Research on the correlation between retinal vascular parameters and axial length in children using an AI-based fundus image analysis system

Chaoyang Zhao; Huilin Li; Ziyou Yuan; Zihan Yang; Tiantian Wang; Yan Wang; Qian Tong; Shaofeng Hao

doi:10.1371/journal.pone.0324352

. 2025 Jun 17;20(6):e0324352. doi: 10.1371/journal.pone.0324352

Research on the correlation between retinal vascular parameters and axial length in children using an AI-based fundus image analysis system

Chaoyang Zhao ^1,^2,^‡, Huilin Li ^1,^‡, Ziyou Yuan ¹, Zihan Yang ^1,², Tiantian Wang ^1,², Yan Wang ^1,², Qian Tong ³, Shaofeng Hao ^1,^*

Editor: Xu Yanwu⁴

PMCID: PMC12173413 PMID: 40526760

Abstract

Objective

This study aims to utilize artificial intelligence technology to conduct an in-depth analysis of fundus data from myopic children and adolescents, thoroughly exploring the correlation between retinal vascular parameters and axial length (AL), and ultimately revealing the changing patterns of retinal vascular characteristics in children with different refractive errors. The findings aim to provide a scientific basis for the prevention, early screening, and formulation of personalized treatment strategies for myopia.

Methods

The study selected 124 students from Jiandong Primary School in Changzhi City who underwent myopia prevention and control screening. Their axial length data were recorded, and fundus photographs were taken using the Topcon TNF506 non-mydriatic fundus camera. Subsequently, these fundus images were meticulously analyzed using the EVision AI fundus image analysis system, which is a commercial software that employs pre-trained algorithms to automatically extract retinal vascular parameters.Pearson and Spearman correlation coefficients were used to analyze the correlation between retinal vascular parameters and axial length, and multiple linear regression analysis was further conducted to explore their intrinsic associations.

Results

The study found that in the low myopia group, axial length was significantly negatively correlated with various retinal vascular parameters, including the average diameters of arteries and veins, average vascular tortuosity, atrophy arc area, and leopard spot density. In the moderate to high myopia group, axial length also showed significant negative correlations with the average diameter of arteries, some average venous tortuosity, and average vascular diameter. However, fractal dimension of vessels and average branch angle did not show significant changes across all myopia groups.

Conclusion

This study clearly demonstrates a significant correlation between axial length and retinal vascular parameters, with notable differences in this correlation among children with different refractive errors. These findings not only provide a new perspective for understanding the pathological mechanisms of myopia but also offer important scientific evidence for the development of more precise and personalized myopia prevention and control strategies in the future. They have potential guiding significance for clinical practice and policy formulation.

1. Introduction

Myopia is a common refractive error primarily caused by an excessive axial length (Axial Length, AL) that mismatches with the refractive system, leading to the focusing of parallel light rays anterior to the retina and resulting in blurred distant vision [1,2]. In recent years, myopia has emerged as a significant global public health issue, with predictions indicating that nearly half of the world’s population will be affected by 2050 [3]. Particularly alarming is the rising incidence of myopia, with a younger age of onset and a substantial increase in the prevalence of early-onset myopia among children and adolescents, further exacerbating the risk of high myopia [4]. AL plays a central role in the development and progression of myopia, with numerous studies showing that an increase in AL is one of the primary drivers of myopia onset and progression [5]. An excessively long eye axis can cause overstretching of ocular tissues such as the retina, choroid, and sclera, potentially leading to a series of ocular pathological changes [6]. Importantly, the rate of AL growth is closely related to the progression of myopia, especially in children and adolescents, where rapid AL growth is a major risk factor for the development of high myopia [7]. Patients with high myopia have an AL significantly beyond the normal range, which may induce severe complications such as retinal detachment [8], glaucoma [9], macular degeneration [10], and choroidal neovascularization [11], ultimately leading to severe visual impairment or even blindness. Therefore, monitoring and controlling AL growth is crucial for the prevention and control of myopia.

