Eye disease segmentation using hybrid neural encoder decoder based Unet hybrid inception

• Autorzy: Bali Le Akanksha , Singh Kuljeet , Mansotra Vibhakar

Identyfikatory

DOI

10.7494/csci.2024.25.4.5997

• Języki publikacji: EN

Abstrakty

EN

Diabetic retinopathy (DR) is one of the major causes of vision problems worldwide. With proper treatment, early diagnosis of DR can prevent the progression of the disease. In this paper, we present a combinative method using U-Net with a modified Inception architecture for the diagnosis of both the diseases. The proposed method is based on deep neural architecture formalising encoder decoder modelling with convolutional architectures namely Inception and Residual Connection. The performance of the proposed model was validated on the IDRid 2019 contest dataset. Experiments demonstrate that the modified Inception deep feature extractor improves DR classification with a classification accuracy of 99.34% in IDRid across classes with comparison to Resnet. The paper Benchmark tests the dataset with proposed model of Hybrid Dense-EDUHI: Encoder Decoder based U-Net Hybrid Inception model with 15 fold cross validation. The paper in details discusses the various metrics of the proposed model with various visualisation and multifield validations.

Słowa kluczowe

EN

fundus images; UNET; deep learning; diabetic retinopathy (DR); Indian Diabetic Retinopathy Image Dataset (IDRID); IDRID

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2024
• Tom: T. 25 (4)
• Strony: 579–--620
• Opis fizyczny: Bibliogr. 50 poz., rys., tab., wykr.

