Login Register Cart 0
Generic placeholder image

Current Medical Imaging

Editor-in-Chief

ISSN (Print): 1573-4056
ISSN (Online): 1875-6603

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

High-accuracy Automated Diagnosis of Parkinson's Disease

Author(s): Ilker Ozsahin*, Boran Sekeroglu, Pwadubashiyi Coston Pwavodi and Greta S.P. Mok

Volume 16, Issue 6, 2020

Page: [688 - 694] Pages: 7

DOI: 10.2174/1573405615666190620113607

Price: $65

Abstract

Purpose: Parkinson's disease (PD), which is the second most common neurodegenerative disease following Alzheimer’s disease, can be diagnosed clinically when about 70% of the dopaminergic neurons are lost and symptoms are noticed. Neuroimaging methods such as single photon emission computed tomography have become useful tools in vivo to assess dopamine transporters (DATs) in the striatal region. However, inter- and intra-reader variability of construing the images might result in misdiagnosis. To overcome the challenges posed by classification of the disease, image preparation techniques and a back propagation neural network (BPNN) have been proposed. The aim of this study is to show that the proposed method can be used for the classification of PD with high accuracy.

Methods: In this study, we used basic image preparation techniques and a BPNN on DAT imaging datasets from the Parkinson’s Progression Markers Initiative. 1,334 PD and 212 normal control (NC) subjects were included. In the image preparation phase, adaptive histogram equalization was applied to the cropped images, followed by image binarization. Then, the mass-difference method was applied to separate the regions of interest with similar values. Finally, the binarized images were subtracted from the original images, and the average pixel per node approach was applied to the images to minimize the inputs. In the BPNN phase, 400 input neurons and 2 output neurons were used. The dataset was divided into three sets: training, validation, and test. The BPNN was trained several times in order to obtain the optimum values.

Results: The use of 40 hidden neurons, a learning rate of 0.00079, and a momentum factor of 0.90 produced superior results and were applied in the final BPNN architecture. The tolerance value used was 0.80. Uniquely, we found the sensitivity, specificity, and accuracy for PD vs. NC classification to be 99.7%, 99.2%, 99.6%, respectively. To the best of our knowledge, this is the highest accuracy value achieved in the existing literature. Our method increases computational speed together with improved performance.

Conclusion: We have shown that effective image processing methods and the use of BPNN can successfully be applied to PD datasets to accurately determine any abnormalities in DATs. Using the shallow neural network, this procedure requires less processing time compared to other methods, and its accuracy, sensitivity, and specificity are reliable. However, further studies are needed to establish a prediction method for the preclinical and prodromal stages of the disease.

Keywords: Dopamine transporter, Parkinson's disease, back propagation, neural network, image preparation, SPECT.

