ارائه روشی ترکیبی در پردازش تصاویر دیجیتال جهت تشخیص آسیب رگ¬های خونی
محورهای موضوعی : مهندسی برق ( الکترونیک، مخابرات، قدرت، کنترل)
1 - گروه مهندسی برق،واحد فسا،دانشگاه آزاد اسلامی،فسا،ایران
کلید واژه: پردازش تصاویر دیجیتال, استخراج و ناحیه¬بندی رگ¬ها, حذف نویز, آسیب رگ های خونی, پایگاه داده کلید مقدار,
چکیده مقاله :
آسیب رگ های خونی یکی از دلایل شایع نابینایی در جهان است . شناسایی رگها از روی تصاویر شبکیه نقش مهمی در تشخیص بیماریهای چشمی مانند آسیب رگ های خونی ایفا میکنند . استخراج رگهای خونی شبکیه توسط پزشک به صورت دستی انجام میشود که این کار زمانبر و دشوار است و به دلیل وابستگی به فرد با خطا همراه است . شناسایی رگهای کوچک در تصاویر شبکیه به دلیل کنتراست پایین و چرخش دشوار است. در این مقاله روشی جدید و ترکیبی برای استخراج رگهای خونی تصاویر دیجیتالی شبکیه ارائه شده است. مراحل این روش بدین شرح هستند: حذف نوفه در تصاویر شبکیه، استخراج خطوط مرکزی رگ، استفاده از روش گسترش ناحیه و حذف نوفه، اعمال عملیات پردازش محلی بر اساس مشخصات آماری تصویر جهت بهبود کنتراست رگها و پیشزمینه، عملیات تطبیق قالب جهت حذف اثر دیسک نوری، اعمال عملیات مورفولوژی جهت پر کردن فضای بین مرز رگها و در نهایت استخراج رگهای خونی در تصاویر شبکیه . نتایج حاصل از این الگوریتم در مقایسه با دیگر روشها گزینهی بسیارمناسبی برای تشخیص آسیب رگ های خونی توسط پردازش تصاویر دیجیتال میباشد. برای ارزیابی روش پیشنهادی از تصاویر موجود از پایگاه داده کلید مقدار استفاده شده و مقادیر حساسیت، دقت و صحت محاسبه شده است و میانگین این معیارها به ترتیب 92896/0، 98965/0، 91756/0 و 96578/0 گزارش شد. مقادیر این معیارها حاکی از عملکرد رضایت بخش روش پیشنهادی نسبت به سایر روشها میباشد.
Damage to blood vessels is one of the most common causes of blindness in the world. Identification of vessels from retinal images plays an important role in the diagnosis of eye diseases such as damage to blood vessels. The extraction of retinal blood vessels is done manually by the doctor, which is time-consuming and difficult, and due to the dependence on the individual, it is associated with errors. It is difficult to identify small vessels in retinal images due to low contrast and rotation. In this article, a new and combined method for extracting blood vessels from retinal digital images is presented. The steps of this method are as follows: removal of noise in retinal images, extraction of central lines of vessels, use of area expansion and removal of noise, application of local processing operations based on the statistical characteristics of the image to improve the contrast of vessels and background, template matching operation to remove the effect Optical disk, applying morphological operations to fill the space between the borders of the vessels and finally extract blood vessels in retinal images. Compared to other methods, the results of this algorithm are a very suitable option for diagnosing blood vessel damage by digital image processing. To evaluate the proposed method, the available images from the value key database were used and the values of sensitivity, precision and accuracy were calculated and the average of these criteria was reported as 0.92896, 0.98965, 0.91756 and 0.96578 respectively. The values of these criteria indicate the satisfactory performance of the proposed method compared to other methods.
1 Jafari M., “Internet of Things in eye diseases using smart glasses”, International Journal of Engineering Education, 9: 1034-1042, 2017.
2 Mane D., Londhe N., Patil N., Patil O., and Vidhate P., “A Survey on Diabetic Retinopathy Detection Using Deep Learning”, Data Engineering for Smart Systems. Springer, 238: 621-637, 2022. https://doi.org/10.1007/978-981-16-2641-8-59.