Twórcy

autor

Bali Le Akanksha

• University of Jammu, Department of Computer Science and IT

autor

Singh Kuljeet

• University of Jammu, Department of Computer Science and IT

autor

Mansotra Vibhakar

• University of Jammu, Department of Computer Science and IT

Bibliografia

• [1] Abràmoff M.D., Lavin P.T., Birch M., Shah N., Folk J.C.: Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices, npj Digital Medicine, vol. 1(1), 39, 2018. doi: 10.1038/ s41746-018-0040-6.
• [2] Akram M., Khalid S., Khan S.: Identification and classification of microaneurysms for early detection of diabetic retinopathy, Pattern Recognition, vol. 46(1), pp. 107–116, 2013. doi: 10.1016/j.patcog.2012.07.002.
• [3] Azzopardi G., Strisciuglio N., Vento M., Petkov N.: Trainable COSFIRE filters for vessel delineation with application to retinal images, Medical Image Analysis, vol. 19(1), pp. 46–57, 2015. doi: 10.1016/j.media.2014.08.002.
• [4] Bali A., Mansotra V.: Deep Learning-based Techniques for the Automatic Classification of Fundus Images: A Comparative Study. In: 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), pp. 351–359, 2021. doi: 10.1109/ICAC3N53548.2021.9725464.
• [5] Bali A., Mansotra V.: An Overview of Retinal Image Classification-Techniques and Challenges. In: 2021 First International Conference on Advances in Computing and Future Communication Technologies (ICACFCT), pp. 91–97, 2021. doi: 10.1109/ICACFCT53978.2021.9837371.
• [6] Bali A., Mansotra V.: FUNDUS and OCT Image Classification Using DL Techniques. In: V.S. Rathore, S.C. Sharma, J.M.R.S. Tavares, C. Moreira, B. Surendiran (eds.), Rising Threats in Expert Applications and Solutions. Proceedings of FICR-TEAS 2022, Lecture Notes in Networks and Systems, vol. 434, Springer, 2022. doi: 10.1007/978-981-19-1122-4_8.
• [7] Bali A., Mansotra V.: Analysis of Deep Learning Techniques for Prediction of Eye Diseases: A Systematic Review, Archives of Computational Methods in Engineering, vol. 31, pp. 487–520, 2024. doi: 10.1007/s11831-023-09989-8.
• [8] Bali A., Mansotra V.: Multiclass multilabel ophthalmological fundus image classification based on optimised deep feature space evolutionary model, Multimedia Tools and Applicatios, vol. 83, pp. 49813–49843, 2024. doi: 10.1007/s11042-023- 17530-z.
• [9] Chudzik P., Al-Diri B., Caliva F., Ometto G., Hunter A.: Exudates segmentation using fully convolutional neural network and auxiliary codebook. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 770–773, 2018. doi: 10.1109/embc.2018.8512354.
• [10] Chudzik P., Majumdar S., Caliva F., Al-Diri B., Hunter A.: Exudate segmentation using fully convolutional neural networks and inception modules. In: E.D. Angelini, B.A. Landman (eds.), Medical Imaging 2018: Image Processing, vol. 10574, 1057430, International Society for Optics and Photonics, SPIE, 2018. doi: 10.1117/12.2293549.
• [11] Di Cesare M.: Global trends of chronic non-communicable diseases risk factors, European Journal of Public Health, vol. 29(Supplement_4), ckz185-196, 2019. doi: 10.1093/eurpub/ckz185.196.
• [12] Early Treatment Diabetic Retinopathy Study Research Group: Fundus photographic risk factors for progression of diabetic retinopathy: ETDRS report number 12, Ophthalmology, vol. 98(5), pp. 823–833, 1991.
• [13] Franklin S.W., Rajan S.E.: Computerized screening of diabetic retinopathy employing blood vessel segmentation in retinal images, Biocybernetics and Biomedical Engineering, vol. 34(2), pp. 117–124, 2014. doi: 10.1016/j.bbe.2014.01.004.
• [14] Fraz M.M., Barman S.A., Remagnino P., Hoppe A., Basit A., Uyyanonvara B., Rudnicka A.R., Owen C.G.: An approach to localize the retinal blood vessels using bit planes and centerline detection, Computer Methods and Programs in Biomedicine, vol. 108(2), pp. 600–616, 2012. doi: 10.1016/j.cmpb.2011.08.009.
• [15] Gardner G.G., Keating D., Williamson T.H., Elliott A.T.: Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool, British Journal of Ophthalmology, vol. 80(11), pp. 940–944, 1996. doi: 10.1136/bjo.80.11.940.
