DongYue Wang, Dept. of Computer Science, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, Korea
TaegKeun Whangbo, Dept. of Computer Science, Gachon University, Sujeong-Gu, Seongnam-Si, Gyeonggi-Do, Korea
Magnetic resonance (MR) imaging of the midbrain is the primary means for the diagnosis of Parkinson’s disease (PD). However, it is difficult to diagnose PD manually using MR images. Therefore, we developed an automatic diagnostic system for PD based on deep learning using midbrain MR images. The system is component of two neural networks. The first one is the Faster R-CNN, which identifies the areas that may be used for PD diagnosis from midbrain MR images. As Parkinsonian images are highly similar, the non-diagnostic areas that can’t be used for diagnosis may also be detected by the network during the detection of the areas of interest. Thus, we have three types of identified images, namely, normal, Parkinsonian, and non-diagnostic images. The second neural network is a convolutional neural network defined herein, which classifies the areas identified in the first network. We used MR images of 350 patients for training and testing, and the results showed this system exhibits a higher accuracy in PD diagnosis.
Parkinson’s Disease; Faster R-CNN; CNN; Deep Learning
[1] Hughes, Andrew J., et al., "Accuracy of clinical diagnosis of idiopathic Parkinson's disease: a clinico-pathological study of 100 cases." Journal of Neurology, Neurosurgery & Psychiatry, vol. 55, no. 3, (1992), pp.181-184, available online: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1014720/.
[2] Jankovic, Joseph, et al., "Variable expression of Parkinson's disease A base‐line analysis of the DAT ATOP cohort." Neurology, vol. 40, no. 10, (1990), pp: 1529-1529, https://www.ncbi.nlm.nih.gov/pubmed/2215943.
[3] Quattrone, Aldo, et al., "MR imaging index for differentiation of progressive supranuclear palsy from Parkinson disease and the Parkinson variant of multiple system atrophy.", Radiology, vol. 246, no. 1 (2008), pp:214-221, available online: https://www.ncbi.nlm.nih.gov/pubmed/17991785.
[4] Ren, S., He, K., Girshick, R., & Sun, J., "Faster r-cnn: Towards real-time object detection with region proposal networks." In Advances in neural information processing systems, (2015), pp: 91-99, available online: http://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdf.
[5] LeCun, Yann, and Yoshua Bengio, "Convolutional networks for images, speech, and time series.", The handbook of brain theory and neural networks, vol. 3361, no. 10, (1995), https://www.researchgate.net/profile/Yann_Lecun/publication/2453996_Convolutional_Networks
_for_Images_Speech_and_Time-Series/links/0deec519dfa2325502000000.pdf.
[6] Praveen Ch, ra, "A Survey on Deep Learning its Architecture and Various Applications.", Asia-Pacific Journal of Neural Networks and Its Applications, vol. 1, no. 2, (2017) September.
[7] Abraham, Ajith. "Artificial neural networks." handbook of measuring system design, (2005), https://onlinelibrary.wiley.com/doi/pdf/10.1002/0471497398.mm421.
[8] Hecht-Nielsen, Robert, "Theory of the backpropagation neural network.", Neural networks for perception, (1992), pp:65-93, https://doi.org/10.1016/B978-0-12-741252-8.50010-8.
[9] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems, (2012), pp:1097-1105, available online: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf.
[10] Han, Jun, and Claudio Moraga, "The influence of the sigmoid function parameters on the speed of backpropagation learning." International Workshop on Artificial Neural Networks. Springer, Berlin, Heidelberg, (1995), pp:195-201.
[11] Malfliet, Willy, and Willy Hereman. "The tanh method: I. Exact solutions of nonlinear evolution and wave equations." Physica Scripta, Vol.54, No.6, (1996), http://iopscience.iop.org/article/10.1088/0031-8949/54/6/003/meta.
[12] Li, Yuanzhi, and Yang Yuan, "Convergence analysis of two-layer neural networks with relu activation", Advances in Neural Information Processing Systems, 2017, pp:597-607.
[13] Scherer, Dominik, Andreas Müller, and Sven Behnke, "Evaluation of pooling operations in convolutional architectures for object recognition", Artificial Neural Networks–ICANN, Springer, Berlin, Heidelberg, (2010), pp:92-101, https://link.springer.com/chapter/10.1007%2F978-3-642-15825-4_10.
