Features extraction using encoded local binary pattern for detection and grading diabetic retinopathy
Tóm tắt
Reliable computer diagnosis of diabetic retinopathy (DR) is needed to rescue many with diabetes who may be under threat of blindness. This research aims to detect the presence of diabetic retinopathy in fundus images and grade the disease severity without lesion segmentation. To ensure that the fundus images are in a standard state of brightness, a series of preprocessing steps have been applied to the green channel image using histogram matching and a median filter. Then, contrast-limited adaptive histogram equalisation is performed, followed by the unsharp filter. The preprocessed image is divided into small blocks, and then each block is processed to extract uniform local binary patterns (LBPs) features. The extracted features are encoded, and the feature size is reduced to 3.5 percent of its original size. Classifiers like Support Vector Machine (SVM) and a proposed CNN model were used to classify retinal fundus images. The classification is abnormal or normal and to grade the severity of DR. Our feature extraction method was tested on a binary classifier and resulted in an accuracy of 98.37% and 98.84% on the Messidor2 and EyePACS databases, respectively. The proposed system could grade DR severity into three grades (0: no DR, 1: mild DR, and 5: moderate, severe NPDR, and PDR). It obtains an F1-score of 0.9617 and an accuracy of 95.37% on the EyePACS database, and an F1-score of 0.9860 and an accuracy of 97.57% on the Messidor2 database. The resultant values are dependent on the selection of (neighbours, radius) pairs during the extraction of LBP features. This study’s results proved that the preprocessing steps are significant and had a great effect on highlighting image features. The novel method of stacking and encoding the LBP values in the feature vector greatly affects results when using SVM or CNN for classification. The proposed system outperforms the state of the artwork. The proposed CNN model performs better than SVM.
Tài liệu tham khảo
Kumar S, Kumar R, Sathar A. Automatic detection of exudates in retinal images using histogram analysis. In: IEEE recent advances in intelligent computational systems (RAICS) automatic. 2013;5(3):277–281.
Neuwirth J. Diabetic retinopathy: what you should know. Connecticut Medicine. National Eye Institute. 2015;52(6):361. https://www.nei.nih.gov/sites/default/files/2019-06/Diabetic-Retinopathy-What-You-Should-Know-508.pdf
Colomer A, Igual J, Naranjo V. Detection of early signs of diabetic retinopathy based on textural and morphological information in fundus images. Sensors. 2020;20(4):1005. https://doi.org/10.3390/s20041005.
Rathod DD, Manza RR, RajpuY M, Patwari MB, Saswade M, Deshpande N. Localization of optic disc and macula using multilevel 2-D wavelet decomposition based on haar wavelet transform. Int J Eng Res Technol IJERT. 2014;3(7):474–8.
Sekar GB, Nagarajan P. Localisation of optic disc in fundus images by using clustering and histogram techniques. Proceedings of the IEEE International Conference on Computing, Electronics and Electrical Technologies (ICCEET ’12); India: Kumaracoil; 2012. pp. 584–589.
Lu S, Lim JH. Automatic optic disc detection from retinal images by a line operator. IEEE Trans Biomed Eng. 2011;58(1):88–94. https://doi.org/10.1109/TBME.2010.2086455.
Acharya UR, Chua CK, Min LC, Ng EY, Mushrif MM, Laude A (2012) Application of intuitionistic fuzzy histon segmentation for the automated detection of optic disc in digital fundus images. Proceedings of the in IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ’12); Hong Kong, pp 444–447
Trucco E, Ballerini L, Relan D, et al. Novel VAMPIRE algorithms for quantitative analysis of the retinal vasculature. Proceedings of the 4th ISSNIP-IEEE Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC ’13), February 2013. Rio de Janerio, Brazil; 2013. pp. 1–4.
Wan S, Lee HC, Xu T, et al. Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy. Med Image Anal. 2017;38:104–16. https://doi.org/10.1016/j.media.2017.03.002.