Graphical Abstract

[1]
Rewar S. A systematic review on Parkinson Disease (PD). Indian J Biotech Pharm Res 2015; 3(2): 176.
[2]
Ishihara LS, Cheesbrough A, Brayne C, Schrag A. Estimated life expectancy of Parkinson’s patients compared with the UK population. J Neurol Neurosurg Psychiatry 2007; 78(12): 1304-9.
[http://dx.doi.org/10.1136/jnnp.2006.100107] [PMID: 17400591]
[3]
Mehanna R, Moore S, Hou JG, Sarwar AI, Lai EC. Comparing clinical features of young onset, middle onset and late onset Parkinson’s disease. Parkinsonism Relat Disord 2014; 20(5): 530-4.
[http://dx.doi.org/10.1016/j.parkreldis.2014.02.013] [PMID: 24631501]
[4]
Marras C, Beck JC, Bower JH, et al. Prevalence of Parkinson’s disease across North America. NPJ Parkinsons Dis 2018; 4(1): 21.
[http://dx.doi.org/10.1038/s41531-018-0058-0] [PMID: 30003140]
[5]
Martinez-Murcia FJ, Górriz JM, Ramírez J, Moreno-Caballero M, Gómez-Río M. Parametrization of textural patterns in 123I-ioflupane imaging for the automatic detection of Parkinsonism. Med Phys 2014; 41(1) 012502
[http://dx.doi.org/10.1118/1.4845115] [PMID: 24387526]
[6]
Hornykiewicz O. Biochemical aspects of Parkinson’s disease. Neurology 1998; 2: 2-9.
[http://dx.doi.org/10.1212/WNL.51.2_Suppl_2.S2]
[7]
Fearnley JM, Lees AJ. Ageing and Parkinson’s disease: substantia nigra regional selectivity. Brain 1991; 114(Pt 5): 2283-301.
[http://dx.doi.org/10.1093/brain/114.5.2283] [PMID: 1933245]
[8]
Mulder T, Duysens J, Duysens J. Neural control of locomotion: sensory control of the central pattern generator and its relation to treadmill training. Gait Posture 1998; 7(3): 251-63.
[http://dx.doi.org/10.1016/S0966-6362(98)00010-1] [PMID: 10200392]
[9]
Zehr EP. Neural control of rhythmic human movement: the common core hypothesis. Exerc Sport Sci Rev 2005; 33(1): 54-60.
[PMID: 15640722]
[10]
Dietz V. Proprioception and locomotor disorders. Nat Rev Neurosci 2002; 3(10): 781-90.
[http://dx.doi.org/10.1038/nrn939] [PMID: 12360322]
[11]
Camara C, Warwick K, Bruña R, Aziz T, del Pozo F, Maestú F. A fuzzy inference system for closed-loop deep brain stimulation in Parkinson’s disease. J Med Syst 2015; 39(11): 155.
[http://dx.doi.org/10.1007/s10916-015-0328-x] [PMID: 26385550]
[12]
Hawkes CH, Del Tredici K, Braak H. A timeline for Parkinson’s disease. Parkinsonism Relat Disord 2010; 16(2): 79-84.
[http://dx.doi.org/10.1016/j.parkreldis.2009.08.007] [PMID: 19846332]
[13]
Goedert M, Spillantini MG, Del Tredici K, Braak H. 100 years of Lewy pathology. Nat Rev Neurol 2013; 9(1): 13-24.
[http://dx.doi.org/10.1038/nrneurol.2012.242] [PMID: 23183883]
[14]
Tanner CM. Is the cause of Parkinson’s disease environmental or hereditary? Evidence from twin studies. Adv Neurol 2003; 91: 133-42.
[PMID: 12442672]
[15]
Dick FD, De Palma G, Ahmadi A, et al. Environmental risk factors for Parkinson’s disease and parkinsonism: the Geoparkinson study. Occup Environ Med 2007; 64(10): 666-72.
[http://dx.doi.org/10.1136/oem.2006.027003] [PMID: 17332139]
[16]
Parkinson’s Society India 2013.http://www.parkinsonssocietyindia.com/Causes/M_25
[17]
Bhande S, Raut R. Parkinson diagnosis using neural network: a survey. Imaging Int J Innov Res Sci Engineer Technol 2013; 2: 4843-6.
[18]
Mozley PD, Acton PD, Barraclough ED, Plossl K, Gur RC, Mathur A, et al. Effects of age on the cerebral distribution of [Tc-99m]TRODAT-1 in healthy humans. J Nucl Med 1999; 40: 1812-7.
[PMID: 10565775]
[19]
