's disease classification using 123I-FP-CIT imaging," 2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2017, pp. 1-6.
  • Quan, L. Xu, R. Xu, T. Tong, J. Su, "DaTscan SPECT Image Classification for Parkinson's Disease," arXiv, 2019.
  • Rahmim, P. Huang, N. Shenkov, S. Fotouhi, E. Davoodi-Bojd, L. Lu, Z. Mari, H. Soltanian-Zadeh, V. Sossi, "Improved prediction of outcome in Parkinson's disease using radiomics analysis of longitudinal DAT SPECT images," NeuroImage: Clinical, vol. 16, pp. 539-544, 2017.
  • Choi, S. Ha, H. J. Im, S. H. Paek, D. S. Lee, "Refining diagnosis of Parkinson's disease with deep learning-based interpretation of dopamine transporter imaging," NeuroImage: Clinical, vol. 16, pp. 586-594, 2017.
  • Prashanth, S. Dutta Roy, P. K. Mandal, S. Ghosh, "High-accuracy classification of Parkinson's disease through shape analysis and surface fitting in 123I-Ioflupane SPECT imaging," IEEE journal of biomedical and health informatics, vol. 21, pp. 794-802, 2017.
  • Rumman, A. N. Tasneem, S. Farzana, M. I. Pavel, M. A. Alam, "Early detection of Parkinson’s disease using image processing and artificial neural network," 7th International Conference on Informatics, Electronics & Vision and 2nd International Conference on Imaging, Vision & Pattern Recognition, IEEE, 2018, pp. 256-261.
  • Ortiz, J. Munilla, M. Martínez-Ibañez, J. M. Górriz, J. Ramírez, D. Salas-Gonzalez, "Parkinson's disease detection using iso surfaces-based features and convolutional neural networks," Front. in neuro infor, vol. 13, 2019.
  • Chakraborty, S. Aich, H. C. Kim, "Detection of Parkinson’s disease from 3T T1 weighted MRI scans using 3D convolutional neural network," Diagnostics, vol. 10, no. 6, p. 402, 2020.
  • R. Magesh, R. D. Myloth, R. J. Tom, "An explainable machine learning model for early detection of Parkinson’s disease using lime on datscan imagery," Comput. Biol. Med., vol. 126, p. 104041, 2020.
  • Kaur, H. Aggarwal, R. Rani, "Diagnosis of Parkinson’s disease using deep CNN with transfer learning and data augmentation," Multimedia Tools and Appl, vol. 80, no. 7, pp. 10113-10139, 2021.
  • Farhan Mohammed, Xiangjian He, Yiguang Lin, "An easy-to-use deep-learning model for highly accurate diagnosis of Parkinson's disease using SPECT images," Comput Med Imaging Graph, 2021, 101810.
  • Theerasarn Pianpanit, Sermkiat Lolak, Phattarapong Sawangjai, Thapanun Sudhawiyangkul, Theerawit Wilaiprasitporn, "Parkinson’s disease recognition using SPECT image and interpretable AI: A tutorial," IEEE Sensors Journal, vol. 21, no. 20, pp. 22304-22316, 2021.
  • Chung-Yao Chien, Szu-Wei Hsu, Tsung-Lin Lee, Pi-Shan Sung, Chou-Ching Lin, "Using artificial neural network to discriminate Parkinson’s disease from Parkinsonisms by focusing on putamen of dopamine transporter SPECT images," Biomedicines, vol.9, no.1, 2020.
  • S Dhanalakshmi, M Thakur, Kuresan Harisudha, K Wee Lai, Xiang Wu, "Soft Attention Based DenseNet Model for Parkinson’s Disease Classification Using SPECT Images," Frontiers in Aging Neu.sci, vol. 532, 2022.
  • Liu, G. Tian, Y. Xu, "A different scene classification model is combining Res-Net based transfer learning and data augmentation with a filte," Neuro Comput J, vol. 338, pp. 191–206, 2019.
  • Shao, "Transfer learning for visual categorization: a survey," IEEE Trans Neural Netw Learn Syst, vol. 26, no. 5, pp. 1019–34, 2015.
  • Radford, Alec, Luke Metz, and Soumith Chintala, "Unsupervised representation learning with deep convolutional generative adversarial networks," arXiv preprint, 2015, arXiv:1511.06434.
  • Y. Shams, O. M. Elzeki, Mohamed Abd Elfattah, T. Medhat, Aboul Ella Hassanien, "Why are GANs vital for deep neural networks? A case study on COVID-19 chest X-ray images," Springer, 2020, pp. 147-162.
  • Archana G, Afzal Hussain S, "A comparative study on performance of basic and ensemble classifiers with various datasets," Applied Computer Science, vol.19, 2023.
  • Ledig, L.Theis, F.Huszár, J.Caballero, A.Cunningham, A.Acosta, "Photo-realistic image super-resolution using a generative adversarial network," ArXiv Prepr, 2016.
  • Isola, J.-Y. Zhu, T. Zhou, A. A. Efros, "Image-to-image translation with conditional adversarial networks," ArXiv Prepr, 2017.
  • Wu, S.Zheng, J.Zhang, K.Huang, "Gp-gan: Towards realistic high-resolution image blending," ArXiv Prepr, 2017.
  • A. Yeh, C. Chen, T. Y. Lim, A. G. Schwing, M. Hasegawa-Johnson, M. N. Do, "Semantic image inpainting with deep generative models," IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 5485–5493.
  • Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, Y. Bengio, "Generative adversarial nets," Advances in neural information processing systems, 2014.
  • Iqbal, H. Ali, "Generative adversarial network for medical images (MI-GAN)," J Med Syst, vol. 42, 2018.
  • Mikołajczyk, M. Grochowski, "Data augmentation for improving deep learning in image classification problem," 2018 international interdisciplinary PhD workshop (IIPhDW), IEEE, 2018.
  • Weng, H. Zhou, "Data augmentation computing model based on generative adversarial network," IEEE Access, 2019, 2917207.
  • J. Yoo, "Hyperparameter optimization of deep neural network using univariate dynamic encoding algorithm for searches," Knowl Based Syst, vol. 178, pp. 74–83, 2019.
  • Kaur, H. Aggarwal, R. Rani, "Diagnosis of PD using principal component analysis and deep learning," J Med Imaging Health Inf, vol. 9, no. 3, pp. 602–609, 2019.
  • Nazari, M. Aghemiri, A. Avan, A. Mehrabian, "Machine learning approaches for classification of colorectal cancer with and without feature selection method on microarray data," Gene Reports, vol. 25, p. 101419, 2021.
  • Tewari, U. D. Dwivedi, "A comparative study of heterogeneous ensemble methods for the identification of geological lithofacies," Journal of Petroleum Exploration and Production Technology, vol. 10, 2020.
  • Castillo-Barnes, J. Ramírez, F. Segovia, F. Martínez-Murcia, D. Salas-Gonzalez, J. Górriz, "Robust ensemble classification methodology for i123-ioflupane spect images and multiple heterogeneous biomarkers in the diagnosis of parkinson's disease," Front. Neuroinformatics, 2018.
  • Ruder, "An overview of gradient descent optimization algorithms," arXiv preprint, 1609.04747, 2016.
  • Keys, "Cubic convolution interpolation for digital image processing," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 29, no. 6, pp. 1153-1160, 1981.
  • Kumar, M. Nachamai, "Noise Removal and Filtering Techniques Used in Medical Images," Orient.J. Comp. Sci. and Technol, vol. 10, no. 1, 2017.
  • P. Kingma, J. Ba, "Adam: A Method for Stochastic Optimization," International Conference on Learning Representations, California, 2015.
  • C. Wilson, R. Roelofs, M. Stern, N. Srebro, B. Recht, "The marginal value of adaptive gradient methods in machine learning," Advances in neural information processing systems, vol. 30, 2017.
  • Wang, Q. Zhang, H. Li, H. Zhang, "SPECT molecular imaging in Parkinson's disease", BioMed Research International, 2012.
  • Huang, B. Sherman, R. Lempicki, "Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources", Nat Protoc, vol. 4, 44–57, 2009.
  • Frid-Adar, I. Diamant, E. Klang, M. Amitai, J. Goldberger, H. Greenspan, "GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification", Neurocomputing, vol. 321, 2018.
  • H. Houssein, Z. Abohashima, Elhoseny Mohamed, W. M. Mohamed, "Hybrid quantum-classical convolutional neural network model for COVID-19 prediction using chest X-ray images", Journal of Computational Design and Engineering, 2022, vol. 9, pp. 343–363.
  • Zang Cho, "Review of Recent Advancement of Ultra High Field Magnetic Resonance Imaging: from Anatomy to Tractography", Investigative Magnetic Resonance Imaging, 2016, vol. 20, pp. 141.
  • M. Smith, M. Jenkinson, M. W. Woolrich, C. F. Beckmann, T. E. J. Behrens, H. Johansen-Berg, "Advances in functional and structural MR image analysis and implementation as FSL", Neuroimage, vol. 23, 2004.
  • Jenkinson, C. F. Beckmann, T. E. Behrens, M. W. Woolrich, "FSL", Neuroimage, vol. 62, pp. 782–90, 2012.
  • Grabner, A.L.Janke, M.M.Budge, D.Smith, J. Pruessner, "Symmetric atlasing and model-based segmentation: an application to the hippocampus in older adults," Med Image Comput Comput Assist Interv., 2006, vol. 9.
  • https://towardsdatascience.com/the-annotated-resnet-50-a6c536034758/
  • Li, J. Hou, L. Yin, "A classifier fusion method based on classifier accuracy," 2014 International Conference on Mechatronics and Control (ICMC), Jinzhou, China, pp. 2119-2122, d2016, oi: 10.1109/ICMC57404.2022.00020.
  • Rokach, L., "Ensemble Learning", World Scientific Publishing Co Pte Ltd, 2019, 300.
  • Dietterich, T. G., "Ensemble methods in machine learning," International workshop on multiple classifier systems, pp. 1-15: Springer Berlin Heidelberg, 2000.
  • Al-Khasawneh, M. A., A. Alzahrani, A. Alarood, "Alzheimer’s Disease Diagnosis Using MRI Images," In Data Analysis for Neurodegenerative Disorders, pp. 195-212, Springer Nature Singapore, 2023.
  • Wang and Y. Zhang, "Grad-CAM: Understanding AI Models," Comput. Mater. Contin., vol.76, 2023.
  • R. Palakayala and K. P, "Survey of Parkinson's Disease Detection using Different Symptoms," in Algorithms, Computing and Mathematics Conference (ACM), Chennai, India, 2022, pp. 77-82, doi: 10.1109/ACM57404.2022.00020.
  • Aditi Govindu, Sushila Palwe, “Early detection of Parkinson's disease using machine learning.