Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method
© 2022. The Author(s)..
BACKGROUND: The evaluation of refraction is indispensable in ophthalmic clinics, generally requiring a refractor or retinoscopy under cycloplegia. Retinal fundus photographs (RFPs) supply a wealth of information related to the human eye and might provide a promising approach that is more convenient and objective. Here, we aimed to develop and validate a fusion model-based deep learning system (FMDLS) to identify ocular refraction via RFPs and compare with the cycloplegic refraction. In this population-based comparative study, we retrospectively collected 11,973 RFPs from May 1, 2020 to November 20, 2021. The performance of the regression models for sphere and cylinder was evaluated using mean absolute error (MAE). The accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and F1-score were used to evaluate the classification model of the cylinder axis.
RESULTS: Overall, 7873 RFPs were retained for analysis. For sphere and cylinder, the MAE values between the FMDLS and cycloplegic refraction were 0.50 D and 0.31 D, representing an increase of 29.41% and 26.67%, respectively, when compared with the single models. The correlation coefficients (r) were 0.949 and 0.807, respectively. For axis analysis, the accuracy, specificity, sensitivity, and area under the curve value of the classification model were 0.89, 0.941, 0.882, and 0.814, respectively, and the F1-score was 0.88.
CONCLUSIONS: The FMDLS successfully identified the ocular refraction in sphere, cylinder, and axis, and showed good agreement with the cycloplegic refraction. The RFPs can provide not only comprehensive fundus information but also the refractive state of the eye, highlighting their potential clinical value.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:21 |
|---|---|
| Enthalten in: |
Biomedical engineering online - 21(2022), 1 vom: 17. Dez., Seite 87 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zou, Haohan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Cycloplegic refraction |
|---|
| Anmerkungen: |
Date Completed 20.12.2022 Date Revised 21.12.2022 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1186/s12938-022-01057-9 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM350404321 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM350404321 | ||
| 003 | DE-627 | ||
| 005 | 20231226044918.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s12938-022-01057-9 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1167.xml |
| 035 | |a (DE-627)NLM350404321 | ||
| 035 | |a (NLM)36528597 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zou, Haohan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 20.12.2022 | ||
| 500 | |a Date Revised 21.12.2022 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2022. The Author(s). | ||
| 520 | |a BACKGROUND: The evaluation of refraction is indispensable in ophthalmic clinics, generally requiring a refractor or retinoscopy under cycloplegia. Retinal fundus photographs (RFPs) supply a wealth of information related to the human eye and might provide a promising approach that is more convenient and objective. Here, we aimed to develop and validate a fusion model-based deep learning system (FMDLS) to identify ocular refraction via RFPs and compare with the cycloplegic refraction. In this population-based comparative study, we retrospectively collected 11,973 RFPs from May 1, 2020 to November 20, 2021. The performance of the regression models for sphere and cylinder was evaluated using mean absolute error (MAE). The accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and F1-score were used to evaluate the classification model of the cylinder axis | ||
| 520 | |a RESULTS: Overall, 7873 RFPs were retained for analysis. For sphere and cylinder, the MAE values between the FMDLS and cycloplegic refraction were 0.50 D and 0.31 D, representing an increase of 29.41% and 26.67%, respectively, when compared with the single models. The correlation coefficients (r) were 0.949 and 0.807, respectively. For axis analysis, the accuracy, specificity, sensitivity, and area under the curve value of the classification model were 0.89, 0.941, 0.882, and 0.814, respectively, and the F1-score was 0.88 | ||
| 520 | |a CONCLUSIONS: The FMDLS successfully identified the ocular refraction in sphere, cylinder, and axis, and showed good agreement with the cycloplegic refraction. The RFPs can provide not only comprehensive fundus information but also the refractive state of the eye, highlighting their potential clinical value | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Cycloplegic refraction | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Fusion model | |
| 650 | 4 | |a Ocular refraction | |
| 650 | 4 | |a Retinal fundus photographs | |
| 650 | 7 | |a Mydriatics |2 NLM | |
| 700 | 1 | |a Shi, Shenda |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Xiaoyan |e verfasserin |4 aut | |
| 700 | 1 | |a Ma, Jiaonan |e verfasserin |4 aut | |
| 700 | 1 | |a Fan, Qian |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Xuan |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Yibing |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Mingdong |e verfasserin |4 aut | |
| 700 | 1 | |a Song, Jiaxin |e verfasserin |4 aut | |
| 700 | 1 | |a Jiang, Yanglin |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Lihua |e verfasserin |4 aut | |
| 700 | 1 | |a He, Xin |e verfasserin |4 aut | |
| 700 | 1 | |a Jhanji, Vishal |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Shengjin |e verfasserin |4 aut | |
| 700 | 1 | |a Song, Meina |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Yan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Biomedical engineering online |d 2002 |g 21(2022), 1 vom: 17. Dez., Seite 87 |w (DE-627)NLM122241584 |x 1475-925X |7 nnns |
| 773 | 1 | 8 | |g volume:21 |g year:2022 |g number:1 |g day:17 |g month:12 |g pages:87 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1186/s12938-022-01057-9 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 21 |j 2022 |e 1 |b 17 |c 12 |h 87 | ||