پلتفرم انتخاب رینگ برای درمان قوز قرنیه

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده‌ی مهندسی مکانیک، دانشگاه صنعتی شریف، تهران، ایران.

چکیده

در پژوهش حاضر، در ابتدا مدل قرنیه‌ی یک بیمار با استفاده از داده­های چشم­پزشکی تهیه شده است. پس از تخصیص خواص مکانیکی، عمل شبیه­سازی کاشت رینگ درون قرنیه با متغیر درنظرگرفتن عوامل: شعاع رینگ، زاویه‌ی رینگ، ارتفاع کاشت رینگ، و منطقه‌ی کاشت رینگ و به تعداد 288 شبیه‌سازی انجام شده است. در ادامه، به کمک الگوریتم ژنتیک و استخراج ضرایب زرنیکه، پارامترهای مربوط به کیفیت دید برای هر حالت شبیه­سازی به‌دست آمده است. سپس با استفاده از دو الگوریتم جنگل تصادفی و یادگیری عمیق، داده­ها را آموزش داده و پلتفرمی ایجاد شده است که بتواند برای چشم همان بیمار، نتیجه‌ی عمل جراحی را با تغییر هر یک از عوامل پیش­بینی کند. پارامترهای میانگین مربعات خطا، جذر میانگین مربعات خطا، و ضریب تعیین برای هر حالت گزارش شده ­است. همچنین، درستی پیش­بینی داده­های آموزش‌یافته بر روی یک مدل خاص بررسی شده است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

A Ring Selection Platform for Treatment of Keratoconus

نویسندگان [English]

  • Amirhossein Khademi
  • Mohsen Asghari
  • Mohammad Reza Naderi Eshkaftaki
Faculty of Mechanical Engineering, Sharif University of Technology, Tehran, Iran.
چکیده [English]

This study presents a fully integrated platform for selecting appropriate intrastromal corneal ring segments (ICRS) for keratoconus treatment using a combination of finite element modeling and machine-learning techniques. A patient-specific corneal geometry was reconstructed using Pentacam-derived elevation maps, followed by meshing and biomechanical simulation of ring implantation at various depths and angular positions. Optical parameters of the cornea were calculated using curvature-based relationships (Eqs. (3)–(4)). A comprehensive database of 288 simulated ring-implantation scenarios was generated by varying Ring radius, Implantation depth, ring implantation zone, and arc length (Fig. 7). To predict keratometric outcomes, a random forest regression model and a deep learning architecture were developed and trained on the simulation-derived dataset. Model validation demonstrated acceptable accuracy using an independent rectangular-groove benchmark (Fig. 8). The trained algorithms were finally tested on a separate patient to evaluate generalization capacity. The results indicate that machine-learning prediction of ring-induced corneal response is feasible and can support treatment planning. This platform provides a foundation for developing preoperative decision-support tools to enhance clinical outcomes in keratoconus ring implantation.

کلیدواژه‌ها [English]

  • Keratoconus
  • intrastromal corneal ring segment implantation
  • machine learning
  • random forest algorithm
  • deep learning algorithm