The retinal microvascular system, as the only directly observable vascular network in the human body, provides a unique perspective for studying ocular and systemic diseases [12]. By observing and quantifying morphological and functional characteristics of retinal vessels, such as vessel diameter, fractal dimension (Fractal Dimension, FD), vessel tortuosity, branch angle (Branch Angle, BA), and vascular density (Vascular Density, VD), it is possible to reveal changes in the retinal vascular network structure and provide reliable quantitative indicators for the study of various systemic diseases. Studies have confirmed that changes in retinal vessels are closely related to systemic diseases such as cognitive impairment [13], diabetes [14], multiple sclerosis [15], and coronary heart disease [16]. With the rapid development of fundus photography technology and its analysis software, the visualization and quantitative analysis of the retinal microvascular system are increasingly becoming important tools for disease research.

Despite studies exploring the relationship between retinal vascular parameters and certain ocular and systemic diseases, research on the relationship between myopia and retinal vascular parameters remains relatively scarce, especially in children and adolescents. Currently, there is a lack of in-depth and systematic research on how retinal vascular parameters change during the development of myopia and how these changes are correlated with axial length. Therefore, further exploration of the association between retinal vascular parameters and AL not only helps to reveal the pathological mechanisms of myopia but also may provide new pathways for developing more effective prevention and treatment strategies for myopia, especially in early intervention among children and adolescents. By accurately monitoring changes in retinal vascular parameters, it is possible to detect signs of myopia onset earlier and take timely measures to control its progression.

In this context, this study utilizes artificial intelligence technology to conduct in-depth analysis of fundus data from children and adolescents with myopia, aiming to explore the correlation between retinal vascular parameters and axial length. The findings are intended to provide a scientific basis for the prevention, early screening, and personalized treatment strategies for myopia. This study not only fills a gap in the current research field but also offers new perspectives and methods for the future prevention, control, and treatment of myopia.

2. Materials and methods

2.1. General information

This study employed a cross-sectional research design, including fifth and sixth graders who underwent myopia prevention and control screening at Jiandong Primary School in Changzhi City between June 1st and June 30th, 2023. Through random sampling, 150 students were selected for screening, and ultimately, 124 eligible students were identified as the study subjects based on inclusion and exclusion criteria. Among the study subjects, there were 61 males (49.2%) and 63 females (50.8%), aged 10–12 years, with a mean age of 11.16 ± 0.63 years. Axial length (AL) ranged from 20.18 to 27.60mm, averaging 23.95 ± 1.20mm. The spherical equivalent (SE) of the right eye ranged from -8.5 to +0.38D, averaging -1.98 ± 1.76D. This study strictly adhered to the principles of the Declaration of Helsinki and received approval from the Ethics Committee of Heji Hospital Affiliated to Changzhi Medical College (Ethical Approval Number: 202207).

2.2. Methods

2.2.1. Examination items and procedures.

Inclusion Criteria: (1) Age between 10 and 12 years; (2) Able to cooperate with ophthalmic examinations; (3) Clear fundus images; (4) Students and their guardians agree to undergo refractive and fundus examinations and sign the informed consent form.

Exclusion Criteria: (1) Unable to cooperate with ophthalmic examinations; (2) presence of organic ocular diseases; (3) recent history of ocular trauma; history of previous ocular surgery; (4) students or their guardians refusing refractive or fundus examinations or not signing the informed consent form.

Data collection included students’ basic information (e.g., age, gender) and comprehensive ophthalmic examination results. Ophthalmic examinations were conducted under non-mydriatic conditions using a desktop autorefractor (TOPCON RM-1). Those wearing glasses were measured after removing them. Each eye was measured three times, and the average was taken as the final result. If the difference between any two spherical power measurements was ≥ 0.50D, additional measurements were taken and averaged again. Fundus photography was performed using a high-vision Raymond TNF506 non-mydriatic fundus camera, capturing one 45° fundus color photograph centered on the macula for each eye of each subject. All image acquisitions were completed by uniformly trained and qualified technicians.

