{"title":"Automated Detection of Alzheimer Disease Using Region Growing technique and Artificial Neural Network","authors":"B. Al-Naami, N. Gharaibeh, A. AlRazzaq Kheshman","volume":77,"journal":"International Journal of Biomedical and Biological Engineering","pagesStart":204,"pagesEnd":209,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/11271","abstract":"Alzheimer is known as the loss of mental functions\r\nsuch as thinking, memory, and reasoning that is severe enough to\r\ninterfere with a person's daily functioning. The appearance of\r\nAlzheimer Disease symptoms (AD) are resulted based on which part\r\nof the brain has a variety of infection or damage. In this case, the\r\nMRI is the best biomedical instrumentation can be ever used to\r\ndiscover the AD existence. Therefore, this paper proposed a fusion\r\nmethod to distinguish between the normal and (AD) MRIs. In this\r\ncombined method around 27 MRIs collected from Jordanian\r\nHospitals are analyzed based on the use of Low pass -morphological\r\nfilters to get the extracted statistical outputs through intensity\r\nhistogram to be employed by the descriptive box plot. Also, the\r\nartificial neural network (ANN) is applied to test the performance of\r\nthis approach. Finally, the obtained result of t-test with confidence\r\naccuracy (95%) has compared with classification accuracy of ANN\r\n(100 %). The robust of the developed method can be considered\r\neffectively to diagnose and determine the type of AD image.","references":"[1] Kumar V, Cotran R, Robbins S, eds. Robbins Basic Pathology. 7th ed.\r\nPhiladelphia, PA: Saunders; 2003:252-257\".\r\n[2] Ortiz A, Gorriz J. M., Ramirez J., and Salas-Gonzalez D, Unsupervised\r\nNeural Techniques Applied to MR Brain Image Segmentation, Journal\r\nof Advances in Artificial Neural Systems, in press,\r\ndoi:10.1155\/2012\/457590.\r\n[3] Kennedy D. N., Filipek P. A., and Caviness V. S., \"Anatomic\r\nsegmentation and volumetric calculations in nuclear magnetic resonance\r\nimaging,\" IEEE Transactions on Medical Imaging, vol. 8, no. 1, pp. 1-7,\r\n1989.\r\n[4] Khan A., Tahir S. F., Majid A., and Choi T. S., \"Machine learning based\r\nadaptive watermark decoding in view of anticipated attack,\" Pattern\r\nRecognition, vol. 41, no. 8, pp. 2594-2610, 2008.\r\n[5] Yang Z. and Laaksonen J., \"Interactive retrieval in facial image\r\ndatabase using self-organizing maps,\" in Proceedings of the MVA,\r\n2005.\r\n[6] Garc'\u2500\u2592a-Sebasti'an M., Fern'andez E., Gra\u2566\u00a3na M., and Torrealdea F. J.,\r\n\"A parametric gradient descent MRI intensity inhomogeneity correction\r\nalgorithm,\" Pattern Recognition Letters, vol. 28, no. 13, pp. 1657-1666,\r\n2007.\r\n[7] Fern'andez E., Gra\u2566\u00a3na M., and Cabello J. R., \"Gradient based evolution\r\nstrategy for parametric illumination correction,\" Electronics Letters, vol.\r\n40, no. 9, pp. 531-532, 2004.\r\n[8] Garc'\u2500\u2592a-Sebasti'an M., Isabel Gonz'alez A., and Gra\u2566\u00a3na M., \"An\r\nadaptive field rule for non-parametric MRI intensity inhomogeneity\r\nestimation algorithm,\" Neurocomputing, vol. 72, no.16-18, pp. 3556-\r\n3569, 2009.\r\n[9] Kapur T., Grimson L., Wells W.M., and Kikinis R., \"Segmentation of\r\nbrain tissue from magnetic resonance images,\" Medical Image Analysis,\r\nvol. 1, no. 2, pp. 109-127, 1996.\r\n[10] Tsai Y. F., Chiang I. J., Lee Y. C., Liao C. C., and Wang K. L.,\r\n\"Automatic MRI meningioma segmentation using estimation\r\nmaximization,\" in Proceedings of the 27th Annual International\r\nConference of the Engineering in Medicine and Biology Society (IEEEEMBS\r\n-05), pp. 3074-3077, September 2005.