ارائه یک روش تشخیص بیماری آلزایمر با استفاده از الگوریتم یادگیری عاطفی مغز و ویژگی موجک

محورهای موضوعی : انرژی های تجدیدپذیر

سیده بهناز امامی ¹ (دانشکده مهندسی کامپیوتر- واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران)
نسیم نورافزا ² (مرکز تحقیقات کلان داده- واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران)
شروان فکری ارشاد ³ (دانشکده مهندسی کامپیوتر- واحد نجف‌آباد، دانشگاه آزاد اسلامی، نجف‌آباد، ایران)

تاریخ دریافت : 1399/10/20 تاریخ پذیرش : 1400/02/15 تاریخ انتشار : 1400/10/01

کلید واژه: تبدیل موجک, آلزایمر, آنالیز مؤلفه‌های اصلی, الگوریتم یادگیری عاطفی مغز, آستانه‌گیر,

چکیده مقاله :

آلزایمر ازجمله بیماری‌های شایع قرن ۲۱ است و به سبب آن سلول‌های مغزی بیمار به‌تدریج از بین رفته و بیمار فوت می‌کند. در اکثر مواقع هنگامی این بیماری تشخیص داده می‌شود که علائم آن بروز پیداکرده و کار چندانی برای بیمار نمی‌توان انجام داد. لذا استفاده از الگوریتم‌های یادگیری برای تشخیص بیماری بسیار مفید است. به همین دلیل تاکنون الگوریتم‌های متفاوتی ازجمله نزدیک‌ترین همسایه، آنالیز تشخیص خطی و ماشین بردار پشتیبان برای تشخیص این بیماری استفاده ‌شده است. این روش‌ها دارای نقاط ضعفی ازجمله صحت پایین، پیچیدگی محاسباتی بالا و یا زمان اجرای زیادی هستند. بنابراین در این تحقیق، روشی مبتنی بر یادگیری عاطفی مغز و ویژگی موجک استفاده ‌شده است. ابتدا ماده سفید و خاکستری مغز توسط روش آستانه گیری تفکیک شدند، در مرحله دوم ویژگی‌های بافت تصاویر توسط الگوریتم تبدیل موجک استخراج گردید، مرحله سوم کاهش بعد روی ویژگی‌های استخراج ‌شده توسط آنالیز مؤلفه‌های اصلی انجام ‌گرفته و درنهایت با استفاده از دو الگوریتم یادگیری عاطفی مغز و الگوریتم یادگیری عاطفی مغز مبتنی بر تشخیص الگو طبقه‌بندی صورت گرفته است. نتایج نشان دادند که زمان اجرای الگوریتم یادگیری عاطفی مغز 22/0 ثانیه و نیز الگوریتم یادگیری عاطفی مغز با صحت 95 درصد و الگوریتم یادگیری عاطفی مغز مبتنی بر تشخیص الگو با صحت 97 درصد بهتر از ماشین بردار پشتیبان با صحت 83 درصد عمل کرده‌اند.

چکیده انگلیسی:

Alzheimer’s disease is one of the most common diseases in the 21st century. Alzheimer's patients lose their brain cells gradually and eventually die. It is often diagnosed when the symptoms appear and little work can be done for the patient. Using of learning algorithms is useful for diagnosing of Alzheimer. Previous studies used Support Vector Machine, K-Nearest Neighbor, and Linear Discriminant Analysis in order to diagnose the disease. These methods have some problems such as low accuracy, high computation complexity or high execute time. Therefore in this research, a method based on brain emotional learning and wavelet feature is used. First, the white and gray matters of the brain were separated by a threshold selection method. Second, the texture properties of the images were extracted by wavelet transform algorithm. Third, the dimensional reduction is done on the properties extracted by principal component analysis. Finally, the features were classified using Brain Emotional Learning Algorithm and Brain Emotional Learning Based Pattern Recognizer. Results showed that run time of brain emotional learning algorithm is 0.22 second and Brain Emotional Learning algorithm with 95% accuracy and Brain Emotional Learning Based Pattern Recognizer with 97% accuracy are better than Support Vector Machine with 83% accuracy.

منابع و مأخذ:

[1] E. Pellegrini, L. Ballerini, M.D.C.V. Hernandez, F.M. Chappell, V. González-Castro, D. Anblagan, S. Da­ns­o, S. Muñoz-Maniega, D. Job, C. Pernet, G. Mair, T.J. MacGillivray, E. Trucco, J.M. Wardlaw, "Machine learn­in­g of neuroimaging for assisted diagnosis of cognitive impairment and dementia: A systematic review", Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring, vol. 10, pp. 519-535, 2018 (doi: 10.1016/j.dadm.2018.07.004).