Based on the SE of the right eye, myopia was classified into three categories: normal group (0.5 D ≥ SE > -0.5 D, 27 individuals, 21.8%), low myopia group (-3.00 D < SE ≤ -0.5 D, 61 individuals, 49.2%), and moderate-to-high myopia group (SE ≤ -3.00 D, 36 individuals, 29.0%, including 32 with moderate myopia and 4 with high myopia).

2.2.2. Analysis of retinal vascular parameters based on artificial intelligence.

2.2.2.1. Imaging process: Ⅰ. Image Preprocessing. Establish Region of Interest (ROI): Extract the area of interest, typically the retinal region, from the original image.

Background and Non-retinal Area Removal: Utilize methods such as threshold segmentation or edge detection to eliminate background and other non-retinal areas.

Denoising: Apply low-pass filters or other denoising techniques to remove noise from the image [17].

Normalization: Adjust the image’s color, brightness, and size to ensure consistency for easier subsequent processing.

Enhancement: Use contrast-limiting adaptive histogram equalization (CLAHE) to enhance image contrast and highlight retinal features.

Ⅱ. Segmentation. Segmentation Model Application:

Retinal Vessel Segmentation: Apply the segmentation model to the preprocessed image to identify and segment blood vessels using EVision AI [18].

Refinement of Segmentation Results: Refine segmentation results using morphological operations.

Optic Disc Segmentation: Use polar coordinate transformation and edge detection to locate the optic disc boundary on the polar coordinate image. Subsequently, perform an inverse transformation in the Cartesian coordinate system to accurately position the optic disc boundary.

Ⅲ. Parameter Extraction. Vascular Feature Extraction: Calculate fractal dimension, average vessel diameter, tortuosity, and branching angle of the blood vessels. Extract vascular features using mathematical morphology and image processing techniques.

Quantitative Analysis: Convert the segmented vascular area into pixel-level labels for quantitative analysis. Use the box-counting method to calculate the fractal dimension of blood vessels.

Result Output: Output quantitative parameters of blood vessels, including fractal dimension, average vessel diameter, tortuosity, and branching angle.

2.2.2.2. Image analysis: Next, we will continue to use the artificial intelligence fundus image analysis system EVision AI [17] to conduct in-depth analysis of color fundus images centered on the macula. The analysis covered key indicators such as mean retinal artery diameter, mean retinal vein diameter, arteriovenous diameter ratio, mean artery tortuosity, mean vein tortuosity, mean vascular diameter, mean vascular tortuosity, vascular fractal dimension, mean vascular branching angle, atrophy arc area, and leopard spot density [19–22]. In addition to focusing on vascular parameters in the central macular area, we further analyzed vascular parameters in annular regions at different distances (0.5 to 1.0PD, 1.0 to 1.5PD, 1.5 to 2.0PD, 2.0 to 2.5PD) from the optic disc boundary.

For each measurement index, we provided clear definitions, such as the retinal vascular branching angle (the mean angle formed by the main vessel and branch vessels within 2.0 PD from the optic disc boundary, with larger angles potentially indicating abnormalities), vascular fractal dimension (an indicator assessing the complexity of the vascular network distribution, with higher values indicating more complex and refined distributions), and vascular tortuosity (an indicator reflecting the degree of bending or twisting of retinal vessels). The atrophy arc area represents degenerative changes in the retina or choroid, while leopard spot density reflects structural changes in the choroid and retina of the fundus, often associated with high myopia [23,24].

2.2.2.3. Morphological parameter measurement and recording: Finally, based on the analysis results of EVision AI, we accurately measured and recorded the morphological parameters of various fundus features. These parameters include but are not limited to vessel diameter, optic disc size, and vessel curvature, providing crucial data support for subsequent medical diagnosis and research.(Figs 1–5).

2.2.3. Data collection and sample size determination.

The sample size for this study was determined based on preliminary pilot experiment results and statistical power analysis, aiming to ensure sufficient statistical power to detect the expected effects. Subjects meeting the inclusion criteria were screened from fifth and sixth graders at Jiandong Primary School in Changzhi City through random sampling to ensure the representativeness and breadth of the sample.

