Early Diagnosis of Neurodegenerative Diseases Using CNN-LSTM and Wavelet Transform
Tóm tắt
Early diagnosis of neurodegenerative diseases has always been a major challenge that physicians and medical practitioners face. Therefore, using any method or device that helps with prognostics is of great importance. In recent years, deep neural networks have become popular in medical fields, and the reason is that these networks can help diagnose diseases quickly and precisely. In this research, two novel models based on a CNN-LSTM network are introduced. The main goal is to classify three neurodegenerative diseases, including ALS, Parkinson’s disease, and Huntington’s disease, from one another and from healthy control patients using the gait signals, which are transformed into spectrogram images. In the first model, the spectrogram images derived from the gait signals are fed into a CNN-LSTM network directly. This model achieved 99.42% accuracy. In the second model, the same input data was used to be classified using a CNN-LSTM network, which uses wavelet transform as a feature extractor before the LSTM unit. During the experiments with the second model, the detail sub-bands were eliminated one by one, and the classification results were compared. Comparing these two models has shown that using the wavelet transform and, in particular, the approximation sub-bands can result in a lighter and faster prognosis with nearly 103 times fewer training parameters overall. The classification result using only approximation sub-bands was 95.37%, using three sub-bands was 94.04%, and including all sub-bands was 94.53%, which is remarkable.
Tài liệu tham khảo
Galimberti D, Scarpini E. (2018) Neurodegenerative diseases: clinical aspects, molecular genetics and biomarkers, Springer International Publishing, 179–182
Hausdorff JM, Lertratanakul A, Cudkowicz ME, Peterson AL, Kaliton D, Goldberger AL. (1985) Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis. J Appl Physiol. https://doi.org/10.1152/jappl.2000.88.6.2045
Hausdorff JM, Mitchell SL, Firtion R, Peng CK, Cudkowicz ME, Wei JY, Goldberger AL. (1985) Altered fractal dynamics of gait: reduced stride-interval correlations with aging and Huntington’s disease. J Appl Physiol. https://doi.org/10.1152/jappl.1997.82.1.262
Zhao A, Qi L, Dong J, Yu H. (2018) Dual channel LSTM based multi-feature extraction in gait for diagnosis of neurodegenerative diseases. Knowledge-Based Systems. https://doi.org/10.1016/j.knosys.2018.01.004
Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE. (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. https://doi.org/10.1161/01.cir.101.23.e215
Ning Z, Li L, Jin X. (2018) "Classification of neurodegenerative diseases based on CNN and LSTM," in 2018 9th International Conference on Information Technology in Medicine and Education (ITME), Hangzhou, China, 82–85. https://doi.org/10.1109/ITME.2018.00029
Petrosian AA, Prokhorov DV, Lajara-Nanson W, Schiffer RB. (2001) Recurrent neural network-based approach for early recognition of Alzheimer’s disease in EEG. Clin Neurophysiol. 1378–87. https://doi.org/10.1016/s1388-2457(01)00579-x
Oh SL, Hagiwara Y, Raghavendra U. (2020) A deep learning approach for Parkinson’s disease diagnosis from EEG signals, Neural Comput & Applic. 10927–10933. https://doi.org/10.1007/s00521-018-3689-5
Ruffini G, Ibañez D, Castellano M, Dubreuil-Vall L, Soria-Frisch A, Postuma R, Gagnon JF, Montplaisir J. (2019) Deep learning with EEG spectrograms in rapid eye movement behavior disorder, Frontiers in Neurology. https://doi.org/10.3389/fneur.2019.00806
Xu G, Ren T, Chen Y, Che W. (2020) (A one-dimensional CNN-LSTM model for epileptic seizure recognition using EEG signal analysis, Frontiers in Neuroscience. https://doi.org/10.3389/fnins.2020.578126
Ramos-Aguilar R, Olvera-López JA, Olmos-Pineda I.(2017) Analysis of EEG signal processing techniques based on spectrograms, Research in Computing Science. 151–162. https://doi.org/10.13053/RCS-145-1-12
Blackman RB, Tukey JW. (1958) The measurement of power spectra from the Point of View of Communications Engineering — Part I, Dover Publications. 185–282. https://doi.org/10.1002/j.1538-7305.1958.tb03874.x
Blackman RB, Tukey JW. (1958) The measurement of power spectra from the Point of View of Communications Engineering — Part II, Dover Publications,485–569. https://doi.org/10.1002/j.1538-7305.1958.tb01530.x
Kaiser JF (1966) Digital Filters” – Ch 7 in “Systems analysis by digital computer. John Wiley and Sons, New York, pp 218–285
Sejdic E, Djurovic I, Jiang J.(2009) Time–frequency feature representation using energy concentration: an overview of recent advances. Digital Signal Processing. 153–183. https://doi.org/10.1016/j.dsp.2007.12.004
Daubechies I. (1990) "The wavelet transform, time-frequency localization and signal analysis," in IEEE Transactions on Information Theory. 961–1005. https://doi.org/10.1109/18.57199
Chui C, Heil C. (1992) An introduction to wavelets, computers in physics. 6. 697-. https://doi.org/10.1063/1.4823126
Valueva MV, Nagornov NN, Lyakhov PA, Valuev GV, Chervyakov NI (2020) Application of the residue number system to reduce hardware costs of the convolutional neural network implementation, Mathematics and Computers in Simulation. 232–243. https://doi.org/10.1016/j.matcom.2020.04.031
Hochreiter S, Schmidhuber J. (1997) Long short-term memory. Neural Comput. 1735–1780. 10.1162 /neco.1997.9.8.1735
Gers F.: Understanding LSTM Networks. https://colah.github.io/posts/2015-08-Understanding-LSTMs (2015). Accessed January 2020.
Sainath T, Vinyals O, Senior A, Sak H (2015) Convolutional, Long short-term memory, fully connected deep neural networks, Computer Science 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/ICASSP.2015.7178838