 [2] O.B.  Ahmed, J.  Benois-Pineau, M.  Allard, C.B.  Amar, G.  Catheline, "Classification of Alzheimer’s disease subjects from MRI using hippocampal visual features", Multimedia Tools and Applications, vol. 74, no. 4, pp. 1249-1266, 2015 (doi: 10.1007/s11042-014-2123-y).

 [3] I. Beheshti, H. Demirel, "Feature-ranking-based Alzheimer’s disease classification from structural MRI", Magnetic Resonance Imaging, vol. 34, no. 3, pp. 252-263, April 2016 (doi: 10.1016/j.mri.2015.11.009).

[4] M. Plocharski, L.R. Stergaard, "Extraction of sulcal medial surface and classification of Alzheimer's disease using sulcal features", Computer Methods and Programs in Biomedicine, vol. 133, no. C, pp. 35-44, Sept. 2016 (doi: 10.1016/j.cmpb.2016.05.009).

[5] H. Matsuda, "MRI morphometry in Alzheimer’s disease", Ageing Research Reviews, vol. 30, pp. 17-24, Sept. 2016 (doi: 10.1016/j.arr.2016.01.003).

[6] A. Gholipour, C. Lucas, D. Shahmirzadi, "Predicting geomagnetic activity index by brain emotional learning", WSEAS Transactions on Systems, vol. 3, pp. 296-299, 2004.

[7] S.H. Wang, Y.D. Zhang, Z. Dong, P. Phillips, "Multi-scale and multi-resolution features for structural magnetic resonance imaging", Pathological Brain Detection. Brain Informatics and Health. Springer, Singapore, pp. 71-84, 2018 (doi: 10.1007/978-981-10-4026-9_5).

[8] C.R. Gonzalez, E.R. Woods, "Digital Image Processing", 3rd Edition, Prentice Hall, 2007.

[9] M. Seif El-Nasr, M. Skubic, "A fuzzy emotional agent for decision-making in a mobile robot", Proceeding of the IEEE/FUZZY, vol. 1, pp. 135-140, Anchorage, AK, USA, May 1998 (doi:10.1109/fuzzy.1998.687472).

[10] C. Chung, C.M. Lin, "Brain emotional learning control system design for nonlinear systems", International Journal of Innovative Research in Advanced Engineering, vol. 1, no. 2, Nov. 2014.

[11] M. Parsapoor, U. Bilstrup, B. Svensson "A brain emotional learning-based prediction model for the prediction of geomagnetic Storms", Proceeding of the IEEE/CSIS, pp. 35–42, Warsaw, Poland, Sept. 2014 (doi: 10.1543­9/20­14F231).

[12] Y. Sharafi, S. Setayeshi, A.  Falahiazar, "An improved model of brain emotional learning algorithm based on interval knowledge", Journal of Mathematics and Computer Science, vol. 14, no. 1, pp. 42–53, 2015 (doi: 10­.­22­436/jmcs.014.01.05).

[13] S. Motamed, S. Setayeshi, A. Rabiee, "Speech emotion recognition based on a modified brain emotional learning model", Biologically Inspired Cognitive Architectures, vol. 19, pp. 32–38, Jan. 2017 (doi: 10.1016­/j.bi­ca.2016.12.002).

[14] H. Waheb, M. Rahmati, "Comparison between group of patients with gray matter density voxel in MRI images of Healthy individuals and Alzheimer's patients", Proceeding of the MVIPC, Mashhad, Iran, 2007 (doi: ICMVIP04_072) (in Persian).

 [15] G. Fung, J. Stoeckel, "SVM feature selection for classification of SPECT images of Alzheimer's disease using spatial information", Knowledge and Information Systems, vol. 11, no. 2, pp. 243-258, Sept. 2007 (doi: 10.1007/s10115-006-0043-5).

[16] J. Dukart, K. Mueller, H. Barthel, A. Villringer, O. Sabri, M. L. Schroeter, "Meta-analysis based SVM classification enables accurate detection of Alzheimer's disease across different clinical centers using FDG-PET and MRI", Psychiatry Research: Neuroimaging, vol. 212, no. 3, pp. 230-236, June 2013 (doi: 10.1016/j.­p­scy­chresns.2012.04.007).

[17] X. Liu, D. Tosun, M.W. Weiner, N. Schuff, "Locally linear embedding (LLE) for MRI based Alzheimer's disease classification", NeuroImage, vol. 83, pp. 148-157, June 2013 (doi: 10.1016/j.neuro­image.­2013­.0­6.0­3­3).

[18] S. Liu, S. Liu, W. Cai, S. Pujol, R. Kikinis, D. Feng, "Early diagnosis of Alzheimer's disease with deep learning", Proceeding of the IEEE/ISBI, pp. 1015-1018, Beijing, China, May 2014 (doi: 10.1109/isbi.­201­4.68­68045).