• [16] Gargeya R., Leng T.: Automated identification of diabetic retinopathy using deep learning, Ophthalmology, vol. 124(7), pp. 962–969, 2017. doi: 10.1016/ j.ophtha.2017.02.008.
• [17] Gulshan V., Peng L., Coram M., Stumpe M.C., Wu D., Narayanaswamy A., Venugopalan S., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, JAMA, vol. 316(22), pp. 2402–2410, 2016. doi: 10.1001/jama.2016.17216.
• [18] Guo S., Li T., Kang H., Li N., Zhang Y., Wang K.: L-Seg: An end-to-end unified framework for multi-lesion segmentation of fundus images, Neurocomputing, vol. 349, pp. 52–63, 2019. doi: 10.1016/j.neucom.2019.04.019.
• [19] Hagos M.T., Kant S.: Transfer learning based detection of diabetic retinopathy from small dataset, arXiv preprint arXiv:190507203, 2019.
• [20] Haldorai A., Ramu A., Chow C.O.: Editorial: Big Data Innovation for Sustainable Cognitive Computing, Mobile Networks and Applications, vol. 24, pp. 221–223, 2019. doi: 10.1007/s11036-018-1198-5.
• [21] Imani E., Pourreza H.R.: A novel method for retinal exudate segmentation using signal separation algorithm, Computer Methods and Programs in Biomedicine, vol. 133, pp. 195–205, 2016. doi: 10.1016/j.cmpb.2016.05.016.
• [22] Kassani S.H., Kassani P.H., Khazaeinezhad R., Wesolowski M.J., Schneider K.A., Deters R.: Diabetic Retinopathy Classification Using a Modified Xception Architecture. In: 2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp. 1–6, IEEE, 2019. doi: 10.1109/ isspit47144.2019.9001846.
• [23] Li T., Gao Y., Wang K., Guo S., Liu H., Kang H.: Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening, Information Sciences, vol. 501, pp. 511–522, 2019. doi: 10.1016/j.ins.2019.06.011.
• [24] Lian S., Li L., Lian G., Xiao X., Luo Z., Li S.: A Global and Local Enhanced Residual U-Net for Accurate Retinal Vessel Segmentation, IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 18(3), pp. 852–862, 2019. doi: 10.1109/tcbb.2019.2917188.
• [25] Mansour R.F.: Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy, Biomedical Engineering Letters, vol. 8, pp. 41–57, 2018.
• [26] Noh H., Hong S., Han B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1520–1528, 2015. doi: 10.1109/iccv.2015.178.
• [27] Oh K., Kang H.M., Leem D., Lee H., Seo K.Y.: Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images, Scientific Reports, 2021. doi: 10.1038/s41598-021-81539-3.
• [28] Orlando J., Prokofyeva E., Del Fresno M., Blaschko M.: An ensemble deep learning based approach for red lesion detection in fundus images, Computer Methods and Programs in Biomedicine, vol. 153, pp. 115–127, 2018. doi: 10.1016/ j.cmpb.2017.10.017.
• [29] Orlando J.I., Prokofyeva E., Del Fresno M., Blaschko M.B.: An ensemble deep learning based approach for red lesion detection in fundus images, Computer Methods and Programs in Biomedicine, vol. 153, pp. 115–127, 2018. doi: 10.1016/ j.cmpb.2017.10.017.
• [30] Osareh A., Mirmehdi M., Thomas B., Markham R.: Automated identification of diabetic retinal exudates in digital colour images, The British Journal of Ophthalmology, vol. 87(10), pp. 1220–1223, 2003. doi: 10.1136/bjo.87.10.1220.
• [31] Partovi M., Rasta S.H., Javadzadeh A.: Automatic detection of retinal exudates in fundus images of diabetic retinopathy patients, Journal of Research in Clinical Medicine, vol. 4(2), pp. 104–109, 2016. doi: 10.15171/jarcm.2016.017.
• [32] Playout C., Duval R., Cheriet F.: A novel weakly supervised multitask architecture for retinal lesions segmentation on fundus images, IEEE Transactions on Medical Imaging, vol. 38(10), pp. 2434–2444, 2019. doi: 10.1109/ tmi.2019.2906319.
• [33] Quellec G., Charrière K., Boudi Y., Cochener B., Lamard M.: Deep image mining for diabetic retinopathy screening, Medical Image Analysis, vol. 39, pp. 178–193, 2017. doi: 10.1016/j.media.2017.04.012.
• [34] Qureshi I., Ma J., Abbas Q.: Diabetic retinopathy detection and stage classification in eye fundus images using active deep learning, Multimedia Tools and Applications, vol. 80, pp. 11691–11721, 2021. doi: 10.1007/s11042-020-10238-4.