2.2.4. Statistical analysis methods.

Statistical analysis was conducted using SPSS 25.0 software. First, the normality of quantitative data was tested using the Shapiro-Wilk test to determine the data distribution. For normally distributed data, the mean (± standard deviation, denoted as ±S) was used for description; for non-normally distributed data, the median (interquartile range, denoted as M(IQR)) was used.

For correlation analysis, based on the normality test results of the data, Pearson correlation coefficient (for normal data) and Spearman rank correlation coefficient (for non-normal data) were used to analyze the correlation between axial length (AL) and vascular parameters.

Furthermore, this study conducted multiple linear regression analysis to further explore the impact of leopard spot density and mean vascular tortuosity on axial length (AL). In this analysis, leopard spot density and mean vascular tortuosity were used as independent variables (predictors), while axial length (AL) was used as the dependent variable (response variable). The statistical significance level was set at P < 0.05, indicating that results were considered statistically significant when the P-value was less than 0.05.

3. Results

3.1. Basic information analysis of subjects

Comparisons across normal, low myopia, and moderate-to-high myopia groups revealed significant differences in age, right eye spherical equivalent (SE), and axial length (AL) (P < 0.05), but not in gender (P > 0.05) (Table 1).

Table 1. Comparison of Clinical Data Among Participants in the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

Related factors		Normal Group (n = 27)	Low Myopia Group (n = 61)	Moderate-to-High Myopia Group (n = 36)	F/χ²	P-value
Age (years, `x ± S)		10.78 ± 0.58	11.25 ± 0.57	11.31 ± 0.67	7.15	*0.001*
Gender(n, %)	Male	13.(48.15)	33, (54.10)	15, (41.67)	1.41	0.493
Gender(n, %)	Female	14, (51.85)	28, (45.90)	21, (58.33)
SE(D, `x ± S)		-0.11 ± 0.24	-1.51 ± 0.74	-4.18 ± 1.36	172.63	0.000
Axial Length(mm, x ± S)		23.36 ± 1.13	24.12 ± 1.16	24.12 ± 1.20	4.53	*0.013*

Open in a new tab

Note: SE - Spherical Equivalent; D - Diopter; x ± S - Mean ± Standard Deviation; F - F-statistic for ANOVA; χ²- Chi-square statistic for categorical variables; P-value - Significance level.

3.2. Univariate correlation analysis of axial length and retinal vascular parameters

3.2.1. Axial length and retinal vascular diameters.

In low myopia, AL negatively correlated with mean artery and vein diameters (including segment-specific measurements at 1.0–1.5PD, 1.5–2.0PD, 2.0–2.5PD for arteries; 0.5–1.0PD, 2.0–2.5PD for veins) and mean vascular diameter (P < 0.05). Similar correlations were observed in moderate-to-high myopia for mean artery diameters (all segments) and mean vascular diameter (P < 0.05) (Table 2).

Table 2. Comparison of Retinal Vessel Diameters and Axial Length Among the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