[19] I. Beheshti, H. Demirel, "Probability distribution function-based classification of structural MRI for the detection of Alzheimer’s disease", Computers in Biology and Medicine, vol. 64, pp. 208-216, Sept. 2015 (doi: 10.1016/j.compbiomed.2015.07.006).

[20] I. Beheshti, H. Demirel, "Feature-ranking-based Alzheimer’s disease classification from structural MRI", Magnetic Resonance Imaging, vol. 34, no. 3, pp. 252-263, April 2016 (doi: 10.1016/j.mri.2015.11.009).

 [21] I. Beheshti, H. Demirel, F. Farokhian, C. Yang, H. Matsuda, "Structural MRI-based detection of Alzheimer's disease using feature ranking and classification error", Computer Methods and Programs in Biomedicine, vol. 137, pp. 177-193, Dec. 2016 (doi: 10.1016/j.cmpb.2016.09.019).

[22] L. Sørensen, C. Igel, A. Pai, I. Balas, C. Anker, M. Lillholm, M. Nielsen, "Differential diagnosis of mild cognitive impairment and Alzheimer's disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry", NeuroImage: Clinical, vol. 13, pp. 470-482, 2017 (doi: 10.1016/j.nic­l.201­6.11.025).

[23] F. Zhang, S. Tian, S. Chen, Y. Ma, X. Li, G. Guo, "Voxel-based morphometry: Improving the diagnosis of Alzheimer’s disease based on an extreme learning machine method from the ADNI cohort", Neuroscience, vol. 414, pp. 273-279, Aug. 2019 (doi: 10.1016/j.neuroscience.2019.05.014).

[24] I. Beheshti, H. Demirel, H. Matsuda, "Classification of Alzheimer's disease and prediction of mild cognitive impairment-to-Alzheimer's conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm", Computers in Biology and Medicine, vol. 83, pp. 109-119, April 2017 (doi:10.1016/j.c­omp­b­­iom­ed.2017.02.011).

[25] M.  Eman, A.  Seddik, H. Mohamed, "Automatic detection and classification of Alzheimer's disease from MRI using TANNN", International Journal of Computer Applications, vol. 148, pp. 30-34, 2016 (doi: 10.512­0/I­J­CA­2016911320).

[26] A.R. Gad, N.M.H. Hassan, R.A.A. Seoud, T.M. Nassef, "Automatic machine learning classification of Alzheimer's disease based on selected slices from 3d magnetic resonance imagining", International Journal of Biomedical Science and Engineering, vol. 4, no. 6, pp. 50-54, Feb. 2017 (doi: 10.11648/j.ijbse.20160406.110).

 [27] A. Mohammed Taqi, F. Al-Azzo, M. Milanova, "Classification of Alzheimer disease based on normalized Hu moment Invariants and multiclassifier", International Journal of Advanced Computer Science and Applications, vol. 8, no. 11, 2017 (doi: 10.14569/IJACSA.2017.0811020).

[28] M.  Maleki,   N.  Nourafza, S.  Setayeshi, "A novel approach for designing a cognitive sugarscape cellular society using an extended moren network", Intelligent Automation and Soft Computing, vol. 22, no. 2, pp. 193-201, Nov. 2016 (doi: 10.1080/10798587.2015.1090720).

[29] M.  Parsapoor, "An introduction to brain emotional learning inspired models (BELiMs) with an example of BELiMs’ applications", Artificial Intelligence Review, vol. 52, no. 1, pp. 409-439, June 2019 (doi: 10.1­007/­s1­0462-018-9638-y).

[30] C. Balkenius, J. Moren, "Emotional learning: A computational model of amygdala", Cybernetics and Systems, vol. 32, no. 6, pp. 611-636, 2001 (doi: 10.1080/01969720118947).

[31] T. Babaie, R. Karimizandi, C. Lucas, "Learning based brain emotional intelligence as a new aspect for development of an alarm system", Soft Computing, vol. 12, no. 9, pp. 857–873, July 2008 (doi: 10.1007/s0­05­0­0-007-0­258-8).

[32] J. Abdi, B. Moshiri, B. Abdulhai, A.K. Sedigh, "Forecasting of short-term traffic-flow based on improved neurofuzzy models via emotional temporal difference learning algorithm", Engineering Applications of Artificial Intelligence, vol. 25, no. 5, pp. 1022-1042, Aug. 2012 (doi: 10.1016/j.engappai.2011.09.011).

[33] C. Lucas, D. Shahmirzadi, N. Sheikholeslami, "Ntroducing Belbic: Brain emotional learning based intelligent controller", Intelligent Automation and Soft Computing, vol. 10, no. 1, pp. 11–21, 2004 (doi: 10.1080­/1079­8587.2004.10642862).

[34] E.  Lotfi, M.R.  Akbarzadeh, "Practical emotional neural networks", Neural Networks, vol. 59, pp. 61-72, Nov.  2014 (doi: 10.1016/j.neunet.2014.06.012).