Manojkumar SB, Shama Firdose U, Sheshadri HS. Detection of retinal disease screening using local binary patterns. In: Sridhar V, Padma M, Rao K, editors. Emerging Research in Electronics, Computer Science and Technology. Lecture Notes in Electrical Engineering, vol 545. Singapore: Springer; 2019. pp. 1055. https://doi.org/10.1007/978-981-13-5802-9_91.
Ali MA, Hurtut T, Faucon T, Cheriet F. Glaucoma detection based on local binary patterns in fundus photographs. SPIE Med Imaging. 2014;9035:903531–90353.
Rajput GG, Patil PN. Detection and classification of exudates using k-means clustering in color retinal images. 2014 Fifth International Conference on Signal and Image Processing; 2014. pp. 126-130. https://doi.org/10.1109/ICSIP.2014.25.
Intriago-Pazmino M, Ibarra-Fiallo J, Crespo J, Alonso-Calvo R. Enhancing vessel visibility in fundus images to aid the diagnosis of retinopathy of prematurity. Health Informatics J. 2020;26(4):2722–36. https://doi.org/10.1177/1460458220935369.
Luangruangrong W, Kulkasem P, Rasmequan S, Rodtook A, Chinnasarn K Automatic exudates detection in retinal images using efficient integrated approaches. Signal and Information Processing Association Annual Summit and Conference (APSIPA), Asia-Pacific; 2014. pp. 1–5,. https://doi.org/10.1109/APSIPA.2014.7041749.
Wang J, Luo J, Liu B, Feng R, Lu L, Zou H. Automated diabetic retinopathy grading and lesion detection based on the modified R-FCN object-detection algorithm. IET Comput Vis. 2020;14(1):1–8. https://doi.org/10.1049/iet-cvi.2018.5508.
Dai J, Li Y, He K, Sun J (2016) R-FCN: object detection via region-based fully convolutional networks. In: NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems. December 206: 379–87. https://doi.org/10.48550/arXiv.1605.06409
Ramachandran N, Hong SC, Sime MJ, Wilson GA. Diabetic retinopathy screening using deep neural network. Clin Exp Ophthalmol. 2018;46(4):412–6. https://doi.org/10.1111/ceo.13056.
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. Cornel University 2016; 2014. arXiv:1605.06409v2 [cs.CV]; https://doi.org/10.48550/arXiv.1409.4842
Alex K, Ilya S, Geoffrey HE. ImageNet classification with deep convolutional neural. Commun ACM. 2017;60(6):84–90. https://doi.org/10.1145/3065386.ISSN0001-0782.S2CID195908774.
Johari MH, Hassan HA, Yassin AIM, Tahir NM, Zabidi A, Rizman ZI, Baharom R, Wahab NA. Early detection of diabetic retinopathy by using deep learning neural network. Int J Eng Technol. 2018;7(4):198–201.
Lam C, Yi D, Guo M, Lindsey T. Automated detection of diabetic retinopathy using deep learning. AMIA joint summits on translational science proceedings. AMIA Jt Summits Transl Sci. 2018;2017:147–55.
David A, et al. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Investigat Ophthalmol Visual Sci. 2016;57(13):5200–6. https://doi.org/10.1167/iovs.16-19964.
Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology. 2017;124(7):962–9.
Li X, Hu X, Yu L, Zhu L, Fu CW, Heng PA. CANet: cross-disease attention network for joint diabetic retinopathy and diabetic macular edema grading. IEEE Trans Med Imaging. 2020;39(5):1483–93. https://doi.org/10.1109/tmi.2019.2951844.
Li Y-H, Yeh N-N, Chen S-J, Chung Y-C. Computer-assisted diagnosis for diabetic retinopathy based on fundus images using deep convolutional neural network. Mobile Inform Syst. 2019. https://doi.org/10.1155/2019/6142839.
Shaban M, Ogur Z, Mahmoud A, Switala A, Shalaby A, Abu Khalifeh H, et al. A convolutional neural network for the screening and staging of diabetic retinopathy. PLoS ONE. 2020;15(6): e0233514. https://doi.org/10.1371/journal.pone.0233514.
