Juvenile Refractive Power Prediction Based on Corneal Curvature and Axial Length via a Domain Knowledge Embedding Network

Zhang，Yang1,2; Higashita，Risa1,3; Xu，Yanwu4; Santo，Daisuke3; Hu，Yan1; Long，Guodong2; Liu，Jiang1,4,5,6

10.1007/978-3-030-87000-3_10

2021

0302-9743

1611-3349

LECT NOTES ARTIF INT

12970 LNCS

92-100

Traditional cycloplegic refractive power detection with specific lotions dropping may cause side-effects, e.g., the pupillary retraction disorder, on juvenile eyes. In this paper, we develop a novel neural network algorithm to predict the refractive power, which is assessed by the Spherical Equivalent (SE), using real-world clinical non-cycloplegic refraction records. Participants underwent a comprehensive ophthalmic examination to obtain several related parameters, including sphere degree, cylinder degree, axial length, flat keratometry, and steep keratometry. Based on these quantitative biomedical parameters, a novel neural network model is trained to predict the SE. On the whole age test dataset, the domain knowledge embedding network (DKE-Net) prediction accuracies of SE achieve 59.82% (between ± 0.5 D ), 86.85% (between ± 1 D ), 95.54% (between ± 1.5 D ), and 98.57% (between ± 2 D ), which demonstrate superior performance over conventional machine learning algorithms on real-world clinical electronic refraction records. Also, the SE prediction accuracies on the excluded examples that are disqualified for model training, are 2.16% (between ± 0.5 D ), 3.76% (between ± 1 D ), 6.15% (between ± 1.5 D ), and 8.78% (between ± 2 D ). This is the leading application to predict refraction power using a neural network and domain knowledge, to the best of our knowledge, with a satisfactory accuracy level. Moreover, the model can also assist in diagnosing some specific kinds of ocular disorders.

Neural network Non-cycloplegic detection Refractive power prediction

第一 ; 通讯

英语

EI

20213910959244

Bioinformatics ; Diagnosis ; Embeddings ; Forecasting ; Machine learning ; Medical computing ; Neural networks ; Refraction ; Statistical tests

Biomedical Engineering:461.1 ; Medicine and Pharmacology:461.6 ; Bioinformatics:461.8.2 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Mathematical Statistics:922.2

2-s2.0-85115861198

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.University of Technology Sydney,Sydney,Australia
3.Tomey Corporation,Nagoya,Japan
4.Cixi Institute of Biomedical Engineering,Chinese Academy of Sciences,Beijing,China
5.Research Institute of Trustworthy Autonomous Systems,Southern University of Science and Technology,Shenzhen,China
6.Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation,Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China

Zhang，Yang,Higashita，Risa,Xu，Yanwu,et al. Juvenile Refractive Power Prediction Based on Corneal Curvature and Axial Length via a Domain Knowledge Embedding Network[C],2021:92-100.