Retinal Vessel Diameter	Normal Group		Low Myopia Group		Moderate-to-High Myopia Group
	r-value	p-value	r-value	p-value	r-value	p-value
Arterial Average Diameter	-0.021	0.918	-0.366	*0.004*	-0.462	*0.005*
Average arterial diameter between 0.5–1.0 PD	0.226	0.257	-0.239	0.063	-0.417	*0.011*
Average arterial diameter between 1.0–1.5 PD	0.085	0.672	-0.292	*0.022*	-0.349	*0.037*
Average arterial diameter between 1.5–2.0 PD	0.079	0.695	-0.256	*0.046*	-0.346	*0.039*
Average arterial diameter between 2.0–2.5 PD	-0.166	0.408	-0.297	*0.020*	-0.409	*0.013*
Venous Average Diameter	-0.208	0.298	-0.326	*0.010*	-0.295	0.081
Average venous diameter between 0.5–1.0 PD	0.080	0.693	-0.290	*0.024*	-0.096	0.579
Average venous diameter between 1.0–1.5 PD	0.059	0.769	-0.225	0.081	-0.102	0.554
Average venous diameter between 1.5–2.0 PD	0.032	0.873	-0.043	0.741	-0.179	0.297
Average venous diameter between 2.0–2.5 PD	-0.158	0.431	-0.354	*0.005*	-0.229	0.179
Arteriovenous Diameter Ratio	0.197	0.325	-0.159	0.222	-0.124	0.472
Arteriovenous ratio between 0.5–1.0 PD	0.160	0.425	0.043	0.741	-0.267	0.116
Arteriovenous ratio between 1.0–1.5 PD	0.009	0.964	-0.054	0.677	-0.212	0.215
Arteriovenous ratio between 1.5–2.0 PD	-0.049	0.808	-0.200	0.123	-0.124	0.471
Arteriovenous ratio between 2.0–2.5 PD	0.008	0.968	0.031	0.810	0.045	0.796
Average Vessel Diameter	-0.109	0.588	-0.394	*0.002*	-0.414	*0.012*

Open in a new tab

Note: r-value - Correlation coefficient; p-value - Significance level; PD - Papillary Diameter.

3.2.2. Axial length and retinal vascular tortuosity.

In low myopia, AL negatively correlated with mean artery and vein tortuosity (including segment-specific values at 1.5–2.0PD) and mean vascular tortuosity (segments 0.5–1.0PD, 1.5–2.0PD) (P < 0.05). In moderate-to-high myopia, only mean vein tortuosity at 0.5–1.0PD showed a significant negative correlation (P < 0.05) (Table 3).

Table 3. Comparison of Retinal Vessel Tortuosity and Axial Length Among the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

Retinal Vessel Tortuosity	Normal Group		Low Myopia Group		Moderate-to-High Myopia Group
	r-value	p-value	r-value	p-value	r-value	p-value
Arterial Average Tortuosity	-0.099	0.623	-0.316	*0.013*	0.051	0.769
Arterial Average Tortuosity (0.5–1.0PD)	-0.159	0.427	-0.209	0.106	-0.101	0.556
Arterial Average Tortuosity (1.0–1.5PD)	-0.048	0.811	-0.234	*0.069*	-0.060	0.728
Arterial Average Tortuosity (1.5–2.0PD)	-0.034	0.868	-0.380	*0.003*	-0.037	0.830
Arterial Average Tortuosity (2.0–2.5PD)	-0.012	0.953	-0.156	0.229	-0.135	0.434
Venous Average Tortuosity	0.073	0.718	-0.272	0.034	-0.248	0.146
Venous Average Tortuosity (0.5–1.0PD)	0.348	0.075	-0.141	0.277	-0.394	*0.017*
Venous Average Tortuosity (1.0–1.5PD)	-0.129	0.520	-0.024	0.857	-0.191	0.265
Venous Average Tortuosity (1.5–2.0PD)	0.100	0.621	-0.292	*0.023*	-0.136	0.428
Venous Average Tortuosity (2.0–2.5PD)	0.010	0.962	-0.085	0.516	-0.213	0.212
Average Vessel Tortuosity	-0.020	0.923	-0.343	*0.007*	-0.181	0.290
Average Vessel Tortuosity (0.5–1.0PD)	0.182	0.363	-0.259	*0.044*	-0.225	0.186
Average Vessel Tortuosity (1.0–1.5PD)	-0.102	0.612	-0.225	0.082	-0.123	0.473
Average Vessel Tortuosity (1.5–2.0PD)	0.021	0.915	-0.412	*0.001*	-0.079	0.647
Average Vessel Tortuosity (2.0–2.5PD)	-0.005	0.978	-0.195	0.132	-0.236	0.166

Open in a new tab

Note: r-value - Correlation coefficient; p-value - Significance level; PD - Papillary Diameter.