• [35] Romero-Aroca P., Verges-Puig R., de la Torre J., Valls A., Relaño-Barambio N., Puig D., Baget-Bernaldiz M.: Validation of a deep learning algorithm for diabetic retinopathy, Telemedicine and e-Health, vol. 26(8), pp. 1001–1009, 2020. doi: 10.1089/tmj.2019.0137.
• [36] Roychowdhury S., Koozekanani D.D., Parhi K.K.: DREAM: diabetic retinopathy analysis using machine learning, IEEE Journal of Biomedical and Health Informatics, vol. 18(5), pp. 1717–1728, 2013. doi: 10.1109/jbhi.2013.2294635.
• [37] Shanthi T., Sabeenian R.S.: Modified Alexnet architecture for classification of diabetic retinopathy images, Computers & Electrical Engineering, vol. 76, pp. 56–64, 2019. doi: 10.1016/j.compeleceng.2019.03.004.
• [38] Shen W., Zhou M., Yang F., Yu D., Dong D., Yang C., Zang Y., Tian J.: Multicrop convolutional neural networks for lung nodule malignancy suspiciousness classification, Pattern Recognition, vol. 61, pp. 663–673, 2017. doi: 10.1016/ j.patcog.2016.05.029.
• [39] Sinthanayothin C., Boyce J.F., Williamson T.H., Cook H.L., Mensah E., Lal S., Usher D.: Automated detection of diabetic retinopathy on digital fundus images, Diabetic Medicine, vol. 19(2), pp. 105–112, 2002. doi: 10.1046/j.1464- 5491.2002.00613.x.
• [40] Soomro T.A., Gao J., Khan T., Hani A.F.M., Khan M.A., Paul M.: Computerised approaches for the detection of diabetic retinopathy using retinal fundus images: a survey, Pattern Analysis and Applications, vol. 20, pp. 927–961, 2017. doi: 10.1007/s10044-017-0630-y.
• [41] Sopharak A., Uyyanonvara B., Barman S., Williamson T.H.: Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods, Computerized Medical Imaging and Graphics, vol. 32(8), pp. 720–727, 2008. doi: 10.1016/j.compmedimag.2008.08.009.
• [42] Ting D.S.W., Tan G.S.W., Agrawal R., Yanagi Y., Sie N.M., Wong C.W., San Yeo I.Y., Lee S.Y., Cheung C.M.G., Wong T.Y.: Optical coherence tomographic angiography in type 2 diabetes and diabetic retinopathy, JAMA Ophthalmology, vol. 135(4), pp. 306–312, 2017. doi: 10.1001/jamaophthalmol.2016.5877.
• [43] Walter T., Massin P., Erginay A., Ordonez R., Jeulin C., Klein J.C.: Automatic detection of microaneurysms in color fundus images, Medical Image Analysis, vol. 11(6), pp. 555–566, 2007. doi: 10.1016/j.media.2007.05.001.
• [44] Xia Z., Liu Q., Zhang Z., Wang Y.: Segmentation of exudates in fundus images using fully convolutional neural networks, Journal of Medical Imaging and Health Informatics, 2020.
• [45] Xiancheng W., Wei L., Bingyi M., He J., Jiang Z., Xu W., Ji Z., Hong G., Zhaomeng S.: Retina blood vessel segmentation using a U-Net based Convolutional neural network. In: Procedia Computer Science: International Conference on Data Science (ICDS 2018), pp. 8–9, 2018.
• [46] Xu X., Tan T., Xu F.: An improved U-Net architecture for simultaneous arteriole and venule segmentation in fundus image. In: M. Nixon, S. Mahmoodi, R. Zwiggelaar (eds.), Medical Image Understanding and Analysis: 22nd Conference, MIUA 2018, Southampton, UK, July 9–11, 2018, Proceedings, pp. 333–340, Springer International Publishing, 2018. doi: 10.1007/978-3-319-95921-4_31.
• [47] Yan Z., Han X., Wang C., Qiu Y., Xiong Z., Cui S.: Learning mutually localglobal u-nets for high-resolution retinal lesion segmentation in fundus images. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 597–600, IEEE, 2019. doi: 10.1109/isbi.2019.8759579.
• [48] Zhang W., Zhong J., Yang S., Gao Z., Hu J., Chen Y., Yi Z.: Automated identification and grading system of diabetic retinopathy using deep neural networks, Knowledge-Based Systems, vol. 175, pp. 12–25, 2019. doi: 10.1016/ j.knosys.2019.03.016.
• [49] Zhang X., Thibault G., Decencière E., Marcotegui B., Laû B., Danno R., Cazuguel G., et al.: Exudate detection in color retinal images for mass screening of diabetic retinopathy, Medical Image Analysis, vol. 18(7), pp. 1026–1043, 2014. doi: 10.1016/j.media.2014.05.004.
• [50] Zhao Y.Q., Wang X.H., Wang X.F., Shih F.Y.: Retinal vessels segmentation based on level set and region growing, Pattern Recognition, vol. 47(7), pp. 2437–2446, 2014. doi: 10.1016/j.patcog.2014.01.006.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).