تولید مجموعه داده ساختگی برای تصاویر توموگرافی انسجام نوری دارای ناهنجاری تخریب ماکولای وابسته به سن

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه مهندسی پزشکی، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران

2 مرکز تحقیقات چشم اصفهان، گروه چشم پزشکی، دانشگاه علوم پزشکی اصفهان، اصفهان، ایران

3 دانشکده فناوری های نوین پزشکی، مرکز تحقیقات پردازش تصاویر و سیگنال های پزشکی، دانشگاه علوم پزشکی اصفهان، اصفهان، ایران. دستیار پژوهشی، دانشگاه نیوکاسل، انگلستان

چکیده

مقدمه: توموگرافی انسجام نوری نقش مهمی در چشم پزشکی دارد و آنالیز خودکار این تصاویر از اهمیت زیادی برخوردار است، نیاز به برچسب گذاری و بخش بندی دستی این دادگان توسط چشم پزشک و مشکل دیتای محدود یک چالش در زمینه تصاویر پزشکی است و به تعداد زیادی از آنها برای آموزش الگوریتم های مبتنی بر یادگیری عمیق و نیز ارزیابی عملکرد الگوریتم های پردازش تصویر نیاز است.
مواد و روش ها: داده های این طرح شامل مجموعه دادهOCT در حضور ناهنجاری شبکیه در بیماری تخریب ماکولای وابسته به سن ، اخذ شده از دستگاه AREDS2 Ancillary در دانشگاه دوک می باشد. برای آموزش الگوریتم از هفتاد Bاسکن که به طور تصادفی از مجموعه فوق انتخاب می شوند، استفاده میگردد. مدل شکل فعال برای تولید مرزهای مصنوعی بکار رفته است و تصاویر جدید مشابه شکل های مجموعه آموزش تولید می شوند.
یافته ها: با در نظر گرفتن ویژگی های آناتومیکی تصاویر موجود مانند تعداد و ضخامت لایه ها و همچنین روشنایی مربوط به آن ها، دادگانی با مشابهت بالا در حضور ناهنجاری تولید میگردند. برای ارزیابی نتایج داده های ساختگی توسط چشم پزشک مورد بررسی قرارگرفت.
نتیجه گیری: مدل پیشنهادی با استفاده از ویژگی های مهمی مانند مرز لایه های اصلی شبکیه و بافت تخریب شده در اثر بیماری، برای پر کردن خلا موجود در تولید داده های مصنوعیOCT درحضور ناهنجاری طراحی شده و میتواند به عنوان مجموعه داده برای آموزش الگوریتم های مبتنی بر یادگیری عمیق و همچنین ارزیابی عملکرد الگوریتم های بخش بندی مورد استفاده قرار گیرد.

کلیدواژه‌ها

عنوان مقاله [English]

Production of Synthetic Dataset for Optical Coherence Tomography Images with Age-Related Macular Edema

نویسندگان [English]

  • Hajar Danesh 1
  • Keivan Maghooli 1
  • Alireza Dehghani 2
  • Raheleh Kafieh 3
1 Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 Isfahan Eye Research Center, Department of Ophthalmology, Isfahan University of Medical Sciences, Isfahan, Iran
3 School of Advanced Technologies in Medicine, Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran. Research Associate, Newcastle University, UK
چکیده [English]

Introduction: Today, retinal optical coherence tomography (OCT) plays an important role in ophthalmology and automated analysis of OCT images is very important, The need for labeled data and manual segmentation of these data by the ophthalmologist and limited labeled data are challenges in the field of medical imaging and a large number of labeled data is needed to train deep learning algorithms as well as to evaluate the performance of image processing algorithms.
Methods: The data of this project include OCT dataset in the presence of retinal abnormality in age-related macular degeneration disease, obtained from AREDS2 Ancillary device at Duke University. Seventy B scans that are randomly selected from the above set are used to train the algorithm. The active shape model is used to generate synthetic boundaries, and new images are produced similar to the shapes in the training set.
Results: Considering the anatomical features of the existing images such as the number and thickness of the layers as well as the brightness related to them, data with high similarity are produced in the presence of anomalies. Synthetic data were reviewed by an ophthalmologist to evaluate the results.
Conclusion: The proposed model is designed to fill the gap in the production of OCT Synthetic data in the presence of anomalies, using important features such as the boundary of the main layers of the retina and disease-damaged tissue, and can be used as a data set for training deep learning-based algorithms as well as performance of segmentation algorithms.