\r\n[11] Xie J. and Tsui H. T., \"Image segmentation based on maximumlikelihood\r\nestimation and optimum entropydistribution (MLE-OED),\"\r\nPattern Recognition Letters, vol. 25, no. 10, pp. 1133-1141, 2004.\r\n[12] Tian D. and Fan L., \"A brain MR images segmentation method based on\r\nSOM neural network,\" in Proceedings of the 1st International\r\nConference on Bioinformatics and Biomedical Engineering (ICBBE\r\n-07), pp. 686-689, July 2007.\r\n[13] G\u252c\u00bfuler I., Demirhan A., and R.Karakis\u252c\u00a9, \"Interpretation of MR images\r\nusing self-organizing maps and knowledge-based expert systems,\"\r\nDigital Signal Processing, vol. 19, no. 4, pp. 668-677, 2009.\r\n[14] Sahoo P. K., Soltani S., and Wong A. K. C., \"A survey of thresholding\r\ntechniques,\" Computer Vision, Graphics and Image Processing, vol. 41,\r\nno. 2, pp. 233-260, 1988.\r\n[15] Sun W., \"Segmentation method of MRI using fuzzy Gaussian basis\r\nneural network,\" Neural Information Processing, vol. 8, no. 2, pp. 19-\r\n24, 2005.\r\n[16] M.M.Patil, A.R.Yardi, Classification of 3D Magnetic Resonance Images\r\nof Brain using Discrete Wavelet Transform,\" International Journal of\r\nComputer Applications, Vol. 31- no.7, 2011.\r\n[17] Ahmed, M.M.; Bin Mohamad, D.; Khalil, M.S., \"A Hybrid Approach\r\nfor Segmenting and Validating T1-Weighted Normal Brain MR Images\r\nby Employing ACM and ANN,\" Soft Computing and Pattern\r\nRecognition, 2009. SOCPAR '09. International Conference of , vol., no.,\r\npp.239,244, 4-7 Dec. 2009 doi: 10.1109\/SoCPaR.2009.56.\r\n[18] El Fakhri, G.; Maksud, P.; Moore, S.C.; Zimmerman, R.E.; Kijewski,\r\nM.F., \"Absolute quantitation in simultaneous 99mTc\/123I brain SPECT\r\nusing ANN: design optimization and validation,\" Nuclear Science\r\nSymposium Conference Record, 2001 IEEE , vol.3, no., pp.1429,1431\r\nvol.3, 4-10 Nov. 2001\r\n[19] Zheng, X.M.; Zubal, I.G.; Seibyl, J. P.; King, M.A., \"Correction for\r\nscatter and cross-talk contaminations in dual radionuclide 99mTc and\r\n123I images using artificial neural network,\" Nuclear Science\r\nSymposium Conference Record, 2003 IEEE , vol.3, no., pp.1868,1871\r\nVol.3, 19-25 Oct. 2003 doi: 10.1109\/NSSMIC.2003.1352243\r\n[20] Torabi, M.; Ardekani, R.D.; Fatemizadeh, E., \"Discrimination between\r\nalzheimer's disease and control group in MR-images based on texture\r\nanalysis using artificial neural network,\" Biomedical and Pharmaceutical\r\nEngineering, 2006. ICBPE 2006. International Conference on , vol., no.,\r\npp.79,83, 11-14 Dec. 2006.\r\n[21] Torabi, M.; Moradzadeh, H.; Vaziri, R.; Razavian, S.; Ardekani, R.D.;\r\nRahmandoust, M.; Taalimi, A.; Fatemizadeh, E., \"Development of\r\nAlzheimer's Disease Recognition using Semiautomatic Analysis of\r\nStatistical Parameters based on Frequency Characteristics of Medical\r\nImages,\" Signal Processing and Communications, 2007. ICSPC 2007.\r\nIEEE International Conference on , vol., no., pp.868,871, 24-27 Nov.\r\n2007.\r\n[22] Chengzhong Huang; Bin Yan; Hua Jiang; Dahui Wang, \"Combining\r\nVoxel-based Morphometry with Artifical Neural Network Theory in the\r\nApplication Research of Diagnosing Alzheimer's Disease,\" BioMedical\r\nEngineering and Informatics, 2008. BMEI 2008. International\r\nConference on , vol.1, no., pp.250,254, 27-30 May 2008 doi:\r\n10.1109\/BMEI.2008.245.\r\n[23] El-Sayed Ahmed, El-Dahshan,Tamer Hosny, Abdel-Badeeh M. Salem,\r\n\"Hybrid intelligent techniques for MRI brain images classification\",\r\nDigital Signal Processing 20, 433-441, 2010.\r\ndoi:10.1016\/j.dsp.2009.07.002.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 77, 2013"}