3.2.3. Axial length and other retinal vascular parameters.

In low myopia, AL positively correlated with atrophy arc area and leopard spot density (P < 0.05), while vascular fractal dimension and branching angle did not vary significantly across groups (Table 4).

Table 4. Comparison of Other Retinal Vascular Parameters and Axial Length Among the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

Other Parameters	Normal Group		Low Myopia Group		Moderate-to-High Myopia Group
	r-value	p-value	r-value	p-value	r-value	p-value
Fractal Dimension	0.083	0.681	0.212	0.101	-0.185	0.280
Average Branching Angle	0.059	0.772	0.207	0.110	0.152	0.376
Peripapillary Atrophy Area	0.218	0.274	0.352	*0.005*	0.224	0.189
Fundus Tessellation Density	0.369	0.058	0.346	*0.006*	-0.035	0.838

Open in a new tab

Note: r-value - Correlation coefficient; p-value - Significance level.

3.3. Multiple linear regression analysis of axial length and retinal blood vessel parameters

Regression analysis indicated that a one-unit increase in tessellated fundus density correlated with a 9.743-unit increase in AL (B = 9.734, P = 0.013, 95% CI = 2.114–17.372). Conversely, a one-unit increase in mean vessel curvature correlated with a 20,646.382-unit decrease in AL (B = -20646.382, P = 0.045, 95% CI = -40777.161 to -515.602) (Table 5).

Table 5. Multiple Linear Regression Analysis of Axial Length and Retinal Vascular Parameters.

Variable	B-value	Standard Error	Standardized Coefficient β	t-value	P-value	95% Confidence Interval
Fundus Tessellation Density	9.743	3.841	0.301	2.536	*0.013*	2.114 ~ 17.372
Average Vascular Tortuosity	-20646.382	10135.904	-2.108	-2.037	*0.045*	-40777.161 ~ -515.602

Open in a new tab

Note: B-value - Regression coefficient; Standard Error - Standard error of the regression coefficient; β - Standardized regression coefficient; t-value - t-statistic; P-value - Significance level; 95% Confidence Interval - Confidence interval for the regression coefficient at the 95% level.

4. Discussion

4.1. Relationships between axial length and retinal vascular parameters

This study confirms a significant negative correlation between axial length (AL) and retinal vascular diameters, aligning with prior research in adults [25–27]. In low myopia, AL inversely correlated with artery and vein diameters, arteriovenous diameter ratio, and mean vascular diameter. This relationship likely stems from retinal thinning and stretching due to axial elongation, potentially representing a compensatory mechanism to maintain perfusion [28–31]. Retinal hypoxia, exacerbated by reduced blood flow velocity in myopia [32], may further contribute to ischemia, particularly in high myopia [33,34].

4.2. Vascular curvature and axial length

Abnormal vascular curvature, often linked to vascular dysfunction and blood-retina barrier damage [35,36], decreased with increasing AL in this study. This may reflect hypoxic adaptations from mechanical stretching during myopia progression [37,38], compromising retinal oxygenation and function [39].

4.3. Parafoveal atrophy, tessellated fundus, and axial length

AL positively correlated with parafoveal atrophy (PPA) area [21,40,41], attributed to retinal pigment epithelium and choroidal capillary loss in myopia [42–45]. Similarly, tessellated fundus density increased with AL, consistent with prior findings in Chinese adolescents [46,47], likely due to choroidal structural changes from axial elongation.

4.4. Fractal dimension, branching angle, and study limitations

No significant correlations were observed between AL and vascular fractal dimension or branching angle, possibly due to sample or methodological differences. Future research should explore these parameters in diverse populations.

4.5. Study limitations

Limitations include: (1) restricted vascular assessment from 45° macular-centered fundus images, necessitating wider-angle imaging for comprehensive evaluation; (2) cross-sectional design limiting causal inference, requiring longitudinal studies to clarify dynamic AL-vascular relationships; (3) small sample size, urging future research to include diverse age groups and myopia severities for broader generalizability; and (4) limited exploration of complex vascular parameters (e.g., fractal dimension, branching angle), warranting population-specific analyses to refine myopia prevention strategies.

