(49-2) 14 * << * >> * Russian * English * Content * All Issues

Development of an OCT image analysis algorithm for differential diagnosis of retinal edema based on deep learning
N.S. Demin 1,2, N.Y. Ilyasova 1,2, E.A. Zamytskiy 3, A.V. Zolotarev 3, D.V. Kirsh 1,2, A.Y. Ionov 1

1 Samara National Research University,
443086, Samara, Russia, Moskovskoye Shosse 34;
2 Image Processing Systems Institute, NRC "Kurchatov Institute",
Molodogvardeyskaya Str. 151, Samara, 443001, Russia;
3 Federal State Budgetary Educational Institution of Higher Education «Samara State Medical University»,
of the Ministry of Healthcare of the Russian Federation,
89, Chapaevskaya st., Samara, Russia, 443099

 PDF, 2584 kB

DOI: 10.18287/2412-6179-CO-1613

Pages: 292-300.

Full text of article: Russian language.

Abstract:
The aim of this work is to develop an algorithm for differential diagnosis of retinal edema and study deep learning methods and their application to image analysis. The application of convolutional neural networks for the task of semantic segmentation of retinal layers is investigated and its efficiency is proved for two selected layers (pigment epithelium and retina). An algorithm of disease classification based on the intellectual analysis of the layers selected by the neural network is implemented. A proof of its applicability for differential diagnostics of retinal edema is presented. The accuracy of disease detection amounts to 90%.

Keywords:
image segmentation, convolutional neural networks, image classification, optical coherence tomography, age-related macular degeneration, diabetic macular edema.

Citation:
Demin NS, Ilyasova NY, Zamytskiy EA, Zolotarev AV, Kirsh DV, Ionov AYu. Development of an OCT image analysis algorithm for differential diagnosis of retinal edema based on deep learning. Computer Optics 2025; 49(2): 292-300. DOI: 10.18287/2412-6179-CO-1613.

Acknowledgements:
This work was carried out within the state assignment of NRC “Kurchatov Institute”.

References:
  1. Zakharova MA, Kuroedov AV. Optical coherence tomography: a technology that has become a reality [In Russian]. RMZ. Clinical Ophthalmology 2015; 16(4): 204-211.
  2. Fursova AJ, Gamza YA, Derbeneva AS, Vasilieva MS. Anti-angiogenesis therapy of diabetic macular edema in patients with primary open-angle glaucoma [In Russian]. Russian Annals of Ophthalmology 2020; 136(6, vyp 2): 185-194. DOI: 10.17116/oftalma2020136062185.
  3. Gvetadze AA, Koroleva IA. Age-related macular degeneration. A modern view of the problem (literature review) [In Russian]. RMJ. Clinical Ophthalmology 2015; 16(1): 39-43.
  4. Kizi BN. Age-related macular degeneration of the retina. Academy 2018; 8(35): 57-62.
  5. Astakhov YS, Neroev VV, Shestakova MV, Zaitseva OV, Okhotsimskaya TD, Ryabina MV, Kononenko IV. Diabetes mellitus: diabetic retinopathy, diabetic macular edema. Clinical guidelines [In Russian]. Ministry of Health of the Russian Federation Publisher; 2013.
  6. Harry DD, Sahakyan SV, Khoroshilova-Maslova IP, Tsygankov, AY, Nikitin, OI, Tarasov GY. Machine learning methods in ophthalmology. A review of the literature [In Russian]. Ophthalmology 2020; 17(1): 20-31. DOI: 10.18008/1816-5095-2020-1-20-31.
  7. Demin NS, Ilyasova NYu, Shirokanev AS, Zamytsky EA. Segmentation of OCT images for localization of macular diabetic edema area [In Russian]. Proc Information Technologies and Nanotechnologies (ITNT-2020) 2020; 4: 212-219.
  8. Lu S, Cheung CYL, Liu J, Lim JH, Leung CKS, Wong TY. Automated layer segmentation of optical coherence tomography images. IEEE Trans Biomed Eng 2010; 57(10): 2605-2608. DOI: 10.1109/tbme.2010.2055057.
  9. Lang A, Carass A, Hauser M, Sotirchos ES, Calabresi PA, Ying HS, Prince JL. Retinal layer segmentation of macular OCT images using boundary classification. Biomed Opt Express 2013; 4(7): 1133-1352. DOI: 10.1364/boe.4.001133.
  10. Morales S, Colomer A, Mossi JM, del Amor R, Woldbye D, Klemp K, Larsen M, Naranjo V. Retinal layer segmentation in rodent OCT images: Local intensity profiles & fully convolutional neural networks. Comput Methods Programs Biomed 2021; 198: 105788. DOI: 10.1016/j.cmpb.2020.105788.
  11. Ilyasova N, Demin N, Andriyanov N. Development of a computer system for automatically generating a laser photocoagulation plan to improve the retinal coagulation quality in the treatment of diabetic retinopathy. Symmetry 2023; 15(2): 287. DOI: 10.3390/sym15020287.
  12. Hao S, Zhou Y, Guo Y. A brief survey on semantic segmentation with deep learning. Neurocomputing 2020; 406: 302-321. DOI: 10.1016/j.neucom.2019.11.118
  13. Sikorsky OS. A review of convolutional neural networks for the task of image classification [In Russian]. New Information Technologies in Automated Systems 2017; 20: 37-42.
  14. Roy AG, Conjeti S, Karri SK, Sheet D, Katouzian A, Wachinger C, Navab N. ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks. Biomedical Optics Express 2017; 8(8): 3627-3642. DOI: 10.1364/boe.8.003627.
  15. Siddique N, Paheding S, Elkin CP, Devabhaktuni V. U-net and its variants for medical image segmentation: A review of theory and applications. IEEE Access 2021; 9: 82031-82057. DOI: 10.1109/access.2021.3086020.
  16. Müller A, Guido S. Introduction to machine learning with Python: A guide for data scientists. Sebastopol, CA: O'Reilly Media Inc; 2017. ISBN: 978-1-449-36941-5.
  17. Bradski G, Kaehler A. Learning OpenCV: Computer vision with the OpenCV library. Sebastopol, CA: O’Reilly Media Inc; 2008. ISBN: 978-0-596-51613-0.
  18. Ternovoy EA. Python libraries for image processing. examples of using [In Russian]. All-Russian Student Conf "Student Scientific Spring" Dedicated to the 85th Anniversary of YuA Gagarin 2019: 314-314.
  19. Moruzzi G. Plotting with matplotlib. In Book: Moruzzi G. Essential Python for the physicist. Cham, Switzerland: Springer Nature Switzerland AG; 2020: 53-69. DOI: 10.1007/978-3-030-45027-4_3.
  20. Géron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. 2nd ed. Sebastopol, CA: O’Reilly Media Inc; 2019. ISBN: 978-1-492-03264-9.
  21. Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning. J Big Data 2019; 6(1): 60. DOI: 10.1186/s40537-019-0197-0.
  22. Castro E, Cardoso JS, Pereira JC. Elastic deformations for data augmentation in breast cancer mass detection. 2018 IEEE EMBS Int Conf on Biomedical & Health Informatics (BHI) 2018: 230-234. DOI: 10.1109/BHI.2018.8333411.
  23. Oliphant TE. Guide to NumPy. 2nd ed. Continuum Press; 2015. ISBN: 978-1-5173-0007-4.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20