Mozley PD, Schneider JS, Acton PD, et al. Binding of [99mTc]TRODAT-1 to dopamine transporters in patients with Parkinson’s disease and in healthy volunteers. J Nucl Med 2000; 41(4): 584-9.
[PMID: 10768556]
[20]
Chou KL, Hurtig HI, Stern MB, et al. Diagnostic accuracy of [99mTc]TRODAT-1 SPECT imaging in early Parkinson’s disease. Parkinsonism Relat Disord 2004; 10(6): 375-9.
[http://dx.doi.org/10.1016/j.parkreldis.2004.04.002] [PMID: 15261880]
[21]
Swanson RL, Newberg AB, Acton PD, et al. Differences in [99mTc]TRODAT-1 SPECT binding to dopamine transporters in patients with multiple system atrophy and Parkinson’s disease. Eur J Nucl Med Mol Imaging 2005; 32(3): 302-7.
[http://dx.doi.org/10.1007/s00259-004-1667-x] [PMID: 15791439]
[22]
Acton PD, Newberg A, Plössl K, Mozley PD. Comparison of region-of-interest analysis and human observers in the diagnosis of Parkinson’s disease using [99mTc]TRODAT-1 and SPECT. Phys Med Biol 2006; 51(3): 575-85.
[http://dx.doi.org/10.1088/0031-9155/51/3/007] [PMID: 16424582]
[23]
Das R. A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Syst Appl 2010; 37: 1568-72.
[http://dx.doi.org/10.1016/j.eswa.2009.06.040]
[24]
Bhattacharya I, Bhatia M. SVM classification to distinguish Parkinson disease patients. In: Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India; Tamilnadu, India 2010.
[http://dx.doi.org/10.1145/1858378.1858392]
[25]
Astrom F, Koker R. A parallel neural network approach to prediction of Parkinson’s disease. Expert Syst Appl 2011; 38: 12470-4.
[http://dx.doi.org/10.1016/j.eswa.2011.04.028]
[26]
Bianchini M, Scarselli F. On the complexity of shallow and deep neural network classifiers. In: ESANN 2014 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges, Belgium 2014; pp. 371-6.
[27]
Mhaskar H, Liao Q, Poggio T. When is deep better than shallow. Cent Brain Mind Mach 2016; 2016: 1-12.
[28]
Kůrková V, Sanguineti M. Probabilistic lower bounds for approximation by shallow perceptron networks. Neural Netw 2017; 91: 34-41.
[http://dx.doi.org/10.1016/j.neunet.2017.04.003] [PMID: 28482227]
[29]
Chang LT. A method for attenuation correction in radionuclide computed tomography. IEEE Trans Nucl Sci 1978; 25: 638-43.
[http://dx.doi.org/10.1109/TNS.1978.4329385]
[30]
Friston KJ. Statistical parametric mapping Functional neuroimaging. San Diego, CA: Academic Press 1994; pp. 79-93.
[31]
Friston KJ, Holmes AP, Worsley KJ, Poline JP, Frith CD, Frackowiak RSJ. Statistical parametric maps in functional imaging: a general linear approach. Hum Brain Mapp 1994; 2: 189-210.
[http://dx.doi.org/10.1002/hbm.460020402]
[32]
Lavanyadevi R, Machakowsalya M, Nivethitha J, Kumar AN. Brain tumor classification and segmentation in MRI images using PNN. In: International Conference on Electrical, Instrumentation and Communication Engineering (ICEICE). Karur, India 2017; pp. 1-6.
[http://dx.doi.org/10.1109/ICEICE.2017.8191888]
[33]
Abd-Ellah MK, Awad AI, Khalaf AAM, Hamed HFA. Design and implementation of a computer-aided diagnosis system for brain tumor classification. In: 28th International Conference on Microelectronics (ICM). Giza, Egypt 2016; pp. 73-6.
[http://dx.doi.org/10.1109/ICM.2016.7847911]
[34]
Kaba S, Sekeroglu B, Haci H, Kneebone E. Image Based Diameter Measurement and Aneurysm Detection of the Ascending Aorta. In: Arai K, Kapoor S, Bhatia R, Eds. Intelligent Computing SAI 2018 Advances in Intelligent Systems and Computing. Springer, Cham 2018.
[35]
Sekeroglu B, Emirzade E. A computer aided diagnosis system for lung cancer detection using support vector machine. In: Third International Workshop on Pattern Recognition. Jinan, China. 2018.