5. Conclusion

This study demonstrates significant correlations between axial length (AL) and retinal vascular morphology in myopic children, advancing understanding of myopia pathogenesis. Leveraging AI for detailed vascular analysis, we highlight AL’s impact on vessel diameters and curvature, informing personalized prevention strategies. While retinal vasculature offers insights into ocular health, future research should address imaging limitations, adopt longitudinal designs, and explore complex vascular metrics to refine myopia interventions.

Supporting information

S1 File. Primary Retinal Vasculature Dataset Analyzed by EVision AI.

(XLSX)

pone.0324352.s001.xlsx^{(153.7KB, xlsx)}

S2 File. Statistical Analysis Results Table.

(XLSX)

pone.0324352.s002.xlsx^{(67.1KB, xlsx)}

S3 File. Original fundus photographs (1).

(ZIP)

pone.0324352.s003.zip^{(72.8MB, zip)}

S4 File. Original fundus photographs (2).

(ZIP)

pone.0324352.s004.zip^{(72.1MB, zip)}

S5 File. The original data of vision screening.

(XLS)

pone.0324352.s005.xls^{(95KB, xls)}

Acknowledgments

Not applicable.

Data Availability

All relevant data are within the manuscript and its Supporting information files.

Funding Statement

This study was funded by Major Scientific and Technological Key Project of the “Four Batches” Initiative by the Shanxi Provincial Health Commission (2022XM18). The funder supported not only the research financially but also contributed to study design, data collection, analysis, publication decisions, and manuscript preparation, as required by its funding policy.