3 Ji L., Tian H., Webster K. A., and Li W., “Neurovascular regulation in diabetic retinopathy and emerging therapies”, Cellular and Molecular Life Sciences, 78: 5977-5985, 2021. https://doi.org/10.1007/s00018-021-03893-9.
4 Antonetti D. A., Silva P. S., and Stitt A. W., “Current understanding of the molecular and cellular pathology of diabetic retinopathy.” Nature Reviews Endocrinology, 17(4): 195-206, 2021. https://doi.org/10.1038/s41574-020-00451-4.
5 Li H. and Zheng M., “Analysis of optic disc and macular vascular density in patients with non-proliferative diabetic retinopathy”, American Journal of Translational Research, 13(8): 9160-9167, 2021.
6 Ranjit G., Saha A., and Das S., “A Improved Vessel Extraction Scheme from Retinal Fundus Images”, Multimedia Tools and Applications, 78(18): 25221-25239, 2019. https://doi.org/10.1007/s11042-019-7719-9.
7 Prouski G., Jafari M., and Zarrabi H., “Internet of Things in Eye Diseases, Introducing a New Smart Eyeglasses Designed for Probable Dangerous Pressure Changes in Human Eyes.” International Conference on Computer and Applications, 364-368, 2017. https://doi.org/10.1109/COMAPP.2017.8079762.
8 Crabtree G. S. and Chang J. S., “Management of complications and vision loss from proliferative diabetic retinopathy”, Current diabetec reports, 21(9): 1-8, 2021. https://doi.org/10.1007/s11892-021-01396-2.
9 American Diabetes Association, (online): http://dyabetes.com/Article/7/10noticesdiabetesEyes, visited on 26 February, 2021.
10 Soomro T. A., Afifi A. J., Gao J., Hellwich O., Zheng L., and Paul M., “Strided Fully Convolutional Neural Network for Boosting the Sensitivity of Retinal Blood Vessels Segmentation”, Expert Systems with Applications, 134: 36-52, 2019. https://doi.org/10.1016/j.eswa.2019.05.029.
11 Nguyen U. T. V., Bhuiyan A., Park L. A. F., and Ramamohanarao K., “An Effective Retinal Blood Vessel Segmentation Method Using Multi-Scale Line Detection”, Pattern Recognition, 46(3): 703-715, 2013.
12 هویدا ف.، شاه¬بهرامی ا.، «ارزیابی کارایی تشخیص جعل کپی- انتقال تصاویر مبتنی بر بلاک¬بندی»، مجله محاسبات نرم، جلد 7، شماره 1، ص. 79-62، 1397.
13 Emary E., Zawbaa H. M., Hassanien A. E., and Parv B., “Multi-Objective Retinal Vessel Localization Using Flower Pollination Search Algorithm with Pattern Search”, Advanced Data Analysis and Classification, 11(3): 611-627, 2017. https://doi.org/10.1007/s11634-016-0257-7.
14 Al Shehhi R., Marpu P. R., and Woon W. L., “An Automatic Cognitive Graph-Based Segmentation for Detection of Blood Vessels in Retinal Images”, Mathematical Problems in Engineering, pp. 1-15, 2016. https://doi.org/10.1155/2016/7906165.
15 Singh N. P. and Srivastava R., “Retinal Blood Vessels Segmentation by Using Gumbel Probability Distribution Function Based Matched Filter”, Computer Methods and Programs in Biomedicine, 129: 40-50, 2016. https://doi.org/10.1016/j.cmpb.2016.03.001.
16 Liskowski P. and Krawiec K., “Segmenting Retinal Blood Vessels with Deep Neural Networks”, IEEE Transactions on Medical Imaging, 35(11): 2369-2380, 2016. https://doi.org/10.1109/TMI.2016.2546227.
17 Oliveira W. S., Teixeira J. V., Ren T. I., Cavalcanti G. D. C., and Sijbers J., “Unsupervised Retinal Vessel Segmentation Using Combined Filters”, PLOS ONE, 11(2): 121, 2016. https://doi.org/10.1371/journal.pone.0149943.
