将机器学习技术应用于眼内镜片光学倍率的预 测:诊断数据的归纳
- 作者: Arzamastsev A.А.1,2, Fabrikantov O.L.2, Zenkova N.А.3, Belikov S.V.2
-
隶属关系:
- Voronezh State University
- The S. Fyodorov Eye Microsurgery Federal State Institution
- Derzhavin Tambov State University
- 期: 卷 5, 编号 1 (2024)
- 页面: 53-63
- 栏目: 原创性科研成果
- URL: https://journals.rcsi.science/DD/article/view/262957
- DOI: https://doi.org/10.17816/DD623995
- ID: 262957
如何引用文章
详细
论证。现代眼内镜片的植入使眼科医生能够有效解决白内障患者的手术康复难题。患者视觉功能的改善程度与术前计算眼内镜片光学倍率的准确性直接相关。SRK II、SRK/T、Hoffer-Q、Holladay II、 Haigis、Barrett等公式都被用来计算这一指数。所有这些公式对于“中等症患者”来说都很有效。但是,在输入变量范围的极端情况下,它们就不够充分。
目的。本研究的目的是探索使用人工神经网络深度学习衍生的数学模型来归纳数据并预测现代眼内镜片光学倍率的可能性。
材料与方法。基于人工神经网络的模型训练是在大规模样本上进行的,包括来自眼科诊所患者的匿名数据。这些数据由眼科医生K.K.谢雷赫于2021年提供。这些数据反映了患者术前和术后的观察结果。用于建立基于人工神经网络模型的源文件包括455条记录(26列输入因子和1列输出因子),被用于计算眼内镜片(屈光度)。为了方便地建立模型,使用了先前开发的一个模拟程序。
结果。与传统的公式相比,所获得的模型更能反映患者的区域特性。它们还可以根据新获得的数据重新训练和优化模型结构。这样就有可能考虑到对象的非稳定性。与白内障手术中广泛使用的已知公式相比,这种基于人工神经网络模型的一个显著特点是可以考虑大量记录的输入值。这使得计算眼内镜片光学倍率的平均相对误差可以从10-12%降低到3.5%。
结论。本项研究表明,使用人工神经网络模型的深度学习来归纳大量经验数据来计算人工晶状体的光学强度是基本可行的。与使用传统公式和方法相比,这种网络的输入变量数量要大得多。所得结果使得构建新数据动态输入、模型逐步再训练的智能专家系统成为可能。
作者简介
Alexander А. Arzamastsev
Voronezh State University; The S. Fyodorov Eye Microsurgery Federal State Institution
Email: arz_sci@mail.ru
ORCID iD: 0000-0001-6795-2370
SPIN 代码: 4410-6340
Dr. Sci. (Engineering), Professor
俄罗斯联邦, Voronezh; TambovOleg L. Fabrikantov
The S. Fyodorov Eye Microsurgery Federal State Institution
Email: fabr-mntk@yandex.ru
ORCID iD: 0000-0003-0097-991X
SPIN 代码: 9675-9696
MD, Dr. Sci. (Medicine), Professor
俄罗斯联邦, TambovNatalia А. Zenkova
Derzhavin Tambov State University
Email: natulin@mail.ru
ORCID iD: 0000-0002-2325-1924
SPIN 代码: 2266-4168
Cand. Sci. (Psychology), Assistant Professor
俄罗斯联邦, TambovSergey V. Belikov
The S. Fyodorov Eye Microsurgery Federal State Institution
编辑信件的主要联系方式.
Email: pvt.leopold@gmail.com
ORCID iD: 0000-0002-4254-3906
SPIN 代码: 5553-8398
MD
俄罗斯联邦, Tambov参考
- Fyodorov SN, Kolinko AI. Method of calculating the optical power of an intraocular lens. The Russian Annals of Ophthalmology. 1967;(4):27–31. (In Russ).
