A deep learning framework for the detection of Plus disease in retinal fundus images of preterm infants

• Autorzy: Ramachandran Sivakumar , Niyas Punnakadan , Vinekar Anand , John Renu

Identyfikatory

DOI

10.1016/j.bbe.2021.02.005

• Języki publikacji: EN

Abstrakty

EN

Retinopathy of prematurity (ROP) is an eye disorder that mainly affects fundus vasculature of immature infants. The effect of this disease can be mild with no observable impairments or may become severe with neovascularization, leading to retinal detachment and possibly childhood blindness. Avital sign for initiating treatment for ROP is the detection of Plus disease, which is clinically diagnosed by identifying certain morphological changes to the blood vessels present in the retina of preterm infants. The main goal of this study is to develop a diagnostic method that can distinguish between Plus-diseased and healthy infant retinal images. This work utilizes a fully convolutional deep learning architecture for achieving the desired objective. We use a semi-supervised learning technique for training the network. The proposed technique accurately predicts bounding boxes over the tortuous vessel segments present in an infant retinal image. The count of bounding boxes serve as a measure to quantify tortuosity. We also compare the proposed technique with a recently introduced ROP diagnostic method employing U-COSFIRE filters. We show the efficacy of the proposed methodology on a proprietary data set of 289 infant retinal images (89 with ROP, and 200 healthy), obtained from KIDROP Bangalore, India. We obtain sensitivity (true positive rate) and specificity (true negative rate) equal to 0.99 and 0.98, respectively in the experimented data set. The results obtained in this study show the robustness of the proposed pipeline, as a computer aided diagnostic tool, that can augment medical experts in the early diagnosis of ROP.

Słowa kluczowe

EN

retinopathy of prematurity; plus disease; vessel segmentation; tortuosity; convolutional neural network

PL

retinopatia wcześniaków; segmentacja naczyń krwionośnych; sieć neuronowa konwolucyjna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 362--375
• Opis fizyczny: Bibliogr. 61 poz., rys., tab., wykr.

Twórcy

autor

Ramachandran Sivakumar

• Department of Electronics and Communication Engineering, College of Engineering Trivandrum, Kerala, India

autor

Niyas Punnakadan

• Department of Electronics and Communication Engineering, College of Engineering Trivandrum, Kerala, India

autor

Vinekar Anand

• Department of Pediatric and Tele-ROP services, Narayana Nethralaya Eye Hospital, Bangalore, India

autor

John Renu

• Department of Biomedical Engineering, Indian Institute of Technology Hyderabad, Telangana, India