کلیدواژه‌ها [English]

  • Optical coherence tomography
  • synthetic data
  • age related macular degeneration
  • active shape model

مراجع

  1. J.MSchmitt, "Optical coherence tomography (OCT): a review," IEEE Journal of Selected Topics
    in Quantum Electronics 5(4): , doi: :10.1109/2944.796348.
    2. D. Huang, E. A. Swanson, C. P. Lin, J. S. Schuman, W. G. Stinson, W. Chang, M. R. Hee, T.
    Flotte et al., "Optical coherence tomography," Massachusetts Institute of Technology, Whitaker
    College of Health Sciences and Technology, 1993 .
    3. J. A. Sousa, A. Paiva, A. Silva, J. D. Almeida, G. Braz Junior, J. O. Diniz, W. K. Figueredo, and
    M. Gattass, "Automatic segmentation of retinal layers in OCT images with intermediate age-related
    macular degeneration using U-Net and DexiNed," Plos one, vol. 16, no. 5, p. e0251591, 2021, doi:
    10.1371/journal.pone.0251591.
    4. D. Mahapatra, B. Bozorgtabar, and L. Shao, "Pathological retinal region segmentation from oct
    images using geometric relation based augmentation," in Proceedings of the IEEE/CVF Conference
    on Computer Vision and Pattern Recognition, 2020, pp. 9611-9620 .
    5. Z. Chen, D. Li, H. Shen, Y. Mo, H. Wei, and P. Ouyang, "Automated retinal layer segmentation
    in OCT images of age-related macular degeneration," IET Image Processing, vol. 13, no. 11, pp.
    1824-1834, 2019, doi: 10.1049/iet-ipr.2018.5304.
    6. A. Shirokanev, N. Ilyasova, N. Demin, and E. Zamyckij, "Extracting a DME area based on
    graph-based image segmentation and collation of OCT retinal images," in Journal of Physics:
    Conference Series, 2021, vol. 1780, no. 1: IOP Publishing, p. 012031 .
    7. N. Ilyasova, A. Shirokanev, N. Demin, and R. Paringer, "Graph-Based Segmentation for
    Diabetic Macular Edema Selection in OCT Images," in 2019 5th International Conference on
    Frontiers of Signal Processing (ICFSP), 2019: IEEE, pp. 77-81 .
    8. Z. Mishra, A. Ganegoda, J. Selicha, Z. Wang, S. R. Sadda, and Z. Hu, "Automated Retinal Layer
    Segmentation Using Graph-based Algorithm Incorporating Deep-learning-derived Information,"
    Scientific Reports, vol. 10, no. 1, pp. 1-8, 2020, doi: 10.1038/s41598-020-66355-5.
    9. Y. He, A. Carass, Y. Liu, B. M. Jedynak, S .D. Solomon, S. Saidha, P. A. Calabresi, and J. L.
    Prince, "Deep learning based topology guaranteed surface and MME segmentation of multiple
    sclerosis subjects from retinal OCT," Biomedical optics express, vol. 10, no. 10, pp. 5042-5058,
    2019, doi: 10.1364/BOE.10.005042.
    10. D. Lu, M. Heisler, S. Lee, G. W. Ding, E. Navajas, M. V. Sarunic, and M. F. Beg, "Deeplearning based multiclass retinal fluid segmentation and detection in optical coherence tomography
    images using a fully convolutional neural network," Medical image analysis, vol. 54, pp. 100-110,
    2019, doi: 10.1016/j.media.2019.02.011.
  2. 11. Z. Wang, Y. Zhong, M. Yao, Y. Ma, W. Zhang, C. Li, Z. Tao, Q. Jiang et al., "Automated
    segmentation of macular edema for the diagnosis of ocular disease using deep learning method,"
    Scientific Reports, vol. 11, no. 1, pp. 1-12, 2021, doi: 10.1038/s41598-021-92458-8.
    12. K. Alsaih, M. Z. Yusoff, T. B. Tang, I. Faye, and F. Mériaudeau, "Deep learning architectures