18 Abdellahoum H., Mokhtari N., Brahimi A., and Boukra A., “CSFCM: An Improved Fuzzy C-Means Image Segmentation Algorithm Using a Cooperative Approach”, Expert Systems with Applications, 166: 114063-114085, 2021. https://doi.org/10.1016/j.eswa.2020. 114063.
19 Imani E., Javidi M., Pourreza H., “Improvement of Retinal Blood Vessel Detection Using Morphological Component Analysis”, Computer Methods and Programs in Biomedicine, 118(3): 263-279, 2015. https://doi.org/10.1016/j.cmpb.2015.01.004.
20 Mishra S., Chen D. Z., and Hu X. S., “A data-aware deep supervised method for retinal vessel segmentation”, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pp. 1254-1257, 2020. https://doi.org/10.1109/ISBI45749.2020.9098403.
21 Wang D., HaythamA., Pottenburgh J., Saeedi O., and Tao Y., “Hard attention net for automatic retinal vessel segmentation”, IEEE Journal of Biomedical and Health Informatics, 24(12): 3384-3396, 2020. https://doi.org/10.1109/JBHI.2020.3002985.
22 Uysal E, and Guraksin G. E., “Computer-aided retinal vessel segmentation in retinal images: convolutional neural networks”, Multimedia Tools and Applications, 80(3): 3505-3528, 2021. https://doi.org/10.1007/s11042-020-09372-w.
23 Oliveira A., Pereira S., and Silva C. A., “Retinal vessel segmentation based on Fully Convolutional Neural Networks”, Expert Systems with Applications, 112: 229-242, 2018. https://doi.org/10.1016/j.eswa.2018.06.034.
24 Dai P., Luo H., Sheng H., Zhao Y., Li L., Wu J., Zhao Y., and Suzuki K., “A new approach to segment both main and peripheral retinal vessels based on grayvoting and gaussian mixture model” PLoS ONE, 10(6): 122, 2015.
25 شاه¬بیک ص.، پورقاسم ح.، «استخراج رگ¬های خونی تصاویر شبکیه با استفاده از تبدیل نسل جدید کرولت و عملگرهای مورفولوژی وزن¬دار شده وفقی»، هوش محاسباتی در مهندسی برق، دوره 3، شماره 4، ص. 76-63، 1391.
26 خرقانیان ر.، احمدی¬فرد ع.، «استخراج خطوط مرکزی رگ¬های شبکیه چشم با استفاده از ویژگی¬های توپوگرافیکی و فیلترهای جهت¬دار»، سیستم¬های هوشمند در مهندسی برق، دوره 3، شماره 1، ص. 28-17، 1391.
27 L. Gang, O. Chutatape, and S. M. Krishnan. “Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter”. IEEE Trans on Biomedical Engineering, 49(2): 168-172, 2002.
28 S. Chaudhuri, S. Chatterjee, N. Katz, M. Nelson, and M. Goldbaum, “Detection of blood vessels in retinal images using two-dimensional matched filters”, IEEE Trans on Med. Image., vol. 8, pp. 263-269, Sept. 1989.
29 J. J. Staal, M. D. Abr amoff, M. Niemeijer, M. A. Viergever, and B. van Ginneken, “Ridge based vessel segmentation in color images of the retina,” IEEE Trans on Medical Imaging, vol. 23(4): 501-509, 2004.
30 A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piece-wise threshold probing of a matched filter response”, IEEE Trans. Med. Image., vol. 19, pp. 203-210, Mar. 2000.
31 http://www.isi.uu.nl/Research/key value
32 http://www.ces.clemson.edu/ahoover/stare
33 X. Jiang and D. Mojon, “Adaptive local thresholding by verification based multithreshold probing withapplication to vessel detection in retinal images”, IEEE Trans on Pattern Analysis and Machine Intelligence, vol. 25(1): 131-137, 2003.