Bibliografia

• [1] Azad R, Gilbert C, Gangwe AB, Zhao P, Wu W-C, Sarbajna P, Vinekar A. Retinopathy of prematurity: How to prevent the third epidemics in developing countries. Asia-Pacific J. Ophthalmol. 2020;9(5):440–8.
• [2] Blencowe H, Lawn JE, Vazquez T, Fielder A, Gilbert C. Pretermassociated visual impairment and estimates of retinopathy of prematurity at regional and global levels for 2010. Pediatric Res. 2013;74(S1):35–49.
• [3] Antaki F, Bachour K, Kim TN, Qian CX. The role of telemedicine to alleviate an increasingly burdened healthcare system: Retinopathy of prematurity. Ophthalmol. Ther. 2020:1–16.
• [4] Greenwald MF, Danford ID, Shahrawat M, Ostmo S, Brown J, Kalpathy-Cramer J, Bradshaw K, Schelonka R, Cohen HS, Chan RP, et al. Evaluation of artificial intelligence-based telemedicine screening for retinopathy of prematurity. J. Am. Assoc. Pediatric Ophthalmology Strabismus 2020;24(3):160–2.
• [5] Le C, Basani LB, Zurakowski D, Ayyala RS, Agraharam SG, et al. Retinopathy of prematurity: Incidence, prevalence, risk factors, and outcomes at a tertiary care center in telangana. J. Clinical Ophthalmol. Res. 2016;4(3):119.
• [6] Hewing NJ, Kaufman DR, Chan RP, Chiang MF. Plus disease in retinopathy of prematurity: qualitative analysis of diagnostic process by experts. JAMA Ophthalmol. 2013;131(8):1026–32.
• [7] Gschließer A, Stifter E, Neumayer T, Moser E, Papp A, Pircher N, Dorner G, Egger S, Vukojevic N, Oberacher-Velten I, et al. Inter-expert and intra-expert agreement on the diagnosis and treatment of retinopathy of prematurity. Am. J. Ophthalmol. 2015;160(3):553–60.
• [8] Sivakumar R, Veena V, John R. A curvature based approach for the automated screening of retinopathy of prematurity in preterm infants. In: 2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS). IEEE; 2017. p. 503–8.
• [9] Sivakumar R, Eldho M, Jiji C, Vinekar A, John R. Diagnosis of plus diseases for the automated screening of retinopathy of prematurity in preterm infants. In: 2016 11th International Conference on Industrial and Information Systems (ICIIS). IEEE; 2016. p. 408–13.
• [10] R. Sivakumar, M. Eldho, C. Jiji, A. Vinekar, R. John, Computer aided screening of retinopathy of prematurity–a multiscale gabor filter approach, in: 2016 Sixth International Symposium on Embedded Computing and System Design (ISED), IEEE, 2016, pp. 259–264.
• [11] Oloumi F, Rangayyan RM, Ells AL. Computer-aided diagnosis of retinopathy in retinal fundus images of preterm infants via quantification of vascular tortuosity. J. Med. Imaging 2016;3(4) 044505.
• [12] Ramachandran S, Strisciuglio N, Vinekar A, John R, Azzopardi G. U-cosfire filters for vessel tortuosity quantification with application to automated diagnosis of retinopathy of prematurity. Neural Comput. Appl. 2020:1–16.
• [13] H. Fu, Y. Xu, S. Lin, D.W.K. Wong, J. Liu, Deepvessel: Retinal vessel segmentation via deep learning and conditional random field, in: International conference on medical image computing and computer-assisted intervention, Springer, 2016, pp. 132–139.
• [14] A. Dasgupta, S. Singh, A fully convolutional neural network based structured prediction approach towards the retinal vessel segmentation, in: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), IEEE, 2017, pp. 248–251.
• [15] Feng Z, Yang J, Yao L. Patch-based fully convolutional neural network with skip connections for retinal blood vessel segmentation. In: 2017 IEEE International Conference on Image Processing (ICIP). IEEE; 2017. p. 1742–6.
• [16] Guo Y, Budak Ü., Şengür A. A novel retinal vessel detection approach based on multiple deep convolution neural networks. Computer Methods Programs Biomed. 2018;167:43–8.
• [17] Lotmar W, Freiburghaus A, Bracher D. Measurement of vessel tortuosity on fundus photographs, Graefe’s Archive for. Clinical Exp. Ophthalmol. 1979;211(1):49–57.