Katada Y, Ozawa N, Masayoshi K, Ofuji Y, Tsubota K, Kurihara T. Automatic screening for diabetic retinopathy in interracial fundus images using artificial intelligence. Intelligence-Based Med. 2020. https://doi.org/10.1016/j.ibmed.2020.100024.R.
Decencière E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R, MassiP N, Erginay A, Charton B, Klein J. Feedback on a publicly distributed database: the Messidor database. Image Anal Stereol. 2014;33(3):231–4.
Kaggle Datasets, Diabetic Retinopathy Detection Identify signs of diabetic retinopathy in eye images dataset. https://www.kaggle.com/competitions/diabetic-retinopathy-detection/data
Usman AM, Shehzad K, Khan SA. Identification and classification of microaneurysms for early detection of diabetic retinopathy. Pattern Recognit. 2012;46(1):107–16. https://doi.org/10.1016/j.patcog.2012.07.002.
Zuiderveld K. Contrast limited adaptive histogram equalization. Graphics gems IV. 1994;42(1):474–85.
Sarhan MH, Albarqouni S, Yigitsoy M, Navab N, Abouzar E. Microaneurysms segmentation and diabetic retinopathy detection by learning discriminative representations. IET Image Process. 2020;14(17):4571–8. https://doi.org/10.1049/iet-ipr.2019.0804.
Costa P, Galdran A, Smailagic A, Campilho A. A weakly-supervised framework for interpretable diabetic retinopathy detection on retinal images. IEEE Access. 2018;6:18747–58. https://doi.org/10.1109/ACCESS.2018.2816003.
Dutta S, Manideep BC, Basha SM, Caytiles RD, Iyengar NCSN. Classification of diabetic retinopathy images by using deep learning models. Int J Grid Distrib Comput. 2018;11(1):99–106.
Chetoui M, Akhloufi MA. Explainable end-to-end deep learning for diabetic retinopathy detection across multiple datasets. J Med Imaging. 2020;7(4): 044503. https://doi.org/10.1117/1.JMI.7.4.044503.
Kwasigroch A, Jarzembinski B, Grochowski M. Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy. Int Interdisc PhD Workshop (IIPhDW). 2018;2018:111–6. https://doi.org/10.1109/IIPHDW.2018.8388337.
Chowdhury MMH, Meem NTA, Marium-E-Jannat. A machine learning approach to detect diabetic retinopathy using convolutional neural network. In: Uddin M, Bansal J, editors. Proceedings of International Joint Conference on Computational Intelligence. Algorithms for Intelligent Systems. Singapore: Springer. https://doi.org/10.1007/978-981-13-7564-4_23
Sayres R, Taly A, Rahimy E, Blumer K, Coz D, Hammel N, Krause J, Narayanaswamy A, Rastegar Z, Wu D, et al. Using a deep learning algorithm and integrated gradients explanation to assist grading for diabetic retinopathy. Ophthalmology. 2019;126:552–64.
Sengupta S, Singh A, Zelek J, Lakshminarayanan V. Cross-domain diabetic retinopathy detection using deep learning. Proc. SPIE 11139, Applications of Machine Learning. 111390V. https://doi.org/10.1117/12.2529450
Pao SI, Lin HZ, Chien KH, Tai MC, Chen JT, Lin GM. Detection of diabetic retinopathy using bichannel convolutional neural network. J Ophthalmol. 2020. https://doi.org/10.1155/2020/9139713.
Samanta A, Saha A, Satapathy SC, Fernandes SL, Zhang YD. Automated detection of diabetic retinopathy using convolutional neural networks on a small dataset. Pattern Recognit Lett. 2020;135:293–8.
Thota NB, Reddy DU. Improving the accuracy of diabetic retinopathy severity classification with transfer learning. In: Proceedings of the 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS). MA, USA: Springfield; Springfield; 2020. pp. 1003–1006.
Ludwig CA, Chandrashan P, David M, Greven MA, Smith SJ, Chang RT, Theodore L. Automatic identification of referral-warranted diabetic retinopathy using deep learning on mobile phone images. Trans Vis Sci Tech. 2020;9(2):60. https://doi.org/10.1167/tvst.9.2.60.