[http://dx.doi.org/10.1117/12.2502010]
[36]
Sekeroglu B, Khashman A. Methods for document images. In: International Conference on Advances in Image Processing;. New York; NY; USA 2017; pp. 25-7.
[37]
Otsu N. A threshold selection method from gray-level histogram. IEEE Trans Syst Man Cybern 1979; 9: 62-6.
[http://dx.doi.org/10.1109/TSMC.1979.4310076]
[38]
Khashman A, Sekeroglu B. Novel thresholding method for document analysis. In: International Conference on Industrial Technology (ICIT2006). Mumbai, India 2006; pp. 15-7.
[http://dx.doi.org/10.1109/ICIT.2006.372219]
[39]
Khashman A, Sekeroglu B, Dimililer K. Intelligent coin identification system. In: International Symposium on Intelligent Control (ISIC’06). Kunming, China 2006; pp. 4-6.
[40]
Kon N, Chinsatit W, Saitoh T. Pupil center detection for infrared irradiation eye image using CNN. In: Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE). Kanazawa, Japan 2017; pp. 100-5.
[41]
Li Q, Zhang X, Rigat A, Li Y. Parameters optimization of back propagation neural network based on memetic algorithm coupled with genetic algorithm. In: IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th International Conference on Autonomic and Trusted Computing and IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom). Beijing, China. 2016; pp. 1359-64.
[http://dx.doi.org/10.1109/UIC-ATC-ScalCom-CBDCom- IoP.2015.245]
[42]
Kolsch A, Afzal MZ, Ebbecke M, Liwicki M. Real-time document image classification using deep CNN and extreme learning machines. In: IAPR International Conference on Document Analysis and Recognition (ICDAR). Kyoto, Japan. 2017; pp. 1318-23.
[http://dx.doi.org/10.1109/ICDAR.2017.217]
[43]
Zhao B, Lu H, Chen S, Liu J, Wu D. Convolutional neural networks for time series classification. J Syst Eng Electron 2017; 28(1): 162-9.
[http://dx.doi.org/10.21629/JSEE.2017.01.18]
[44]
Illan IA, Gorrz JM, Ramirez J, Segovia F, Jimenez-Hoyuela JM, Ortega Lozano SJ. Automatic assistance to Parkinson’s disease diagnosis in DaTSCAN SPECT imaging. Med Phys 2012; 39(10): 5971-80.
[http://dx.doi.org/10.1118/1.4742055] [PMID: 23039635]
[45]
Choi H, Ha S, Im HJ, Paek SH, Lee DS. Refining diagnosis of Parkinson’s disease with deep learning-based interpretation of dopamine transporter imaging. Neuroimage Clin 2017; 16: 586-94.
[http://dx.doi.org/10.1016/j.nicl.2017.09.010] [PMID: 28971009]
[46]
Oliveira FP, Castelo-Branco M. Computer-aided diagnosis of Parkinson’s disease based on [(123)I]FP-CIT SPECT binding potential images, using the voxels-as-features approach and support vector machines. J Neural Eng 2015; 12(2) 026008
[http://dx.doi.org/10.1088/1741-2560/12/2/026008] [PMID: 25710187]
[47]
Towey DJ, Bain PG, Nijran KS. Automatic classification of 123I-FP-CIT (DaTSCAN) SPECT images. Nucl Med Commun 2011; 32(8): 699-707.
[http://dx.doi.org/10.1097/MNM.0b013e328347cd09] [PMID: 21659911]
[48]
Segovia F, Gorriz JM, Ramirez J, Alvarez I, Jimenez-Hoyuela JM, Ortega SJ. Improved parkinsonism diagnosis using a partial least squares based approach. Med Phys 2012; 39(7): 4395-403.
[http://dx.doi.org/10.1118/1.4730289] [PMID: 22830772]
[49]
Prashanth R, Dutta Roy S, Mandal PK, Ghosh S. Automatic classification and prediction models for early Parkinson’s disease diagnosis from SPECT imaging. Expert Syst Appl 2014; 7: 3333-42.
[http://dx.doi.org/10.1016/j.eswa.2013.11.031]

Rights & Permissions Print Cite
Article Metrics
19
1
© 2024 Bentham Science Publishers | Privacy Policy