ارائه یک سیستم خودکار برای تشخیص افراد سالم و افراد دارای بیماری رتینوپاتی دیابتی
محورهای موضوعی : انرژی های تجدیدپذیر
مینا غیور
1
(دانشکده مهندسی برق- واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران)
حسین پورقاسم
2
(مرکز تحقیقات پردازش تصویر و بینایی ماشین، واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران)
کلید واژه: ماشین بردار پشتیبان, رتینوپاتی دیابتی, تجزیه و تحلیل مؤلفه‌های اصلی, ویژگی‌های شکل و رنگ تصاویر,
چکیده مقاله :
دیابت یکی از شایع ترین بیماری ها در جهان است که آثار مخربی بر روی قسمت های مختلف بدن برجای می گذارد. از ابتدایی ترین قسمت هایی که دچار عارضه می شود چشم است. تحلیل صدمات وارد شده بر روی شبکیه چشم از بهترین راه های تشخیص دیابت است. به همین علت ابتدا یک روش پرکاربرد و موثر برای حذف نویز تصاویر با ترکیب فیلتر وینر و تبدیل موجک گسسته اعمال می شود. در مرحله بعد از الگوریتم خوشه بندی k-means برای حذف قسمت های نامطلوب تصویر شامل نواحی خیلی روشن و خیلی تیره تصویر، استفاده می شود. سپس ویژگی های رنگ و شکل تصاویر استخراج می شود. برای استخراج ویژگی های رنگ تصویر، تصاویر را به فضای lab که برای چشم انسان بهتر قابل درک است برده می شود و برای استخراج ویژگی های شکل ابتدا تصاویر را به تصاویر خاکستری تبدیل کرده و سپس اقدام به استخراج ویژگی های شکل می گردد. پس از استخراج ویژگی ها به کمک الگوریتم تجزیه و تحلیل مؤلفه های اصلی تعداد ویژگی ها را کاهش داده و بهترین و مؤثرترین ویژگی ها انتخاب می شود. در پایان برای طبقه بندی ویژگی ها و تصاویر به دو گروه سالم و بیمار، از طبقه بند ماشین بردار پشتیبان با کرنل های متفاوت استفاده می شود. این الگوریتم صحت بالای 90% برای تصاویر آزمایشی حاصل می کند.
Diabetes is one of the most common diseases in the world, adversely affects different body organs. One of the most common causes of eye problems is diabetes. Analyzing retinal damage is one of the best ways to diagnose diabetes so one of the best ways to diagnose diabetes is to look at the damage to the retina. Hence, first, a highly applicable and effective method, which is a combination of the Wiener filter and the discrete wavelet transform (DWT), is used for the removal of noise from images. Afterward, the k-means clustering algorithm is used to remove the bad image sections including very light and very dark areas of the image. Next, the image color and shape features are extracted. We transfer the images to the lab space, which fits the eye more, to extract the image color features. To extract the image shape features, first the images are converted into grey images and then the shape features are extracted. After extracting the features, the number of features is reduced using the Principal Component Analysis (PCA) algorithm. Besides, the best and most effective features are also selected. Finally, the support vector machine classifier with different kernel is used to classify the features and images into two categories, namely the healthy participants and patients. The accuracy resulting from this algorithm using the test images is over 90%.
[1] S. Ali, "The survey of method base on training and electronic learning for early detection of retinal hemorrhages in diabetic retinopathy", Interdisciplinary Journal of Virtual Learning in Medical Sciences, vol. 5, no. 1, pp. 77-87, April 2014.
[2] A. W. Reza, C. Eswaran, "A decision support system for automatic screening of non-proliferative diabetic retinopathy", Journal of Medical Systems, vol. 35, no 1, pp.17-24, Feb. 2011 (doi: 10.1007/s10916-009-9337-y).
[3] M. Sona, F. Amin, "Feature extraction and intelligent detection of diabetic retinopathy in retinal images", Proceeding of the NCESD, May 2016 (in Persian)
[4] J. Amin, M. Sharif, M. Yasmin, H. Ali, S.L. Fernandes, "A method for the detection and classification of diabetic retinopathy using structural predictors of bright lesions", Journal of Computational Science, vol. 19, pp.153-64, March 2017 (doi: 10.1016/j.jocs.2017.01.002).
[5] X. Zhang, G. Thibault, E. Decencière, B. Marcotegui, B. Laÿ, R. Danno, G. Cazuguel, G. Quellec, M. Lamard, P. Massin, A. Chabouis, Z. Victor, A. Erginay, "Exudate detection in color retinal images for mass screening of diabetic retinopathy”, Medical Image Analysis, vol. 18, no. 7, pp. 1026-1043, Oct. 2014 (doi: 10.1016/j.media.2014.05.004).