    analysis for age-related macular degeneration segmentation on optical coherence tomography scans,"
    Computer methods and programs in biomedicine, vol. 195, p. 105566, 2020, doi:
    10.1016/j.cmpb.2020.105566.
    13. M. Pekala, N. Joshi, T. A. Liu, N. M. Bressler, D. C. DeBuc, and P. Burlina, "Deep learning
    based retinal OCT segmentation," Computers in biology and medicine, vol. 114, p. 103445, 2019,
    doi: 10.1016/j.compbiomed.2019.103445.
    14. J. Kugelman, D. Alonso-Caneiro, Y. Chen, S. Arunachalam, D. Huang, N. Vallis, M. J. Collins,
    and F. K. Chen, "Retinal boundary segmentation in stargardt disease optical coherence tomography
    images using automated deep learning," Translational vision science & technology, vol. 9, no. 11, pp.
    12-12, 2020, doi: 10.1167/tvst.9.11.12.
    15. P. Serranho, C. Maduro, T. Santos ,J. Cunha-Vaz, and R. Bernardes, "Synthetic oct data for
    image processing performance testing," in 2011 18th IEEE International Conference on Image
    Processing, 2011: IEEE, pp. 401-404 .
    16. E. S. Varnousfaderani, W.-D. Vogl, J. Wu, B. S. Gerendas, C. Simader, G. Langs, S. M.
    Waldstein, and U. Schmidt-Erfurth, "Improve synthetic retinal OCT images with present of
    pathologies and textural information," in Medical Imaging 2016: Image Processing, 2016, vol. 9784:
    International Society for Optics and Photonics, p. 97843V .
    17. P. Kulkarni, D. Lozano, G. Zouridakis, and M. Twa, "A statistical model of retinal optical
    coherence tomography image data," in 2011 Annual International Conference of the IEEE
    Engineering in Medicine and Biology Society, 2011: IEEE ,pp. 6127-6130 .
    18. A. Montuoro, S. M. Waldstein, B. Gerendas, G. Langs, C. Simader, and U. Schmidt-Erfurth,
    "Statistical retinal OCT appearance models," Investigative ophthalmology & visual science, vol. 55,
    no. 13, pp. 4808-4808, 2014.
    19. H. Danesh ,K. Maghooli, A. Dehghani, and R. Kafieh, "Automatic production of synthetic
    labelled OCT images using an active shape model," IET Image Processing, vol. 14, no. 15, pp. 3812-
    3818, 2020, doi: 10.1049/iet-ipr.2020.0075.
    20. S. J. Chiu, J. A. Izatt, R. V. O'Connell, K. P. Winter, C. A. Toth, and S. Farsiu, "Validated
    automatic segmentation of AMD pathology including drusen and geographic atrophy in SD-OCT
    images," Investigative ophthalmology & visual science, vol. 53, no. 1, pp. 53-61, 2012.
    21. B. E. Cootes T, Graham J. , "An introduction to active shape models," Image processing and
    analysis, vol. 223-48., 2000.
    22. T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham, "Active shape models-their training and
    application," Computer vision and image understanding, vol. 61, no. 1, pp. 38-59, 1995.
    23. J. C. Gower, "Generalized procrustes analysis," Psychometrika, vol. 40, no. 1, pp. 33-51, 1975.
    24. R. Reris and J. P. Brooks, "Principal component analysis and optimization: A tutorial," 2015.
    25. G. Hamarneh, R. Abu-Gharbieh, T. Gustavsson, and R. Abu-gharbieh, "Active shape modelspart i: Modeling shape and gray level variations," 1998.
مجله دانشکده پزشکی دانشگاه علوم پزشکی مشهد
دوره 65، شماره 2
خرداد و تیر 1401
صفحه 493-504

فایل ها

هم رسانی

ارجاع به این مقاله

آمار