- Balashevich LI, Danilenko EV. Results in application of the fyodorov’s iol power formula for posterior chamber lenses calculation. Fyodorov Journal of Ophthalmic Surgery. 2011;(1):34–38. EDN: PXRASV
- Sanders DR, Kraff MC. Improvement of intraocular lens power calculation using empirical data. American Intra-Ocular Implant Society Journal. 1980;6:263–267. doi: 10.1016/s0146-2776(80)80075-9
- Sanders DR, Retzlaff JA, Kraff MC. Comparison of the SRK II formula and other second-generation formulas. Journal of Cataract & Refractive Surgery. 1988;14(2):136–141. doi: 10.1016/s0886-3350(88)80087-7
- Sanders DR, Retzlaff JA, Kraff MC. Development of the SRK/T IOL power calculation formula. Journal of Cataract & Refractive Surgery. 1990;16(3):333–340. doi: 10.1016/s0886-3350(13)80705-5
- Hoffer KJ. The Hoffer Q formula: a comparison of theoretic and regression formulas. Journal of Cataract & Refractive Surgery. 1993;19(6):700–712. doi: 10.1016/s0886-3350(13)80338-0
- Holladay JT, Prager TC, Ruiz RS, et al. A three-part system for refining intraocular lens power calculation. Journal of Cataract & Refractive Surgery. 1988;14(1):17–24. doi: 10.1016/S0886-3350(88)80059-2
- Pershin KB, Pashinova NF, Tsygankov AYu, Legkhih SL. Choice of IOL Optic Power Calculation Formula in Extremely High Myopia Patients “Excimer” Ophthalmology Centre, Moscow. Point of view. East - West. 2016;(1):64–67. EDN: WHCNPF
- Buduma N, Lokasho N. Foundations of deep learning. Creating Algorithms for Next Generation Artificial Intelligence. Moscow: Mann, Ivanov i Ferber; 2020. (In Russ).
- Foster D. Generative deep learning. Creative potential of neural networks. Saint Petersburg: Piter; 2020. (In Russ).
- Ramsundar B, Istman P, Uolters P, Pande V. Deep learning in biology and medicine. Moscow: DMK Press; 2020. (In Russ).
- Kharrison M. Machine learning: a pocket guide. A quick guide to structured machine learning methods in Python. Saint Petersburg: Dialektika LLC; 2020. (In Russ).
- Arzamastsev AA, Fabrikantov OL, Zenkova NA, Belousov NK. Optimization of Formulae for Intraocular Lenses Calculating. Tambov University Reports. Series: Natural and Technical Sciences. 2016;21(1):208–213. EDN: VNWHVZ doi: 10.20310/1810-0198-2016-21-1-208-213
- Yamauchi T, Tabuchi T, Takase K, Masumoto H. Use of a machine learning method in predicting refraction after cataract surgery. Journal of Clinical Medicine. 2021;10(5):1103. doi: 10.3390/jcm10051103
- Certificate of state registration of the computer program № 2012618141/ 07.09.2012. Arzamastsev AA, Rykov VP, Kryuchin OV. Artificial neural network simulator with implementation of modular learning principle. (In Russ).
- Kolmogorov AN. On the representation of continuous functions of several variables by superpositions of continuous functions of fewer variables. Doklady Akademii nauk SSSR. 1956;108(2):179–182. (In Russ).
- Kolmogorov AN. On the representation of continuous functions of several variables as a superposition of continuous functions of one variable. Doklady Akademii nauk SSSR. 1957;114(5):953–956. (In Russ).
- Arzamaszev AA, Kryuchin OV, Azarova PA, Zenkova NA. The universal program complex for computer simulation on the basis of the artificial neuron network with self-organizing structure. Tambov University Reports. Series: Natural and Technical Sciences. 2006;11(4):564–570. EDN: IRMPYX
- Arzamastsev AA, Zenkova NA, Kazakov NA. Algorithms and methods for extracting knowledge about objects defined by arrays of empirical data using ANN models. Journal of Physics: Conference Series. 2021. doi: 10.1088/1742-6596/1902/1/012097