[6] N. G. Ranamuka, R. G. N. Meegama, "Detection of hard exudates from diabetic retinopathy images using fuzzy logic”, IET Image Processing, vol. 7, no. 2, pp. 121-130, March 2013 (doi: 10.1049/iet-ipr.2012.0134).
[7] I. Lazar, A. Hajdu, "Retinal microaneurysm detection through local rotating cross-section profile analysis", IEEE Trans. on Medical Imaging, vol. 32, no. 2, pp. 400-407, Feb. 2013 (doi: 10.1109/TMI.2012.2228665).
[8] L. Tang, M. Niemeijer, J. M. Reinhardt, M. K. Garvin, M. D. Abramoff, "Splat feature classification with application to retinal hemorrhage detection in fundus images", IEEE Trans. on Medical Imaging, vol. 32, no. 2, pp. 364-375, Feb. 2013 (doi: 10.1109/TMI.2012.2227119).
[9] E. Imani, H.-R. Pourreza, T. Banaee, "Fully automated diabetic retinopathy screening using morphological component analysis", Computerized Medical Imaging and Graphics, vol. 43, pp. 78-88, July 2015.
[10] L. Seoud, T. Hurtut, J. Chelbi, F. Cheriet, J. P. Langlois, "Red lesion detection using dynamic shape features for diabetic retinopathy screening", IEEE Trans. on medical imaging, vol. 35, no. 4, pp. 1116-1126, Dec. 2015 (doi: 10.1109/TMI.2015.2509785).
[11] M. E. Gegundez-Arias, D. Marin, B. Ponte, F. Alvarez, J. Garrido, C. Ortega, M. J.Vasallo, J. M. Bravo, "A tool for automated diabetic retinopathy pre-screening based on retinal image computer analysis", Computers in Biology and Medicine, vol. 88, pp. 100-109, Sept. 2017 (doi: 10.1016/j.compbiomed.2017.07.007).
[12] M. K. Behera, S. Chakravarty, "Diabetic retinopathy image classification using support vector machine”, Proceeding of the IEEE/ICCSEA, pp. 1-4, Gunupur, India, March 2020 (doi: 10.1109/ICCSEA49143.2020.9132875).
[13] High Resolution Fundus Retinal Image Database: https://www5.cs.fau.de/research/data/fundus-images/.
[14] H.-H. Tsai, Y.-J. Jhuang, Y.-S. Lai, "An SVD-based image watermarking in wavelet domain using SVR and PSO", Applied Soft Computing, vol. 12, no. 8, pp. 2442-2453, Aug. 2012 (doi: 10.1016/j.asoc.2012.02.021).
[15] N. Ehsan, S. Sara, "Reduction of image spectral noise using diffusion equations and pixone image concept", Amirkabir University of Technology (Tehran Polytechnic), March 2008 (in Persian).
[16] A. Somayeh, G. Mohammad, D. Vali, "A new hybrid fuzzy intelligent filter for medical image noise reduction", Computational Intelligence in Electrical Engineering, vol 5, no 3, pp.47-54, 2015 (in Persian).
[17] E. Mehdi, "Data mining concepts and techniques", Knowledge Need, 2014 [online].
[18] V. S. Rathore, M. S. Kumar, A. Verma, "Colour based image segmentation using L* a* b* colour space based on genetic algorithm", International Journal of Emerging Technology and Advanced Engineering, vol. 2, no. 6, pp. 156-162, June 2012.
[19] F. Garcia-Lamont, J. Cervantes, A. López, L. Rodriguez, "Segmentation of images by color features: A survey", Neurocomputing, vol. 292, pp. 1-27, May 2018 (doi: 10.1016/j.neucom.2018.01.091).
[20] M. Yang, K. Kpalma, J. Ronsin, "A survey of shape feature extraction techniques", ed: InTech, Nov 2008.
[21] C. Chang, W. Liu, H. Zhang, "Image retrieval based on region shape similarity", Storage and Etrieval for Media Databases 2001, 2001, vol. 4315: International Society for Optics and Hotonics, pp. 31-38.
_||_[1] S. Ali, "The survey of method base on training and electronic learning for early detection of retinal hemorrhages in diabetic retinopathy", Interdisciplinary Journal of Virtual Learning in Medical Sciences, vol. 5, no. 1, pp. 77-87, April 2014.
[2] A. W. Reza, C. Eswaran, "A decision support system for automatic screening of non-proliferative diabetic retinopathy", Journal of Medical Systems, vol. 35, no 1, pp.17-24, Feb. 2011 (doi: 10.1007/s10916-009-9337-y).