• [18] Gelman R, Martinez-Perez ME, Vanderveen DK, Moskowitz A, Fulton AB. Diagnosis of plus disease in retinopathy of prematurity using retinal image multiscale analysis. Investigative Ophthalmol. Visual Sci. 2005;46(12):4734–8.
• [19] V.V. Makkapati, V.V.C. Ravi, Computation of tortuosity of two dimensional vessels, in: Advances in Pattern Recognition (ICAPR), 2015 Eighth International Conference on, IEEE, 2015, pp. 1–4.
• [20] Hart WE, Goldbaum M, Côté B, Kube P, Nelson MR. Measurement and classification of retinal vascular tortuosity. Int. J. Med. Inform. 1999;53(2):239–52.
• [21] Gensure RH, Chiang MF, Campbell JP. Artificial intelligence for retinopathy of prematurity. Curr. Opin. Ophthalmol. 2020;31(5):312–7.
• [22] Scruggs BA, Chan RP, Kalpathy-Cramer J, Chiang MF, Campbell JP. Artificial intelligence in retinopathy of prematurity diagnosis. Transl. Vision Sci. Technol. 2020;9(2):5.
• [23] Brown JM, Campbell JP, Beers A, Chang K, Ostmo S, Chan RP, Dy J, Erdogmus D, Ioannidis S, Kalpathy-Cramer J, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA Ophthalmol. 2018;136(7):803–10.
• [24] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer; 2015. p. 234–41.
• [25] Wang J, Ju R, Chen Y, Zhang L, Hu J,Wu Y, DongW, Zhong J, Yi Z. Automated retinopathy of prematurity screening using deep neural networks. EBioMedicine 2018;35:361–8.
• [26] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision, in. In: Proceedings of the IEEE conference on computer vision and pattern recognition. p. 2818–26.
• [27] Wang Y, Chen Y. Automated recognition of retinopathy of prematurity with deep neural networks. J. Phys: Conf. Ser. 2019;1187 . https://doi.org/10.1088/1742-6596/1187/4/042057042057.
• [28] Zhang Y, Wang L, Wu Z, Zeng J, Chen Y, Tian R, Zhao J, Zhang G. Development of an automated screening system for retinopathy of prematurity using a deep neural network for wide-angle retinal images. IEEE Access 2018;7:10232–41.
• [29] Ramachandran S, Kochitty S, Vinekar A, John R. A fully convolutional neural network approach for the localization of optic disc in retinopathy of prematurity diagnosis. J. Intell. Fuzzy Syst. 2020:1–10 (Preprint).
• [30] Karnataka internet assisted diagnosis of retinopathy of prematurity. URL:http://kidrop.org/.
• [31] J. Redmon, A. Farhadi, Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767.
• [32] A.L. Maas, A.Y. Hannun, A.Y. Ng, Rectifier nonlinearities improve neural network acoustic models, in: Proc. icml, Vol. 30, 2013, p. 3.
• [33] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition, in. In: Proceedings of the IEEE conference on computer vision and pattern recognition. p. 770–8.
• [34] S. Ioffe, C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXivpreprint arXiv:1502.03167.
• [35] Azzopardi G, Strisciuglio N, Vento M, Petkov N. Trainable cosfire filters for vessel delineation with application to retinal images. Medical Image Anal. 2015;19(1):46–57.
• [36] J. Yosinski, J. Clune, Y. Bengio, H. Lipson, How transferable are features in deep neural networks? in: Advances in neural information processing systems, 2014, pp. 3320–3328.
• [37] Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. ImageNet: A Large-Scale Hierarchical Image Database, in. In: CVPR09.
• [38] D.-H. Lee, Pseudo-label: The simple and efficient semisupervised learning method for deep neural networks, in: Workshop on challenges in representation learning, ICML, Vol. 3, 2013, p. 2.
• [39] D.P. Kingma, J. Ba, Adam: A method for stochastic optimization, arXiv preprint arXiv:1412.6980.
• [40] Chicco D, Jurman G. The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genomics 2020;21(1):6.
• [41] Cohen J. A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 1960;20(1):37–46.
• [42] McHugh ML. Interrater reliability: the kappa statistic. Biochemia Medica 2012;22(3):276–82.
• [43] Y. Wang, Y. Chen, Automated recognition of retinopathy of prematurity with deep neural networks, in: Journal of Physics: Conference Series, Vol. 1187, IOP Publishing, 2019, p. 042057.