34 J. V. B. Soares, J. J. G. Leandro, R. M. Cesar-Jr., H. F. Jelinek, and M. J. Cree. “Using the 2-D morlet wavelet with supervised classification for retinal vessel segmentation”, In IV Workshop de Teses e Dissertacoes em Computacao Grafica e Processamento de Imagens, CD-ROM – 18th Brazilian Symposium on Computer Graphics and Image Processing, Natal, RN, 2005.
35 W. T. Freeman and E. Adelson. “The design and use of steerable filters,” IEEE Trans on Pattern Analysis and Machine Intelligence, 13(9): 891-906, Sept 1991.
36 D. J. Cornforth, H. J. Jelinek, J. J. G. Leandro, J. V. B. Soares, Jr. R. M. Cesar, M. J. Cree, P. Mitchell, T. Bossamaier, “Development of Rentinal Blood Vessel Segmentation Methodology Using Wavelet Transforms Assessment of Diabetic Retinopathy”, Eighth Asia Pacific Symposium on Intelligent and Evolutionary Systems, Cairns, Australia, pp. 50-60, 2004.
37 J. J. G. Leandro, J. V. B. Soares, R. M. Cesar-Jr., and H. F. Jelinek. “Blood vessels segmentation in non-mydriatic images using wavelets and statistical classifiers”, In Proc. Of the 16th Brazilian Symposium on Computer Graphics and Image Processing – SIBGRAPI, pages 262-269. IEEE Computer Society Press, 2003.
38 X. Gao, A. Bharath, A. Stanton, A. Hughes, N. Chapman, and S. Thom. “A method of vessel tracking for vessel diameter measurement on retinal images”, In ICIP01, pages II: 881-884, 2001.
39 M. Lalonde, L. Gagnon, and M.-C. Boucher. “Non-recursive paired tracking for vessel extraction from retinal images”, In Proc. Of the Conference Vision Interface 2000, pages 61-68, 2000.
40 A. Can, H. Shen, J. N. Turner, H. L. Tanenbaum, and B. Roysam. “Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms”, IEEE Trans on Information Technology in Biomedicine, 3(2): 125-138, 1999.
41 Y. A. Tolias and S. M. Panas. “A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering”, IEEE Trans on Medical Imaging, 17: 263-273, April. 1998.
42 M. E. Martinez-Perez, A. D. Hughes, A. V. Stanton, S. A. Thom, A. A. Bharath, and K. H. Parker, “Retinal blood vessel segmentation by means of scale-space analysis and region growing”, In Medical Image Computing and Computer-assisted Intervention-MICCAI, 1999, pp. 90-97.
43 Ahmed Dourhri and etl, KVMod—A Novel Approach to Design Key-Value NoSQL Databases, Feature Papers in Information in 2023,oct 2023.
44 محمدی م.، نجاتی ف.، «نشان¬نگاری با رویکرد تجزیه ماتریسی هسنبرگ»، مجله محاسبات نرم، جلد 9، شماره 1، ص. 157-146، 1399.
45 میرزاخانی ع.، محمدپور م.، «تشخیص تخریب دیسک بین مهره¬ای کمر با استفاده از تصاویر MRI»، مجله محاسبات نرم، جلد 9، شماره 1، ص. 123-114، 1399.
46 K. G. Goh, W. Hsu, M. L. Lee. “An Automatic Diabetic Retinal Image Screening System”, Medical Data Mining and Knowledge Discovery, Springer-Velag, 2000.
47 M. Niemeijer, J. J. Staal, B. van Ginneken, M. Loog, and M. D.Abramoff, “Comparative study of retinal vessel segmentation methods on a new publicly available database”, In SPIE Medical Imaging, J. M.Fitzpatrick and M. Sonka, Eds., vol. 5370, pp. 648-656, 2004.
48 F. Zana and J. Klein, “Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation”, IEEE Trans on Image Processing, 10(7): 1010-1019, 2001.
49 Di Wu, Ming Zhang, Jyh-Charn Liu, and Wendall Bauman, “On the Adaptive Detection of Blood Vessels in Retinal Images”, IEEE Trans on Biomedical Engineering, vol. 53(2), Feb 2006.