[3] M. Sona, F. Amin, "Feature extraction and intelligent detection of diabetic retinopathy in retinal images", Proceeding of the NCESD, May 2016 (in Persian)
[4] J. Amin, M. Sharif, M. Yasmin, H. Ali, S.L. Fernandes, "A method for the detection and classification of diabetic retinopathy using structural predictors of bright lesions", Journal of Computational Science, vol. 19, pp.153-64, March 2017 (doi: 10.1016/j.jocs.2017.01.002).
[5] X. Zhang, G. Thibault, E. Decencière, B. Marcotegui, B. Laÿ, R. Danno, G. Cazuguel, G. Quellec, M. Lamard, P. Massin, A. Chabouis, Z. Victor, A. Erginay, "Exudate detection in color retinal images for mass screening of diabetic retinopathy”, Medical Image Analysis, vol. 18, no. 7, pp. 1026-1043, Oct. 2014 (doi: 10.1016/j.media.2014.05.004).
[6] N. G. Ranamuka, R. G. N. Meegama, "Detection of hard exudates from diabetic retinopathy images using fuzzy logic”, IET Image Processing, vol. 7, no. 2, pp. 121-130, March 2013 (doi: 10.1049/iet-ipr.2012.0134).
[7] I. Lazar, A. Hajdu, "Retinal microaneurysm detection through local rotating cross-section profile analysis", IEEE Trans. on Medical Imaging, vol. 32, no. 2, pp. 400-407, Feb. 2013 (doi: 10.1109/TMI.2012.2228665).
[8] L. Tang, M. Niemeijer, J. M. Reinhardt, M. K. Garvin, M. D. Abramoff, "Splat feature classification with application to retinal hemorrhage detection in fundus images", IEEE Trans. on Medical Imaging, vol. 32, no. 2, pp. 364-375, Feb. 2013 (doi: 10.1109/TMI.2012.2227119).
[9] E. Imani, H.-R. Pourreza, T. Banaee, "Fully automated diabetic retinopathy screening using morphological component analysis", Computerized Medical Imaging and Graphics, vol. 43, pp. 78-88, July 2015.
[10] L. Seoud, T. Hurtut, J. Chelbi, F. Cheriet, J. P. Langlois, "Red lesion detection using dynamic shape features for diabetic retinopathy screening", IEEE Trans. on medical imaging, vol. 35, no. 4, pp. 1116-1126, Dec. 2015 (doi: 10.1109/TMI.2015.2509785).
[11] M. E. Gegundez-Arias, D. Marin, B. Ponte, F. Alvarez, J. Garrido, C. Ortega, M. J.Vasallo, J. M. Bravo, "A tool for automated diabetic retinopathy pre-screening based on retinal image computer analysis", Computers in Biology and Medicine, vol. 88, pp. 100-109, Sept. 2017 (doi: 10.1016/j.compbiomed.2017.07.007).
[12] M. K. Behera, S. Chakravarty, "Diabetic retinopathy image classification using support vector machine”, Proceeding of the IEEE/ICCSEA, pp. 1-4, Gunupur, India, March 2020 (doi: 10.1109/ICCSEA49143.2020.9132875).
[13] High Resolution Fundus Retinal Image Database: https://www5.cs.fau.de/research/data/fundus-images/.
[14] H.-H. Tsai, Y.-J. Jhuang, Y.-S. Lai, "An SVD-based image watermarking in wavelet domain using SVR and PSO", Applied Soft Computing, vol. 12, no. 8, pp. 2442-2453, Aug. 2012 (doi: 10.1016/j.asoc.2012.02.021).
[15] N. Ehsan, S. Sara, "Reduction of image spectral noise using diffusion equations and pixone image concept", Amirkabir University of Technology (Tehran Polytechnic), March 2008 (in Persian).
[16] A. Somayeh, G. Mohammad, D. Vali, "A new hybrid fuzzy intelligent filter for medical image noise reduction", Computational Intelligence in Electrical Engineering, vol 5, no 3, pp.47-54, 2015 (in Persian).
[17] E. Mehdi, "Data mining concepts and techniques", Knowledge Need, 2014 [online].
[18] V. S. Rathore, M. S. Kumar, A. Verma, "Colour based image segmentation using L* a* b* colour space based on genetic algorithm", International Journal of Emerging Technology and Advanced Engineering, vol. 2, no. 6, pp. 156-162, June 2012.
[19] F. Garcia-Lamont, J. Cervantes, A. López, L. Rodriguez, "Segmentation of images by color features: A survey", Neurocomputing, vol. 292, pp. 1-27, May 2018 (doi: 10.1016/j.neucom.2018.01.091).
[20] M. Yang, K. Kpalma, J. Ronsin, "A survey of shape feature extraction techniques", ed: InTech, Nov 2008.
[21] C. Chang, W. Liu, H. Zhang, "Image retrieval based on region shape similarity", Storage and Etrieval for Media Databases 2001, 2001, vol. 4315: International Society for Optics and Hotonics, pp. 31-38.