[14] Srivastava, Nitish, et al., "Dropout: a simple way to prevent neural networks from overfitting", The Journal of Machine Learning Research, Vol.15, No.1, (2014), pp: 1929-1958, https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf.
[15] Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv, (2014), pp:1409-1556, available online: https://arxiv.org/abs/1409.1556v6.
[16] Szegedy, Christian, et al. "Going deeper with convolutions", Proceedings of the IEEE conference on computer vision and pattern recognition, (2015), pp:1-9, https://ieeexplore.ieee.org/document/7298594/.
[17] He, Kaiming, et al., "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, (2016), pp:770-778, https://arxiv.org/abs/1512.03385.
[18] Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the IEEE conference on computer vision and pattern recognition, (2014), pp:580-587, https://arxiv.org/pdf/1311.2524.pdf.
[19] Girshick, Ross. "Fast r-cnn", Proceedings of the IEEE international conference on computer vision, (2015), pp:1440-1448, https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Girshick_Fast_R-CNN_ICCV_2015_paper.pdf.
[20] Gelb, Douglas J., Eugene Oliver, and Sid Gilman, "Diagnostic criteria for Parkinson disease", Archives of neurology, Vol.56, No.1, (1999), pp:33-39, https://jamanetwork.com/journals/jamaneurology/article-abstract/774675.
[21] Schwarz, Stefan T., et al. "The ‘Swallow Tail’Appearance of the Healthy Nigrosome–A New Accurate Test of Parkinson's Disease: A Case-Control and Retrospective Cross-Sectional MRI Study at 3T", PloS one, Vol.9, No.4, (2014): e93814, https://www.ncbi.nlm.nih.gov/pubmed/24710392.
[22] Tang, Wenyi, Bin Liu, and Nenghai Yu, "Deep Scale Feature for Visual Tracking", International Conference on Image and Graphics, Springer, Cham, (2017), https://link.springer.com/chapter/10.1007/978-3-319-71607-7_27.
[23] Hu, Wei, et al., "Deep convolutional neural networks for hyperspectral image classification", Journal of Sensors 2015, (2015), http://dx.doi.org/10.1155/2015/258619.
[24] Cireşan, Dan, Ueli Meier, and Jürgen Schmidhuber, "Multi-column deep neural networks for image classification", arXiv preprint arXiv:1202.2745 (2012), https://arxiv.org/abs/1202.2745.
[25] Jun Mo Jeong, Se Jin Choi, Chiyong Kim3,"Correcting Method of Numerical errors of Soft-max and Cross-entropy according to CNN’s Output value".Asia-Pacific Journal of Neural Networks and Its Applications.Vol.1, No.1, May(2017).
[26] Abadi, Martín, et al., "Tensorflow: a system for large-scale machine learning", OSDI. Vol. 16, (2016), https://arxiv.org/abs/1605.08695.
[27] Chollet, François. "Keras." (2015), https://keras.io/.
[28] https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_tutorials.html
APA:
Wang, D. Y., & Whangbo, T. K. (2019). Automatic Diagnostic System for Parkinson’s Disease Based on Deep Learning Using Midbrain Magnetic Resonance Images. International Journal of Advanced Science and Technology (IJAST), ISSN: 2005-4238(Print); 2207-6360 (Online), NADIA, 124, 1-20. doi: 10.33832/ijast.2019.124.01.
MLA:
Wang, DongYue, et al. “Automatic Diagnostic System for Parkinson’s Disease Based on Deep Learning Using Midbrain Magnetic Resonance Images.” International Journal of Advanced Science and Technology, ISSN: 2005-4238(Print); 2207-6360 (Online), NADIA, vol. 124, 2019, pp. 1-20. IJAST, http://article.nadiapub.com/IJAST/Vol124/1.html.
IEEE:
[1] D. Y. Wang and T. K. Whangbo, “Automatic Diagnostic System for Parkinson’s Disease Based on Deep Learning Using Midbrain Magnetic Resonance Images.” International Journal of Advanced Science and Technology (IJAST), ISSN: 2005-4238(Print); 2207-6360 (Online), NADIA, vol. 124, pp. 1-20, Mar. 2019.
IJAST aims to facilitate and support research related to advanced science and technology and the applications. Our Journal provides a chance for academic and industry professionals to discuss recent progress in the areas of advanced science and technology.