• [44] Chetia S, Nirmala S. Polynomial modeling of retinal vessels for tortuosity measurement. Biocybernetics Biomed. Eng. 2019;39(2):512–25.
• [45] Patel TP, Aaberg MT, Paulus YM, Lieu P, Dedania VS, Qian CX, Besirli CG, Margolis T, Fletcher DA, Kim TN. Smartphone-based fundus photography for screening of plus-disease retinopathy of prematurity. Graefe’s Arch. Clinical Exp. Ophthalmol. 2019;257(11):2579–85.
• [46] Owen CG, Rudnicka AR, Mullen R, Barman SA, Monekosso D, Whincup PH, Ng J, Paterson C. Measuring retinal vessel tortuosity in 10-year-old children: validation of the computer-assisted image analysis of the retina (caiar) program. Investigative Ophthalmol. Visual Sci. 2009;50 (5):2004–10.
• [47] Oloumi F, Rangayyan RM, Casti P, Ells AL. Computer-aided diagnosis of plus disease via measurement of vessel thickness in retinal fundus images of preterm infants. Computers Biol. Med. 2015;66:316–29.
• [48] 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 Inform. J. 2020. 1460458220935369.
• [49] Kim SJ, Campbell JP, Kalpathy-Cramer J, Ostmo S, Jonas KE, Choi D, Chan RP, Chiang MF. Accuracy and reliability of eyebased vs quadrant-based diagnosis of plus disease in retinopathy of prematurity. JAMA Ophthalmol. 2018;136 (6):648–55.
• [50] J. Mao, Y. Shao, J. Lao, X. Yu, Y. Chen, C. Zhang, H. Li, L. Shen, Ultra–wide-field imaging and intravenous fundus fluorescein angiography in infants with retinopathy of prematurity, Retina (Philadelphia, Pa.) 40 (12) (2020) 2357.
• [51] Keck KM, Kalpathy-Cramer J, Ataer-Cansizoglu E, You S, Erdogmus D, Chiang MF. Plus disease diagnosis in retinopathy of prematurity: vascular tortuosity as a function of distance from optic disc. Retina (Philadelphia, Pa.) 2013;33 (8):1700.
• [52] Worrall DE, Wilson CM, Brostow GJ. Automated retinopathy of prematurity case detection with convolutional neural networks. In: International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Springer; 2016. p. 68–76.
• [53] Tan Z, Simkin S, Lai C, Dai S. Deep learning algorithm for automated diagnosis of retinopathy of prematurity plus disease. Transl. Vision Sci. Technol. 2019;8(6):23.
• [54] Tong Y, Lu W, Deng Q-Q, Chen C, Shen Y. Automated identification of retinopathy of prematurity by image-based deep learning. Eye Vision 2020;7(1):1–12.
• [55] Y. Peng, W. Zhu, F. Chen, D. Xiang, X. Chen, Automated retinopathy of prematurity screening using deep neural network with attention mechanism, in: Medical Imaging 2020: Image Processing, Vol. 11313, International Society for Optics and Photonics, 2020, p. 1131321.
• [56] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions, in. In: Proceedings of the IEEE conference on computer vision and pattern recognition. p. 1–9.
• [57] Lepore D, Ji MH, Pagliara MM, Lenkowicz J, Capocchiano ND, Tagliaferri L, Boldrini L, Valentini V, Damiani A. Convolutional neural network based on fluorescein angiography images for retinopathy of prematurity management. Transl. Vision Sci. Technol. 2020;9(2):37.
• [58] Wallace DK, Zhao Z, Freedman SF. A pilot study using ”roptool” to quantify plus disease in retinopathy of prematurity. J. Am. Assoc. Pediatric Ophthalmol. Strabismus 2007;11(4):381–7.
• [59] Shah SM, Callaway NF, Moshfeghi DM. Persistent plus disease subsequent to panretinal photocoagulation in an infant with retinopathy of prematurity. Ophthalmic Surgery, Lasers Imaging Retina 2019;50(8):520–1.
• [60] Harrell SN, Brandon DH. Retinopathy of prematurity: the disease process, classifications, screening, treatment, and outcomes. Neonatal Network 2007;26(6):371–8.
• [61] I.C. for the Classification of Retinopathy of Prematurity, et al., The international classification of retinopathy of prematurity revisited., Archives of ophthalmology (Chicago, Ill.: 1960) 123 (7) (2005) 991.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).