مراجع

1. Whitcher, J.P., Srinivasan, M. and Upadhyay, M.P., 2001. Corneal blindness: a global perspective. Bulletin of the World Health Organization, 79(3), pp. 214-21. https://doi.org/10.1590/S004296862001000300009
2. Sharif, R., Bak-Nielsen, S., Hjortdal, J. and Karamichos, D., 2018. Pathogenesis of Keratoconus: The intriguing therapeutic potential of Prolactin-inducible protein. Progress in Retinal and Eye Research, 67, pp. 150-167. https://doi.org/10.1016/j.preteyeres.2018.05.002
3. Onkar, A., 2020. Commentary: Tackling the corneal foreign body. Indian Journal of Ophthalmology, 68(1), pp. 57-58. https://doi.org/10.4103/ijo.IJO_1625_19
4. Buzzonetti, L., Bohringer, D., Liskova, P., Lang, S. and Valente, P., 2020. Keratoconus in Children: A Literature Review. Cornea, 39(12), pp. 1592-1598. https://doi.org/10.1097/ico.0000000000002420
5. Röck, T., Bartz-Schmidt, K.U. and Röck, D., 2018. Trends in corneal transplantation at the University Eye Hospital in Tübingen, Germany over the last 12 years: 2004 - 2015. PLoS One, 13(6). https://doi.org/10.1371/journal.pone.0198793
6. Xu, H., Wen, Y., Zheng, H., Jiang, D. and Chen, W., 2024. Allergic disease and keratoconus: A two-sample univariable and multivariable Mendelian randomization study. World Allergy Organization Journal, 17(12), pp. 100993. https://doi.org/https://doi.org/10.1016/j.waojou.2024.100993
7. Abadou, J., Dahan, S., Knoeri, J., Leveziel, L., Bouheraoua, N. and Borderie, V.M., 2024. Artificial intelligence versus conventional methods for RGP lens fitting in keratoconus. Contact Lens and Anterior Eye, pp. 102321. https://doi.org/https://doi.org/10.1016/j.clae.2024.102321
8. Suzaki, A., Koh, S., Maeda, N., Asonuma, S., Santodomingo-Rubido, J., Oie, Y., Soma, T., Fujikado, T. and Nishida, K., 2021. Optimizing correction of coma aberration in keratoconus with a novel soft contact lens. Contact Lens and Anterior Eye, 44(4), pp. 101405. https://doi.org/https://doi.org/10.1016/j.clae.2020.12.071
9. Schirmbeck, T., Paula, J.S., Martin, L.F., Crósio Filho, H. and Romão, E., 2005. [Efficacy and low cost in keratoconus treatment with rigid gas-permeable contact lens]. Arquivos Brasileiros de Oftalmologia, 68(2), pp. 219-22. https://doi.org/10.1590/s0004-27492005000200012
10. Javadi, M.A., Motlagh, B.F., Jafarinasab, M.R., Rabbanikhah, Z., Anissian, A., Souri, H. and Yazdani, S., 2005. Outcomes of penetrating keratoplasty in keratoconus. Cornea, 24(8), pp. 941-6. https://doi.org/10.1097/01.ico.0000159730.45177.cd
11. Poulsen, D.M. and Kang, J.J., 2015. Recent advances in the treatment of corneal ectasia with intrastromal corneal ring segments. Current Opinion in Ophthalmology, 26(4), pp. 273-7. https://doi.org/10.1097/icu.0000000000000163
12. Lago, M.A., Rupérez, M.J., Monserrat, C., Martínez-Martínez, F., Martínez-Sanchis, S., Larra, E., Díez-Ajenjo, M.A. and Peris-Martínez, C., 2015. Patient-specific simulation of the intrastromal ring segment implantation in corneas with keratoconus. Journal of the Mechanical Behavior of Biomedical Materials, 51, pp. 260-268. https://doi.org/https://doi.org/10.1016/j.jmbbm.2015.07.023
13. Flecha-Lescún, J., Calvo, B., Zurita, J. and Ariza-Gracia, M., 2018. Template-based methodology for the simulation of intracorneal segment ring implantation in human corneas. Biomechanics and Modeling in Mechanobiology, 17(4), pp. 923-938. https://doi.org/10.1007/s10237-018-1013-z
14. Kaczmarczyk, K. and Miałkowska, K., 2022. Backtesting comparison of machine learning algorithms with different random seed. Procedia Computer Science, 207, pp. 1901-1910. https://doi.org/https://doi.org/10.1016/j.procs.2022.09.248
15. Rao, A., Chen, T., Liu, Y. and Ma, F., 2023. Computational analysis of performances for a hydrogen enriched compressed natural gas engine’ by advanced machine learning algorithms. Fuel, 347, pp. 128244. https://doi.org/https://doi.org/10.1016/j.fuel.2023.128244
16. Yoosefzadeh-Najafabadi, M., Earl, H.J., Tulpan, D., Sulik, J. and Eskandari, M., 2020. Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean. Frontiers in Plant Science, 11, pp. 624273. https://doi.org/10.3389/fpls.2020.624273
17. La Moglia, A. and Mohamad Almustafa, K., 2024. Breast Cancer Prediction Using Machine Learning Classification Algorithms. Intelligence-Based Medicine, pp. 100193. https://doi.org/https://doi.org/10.1016/j.ibmed.2024.100193
18. Cortes, C. and Vapnik, V., 1995. Support-vector networks. Machine Learning, 20(3), pp. 273-297. https://doi.org/10.1007/BF00994018
19. Valdés-Mas, M.A., Martín-Guerrero, J.D., Rupérez, M.J., Pastor, F., Dualde, C., Monserrat, C. and Peris-Martínez, C., 2014. A new approach based on Machine Learning for predicting corneal curvature (K1) and astigmatism in patients with keratoconus after intracorneal ring implantation. Computer Methods and Programs in Biomedicine, 116(1), pp. 39-47. https://doi.org/10.1016/j.cmpb.2014.04.003
20. Ting, D.S.J., Foo, V.H., Yang, L.W.Y., Sia, J.T., Ang, M., Lin, H., Chodosh, J., Mehta, J.S. and Ting, D.S.W., 2021. Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology. British Journal of Ophthalmology, 105(2), pp. 158-168. https://doi.org/10.1136/bjophthalmol-2019-315651
21. Sekhar, C.R., Minal and Madhu, E., 2016. Mode Choice Analysis Using Random Forrest Decision Trees. Transportation Research Procedia, 17, pp. 644-652. https://doi.org/https://doi.org/10.1016/j.trpro.2016.11.119
22. Akinrinade, O. and Du, C., 2024. Skin Cancer Detection Using Deep Machine Learning Techniques. Intelligence-Based Medicine, pp. 100191. https://doi.org/https://doi.org/10.1016/j.ibmed.2024.100191
23. Liu, M., He, Y. and Ye, B., 2007. Image Zernike moments shape feature evaluation based on image reconstruction. Geo-spatial Information Science, 10(3), pp. 191-195. https://doi.org/10.1007/s11806-007-0060-x
24. Yuan, F., Sun, Y., Han, Y., Chu, H., Ma, T. and Shen, H., 2024. Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials. Sensors (Basel), 24(2). https://doi.org/10.3390/s24020698

فایل ها

هم رسانی

ارجاع به این مقاله

آمار