References

1.Harb EN, Wildsoet CF. Origins of Refractive Errors: Environmental and Genetic Factors. Annu Rev Vis Sci. 2019;5:47–72. doi: 10.1146/annurev-vision-091718-015027 [DOI] [PMC free article] [PubMed] [Google Scholar]
2.Yang J, Ouyang X, Fu H, Hou X, Liu Y, Xie Y, et al. Advances in biomedical study of the myopia-related signaling pathways and mechanisms. Biomed Pharmacother. 2022;145:112472. doi: 10.1016/j.biopha.2021.112472 [DOI] [PubMed] [Google Scholar]
3.Holden BA, Fricke TR, Wilson DA, Jong M, Naidoo KS, Sankaridurg P, et al. Global Prevalence of Myopia and High Myopia and Temporal Trends from 2000 through 2050. Ophthalmology. 2016;123(5):1036–42. doi: 10.1016/j.ophtha.2016.01.006 [DOI] [PubMed] [Google Scholar]
4.Biswas S, El Kareh A, Qureshi M, Lee DMX, Sun C-H, Lam JSH, et al. The influence of the environment and lifestyle on myopia. J Physiol Anthropol. 2024;43(1):7. doi: 10.1186/s40101-024-00354-7 [DOI] [PMC free article] [PubMed] [Google Scholar]
5.Zhang S, Chen Y, Li Z, Wang W, Xuan M, Zhang J, et al. Axial Elongation Trajectories in Chinese Children and Adults With High Myopia. JAMA Ophthalmol. 2024;142(2):87–94. doi: 10.1001/jamaophthalmol.2023.5835 [DOI] [PMC free article] [PubMed] [Google Scholar]
6.Tian F, Zheng D, Zhang J, Liu L, Duan J, Guo Y, et al. Choroidal and Retinal Thickness and Axial Eye Elongation in Chinese Junior Students. Invest Ophthalmol Vis Sci. 2021;62(9):26. doi: 10.1167/iovs.62.9.26 [DOI] [PMC free article] [PubMed] [Google Scholar]
7.Shah R, Vlasak N, Evans BJW. High myopia: Reviews of myopia control strategies and myopia complications. Ophthalmic Physiol Opt. 2024;44(6):1248–60. doi: 10.1111/opo.13366 [DOI] [PubMed] [Google Scholar]
8.Li S, Li M, Wu J, Li Y, Han J, Song Y, et al. Developing and validating a clinlabomics-based machine-learning model for early detection of retinal detachment in patients with high myopia. J Transl Med. 2024;22(1):405. doi: 10.1186/s12967-024-05131-9 [DOI] [PMC free article] [PubMed] [Google Scholar]
9.Zhang X, Jiang J, Kong K, Li F, Chen S, Wang P, et al. Optic neuropathy in high myopia: Glaucoma or high myopia or both? Prog Retin Eye Res. 2024;99:101246. doi: 10.1016/j.preteyeres.2024.101246 [DOI] [PubMed] [Google Scholar]
10.Jiang F, Wang D, Xiao O, Guo X, Yin Q, Luo L, et al. Four-Year Progression of Myopic Maculopathy in Children and Adolescents With High Myopia. JAMA Ophthalmol. 2024;142(3):180–6. doi: 10.1001/jamaophthalmol.2023.6319 [DOI] [PMC free article] [PubMed] [Google Scholar]
11.Zhang XJ, Chen XN, Tang FY, Szeto S, Ling XT, Lin ZX, et al. Pathogenesis of myopic choroidal neovascularization: A systematic review and meta-analysis. Surv Ophthalmol. 2023;68(6):1011–26. doi: 10.1016/j.survophthal.2023.07.006 [DOI] [PubMed] [Google Scholar]
12.Cheung CY, Xu D, Cheng C-Y, Sabanayagam C, Tham Y-C, Yu M, et al. A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre. Nat Biomed Eng. 2021;5(6):498–508. doi: 10.1038/s41551-020-00626-4 [DOI] [PubMed] [Google Scholar]
13.Ong SS, Peavey JJ, Hiatt KD, Whitlow CT, Sappington RM, Thompson AC, et al. Association of fractal dimension and other retinal vascular network parameters with cognitive performance and neuroimaging biomarkers: The Multi-Ethnic Study of Atherosclerosis (MESA). Alzheimers Dement. 2024;20(2):941–53. doi: 10.1002/alz.13498 [DOI] [PMC free article] [PubMed] [Google Scholar]
14.Zhao G, Xu X, Yu X, Sun F, Yang A, Jin Y, et al. Comprehensive retinal vascular measurements: time in range is associated with peripheral retinal venular calibers in type 2 diabetes in China. Acta Diabetol. 2023;60(9):1267–77. doi: 10.1007/s00592-023-02120-0 [DOI] [PubMed] [Google Scholar]
15.Bostan M, Li C, Sim YC, Bujor I, Wong D, Tan B, et al. Combining retinal structural and vascular measurements improves discriminative power for multiple sclerosis patients. Ann N Y Acad Sci. 2023;1529(1):72–83. doi: 10.1111/nyas.15060 [DOI] [PubMed] [Google Scholar]
16.Fu Y, Yusufu M, Wang Y, He M, Shi D, Wang R. Association of retinal microvascular density and complexity with incident coronary heart disease. Atherosclerosis. 2023;380:117196. doi: 10.1016/j.atherosclerosis.2023.117196 [DOI] [PubMed] [Google Scholar]
17.Xu Y, Wang Y, Liu B, Tang L, Lv L, Ke X, et al. The diagnostic accuracy of an intelligent and automated fundus disease image assessment system with lesion quantitative function (SmartEye) in diabetic patients. BMC Ophthalmol. 2019;19(1):184. doi: 10.1186/s12886-019-1196-9 [DOI] [PMC free article] [PubMed] [Google Scholar]
18.Shi XH, Dong L, Zhang RH, Zhou DJ, Ling SG, Shao L, et al. Relationships between quantitative retinal microvascular characteristics and cognitive function based on automated artificial intelligence measurements. Front Cell Dev Biol. 2023;11:1174984. doi: 10.3389/fcell.2023.1174984 [DOI] [PMC free article] [PubMed] [Google Scholar]
19.Han Y, Zhang L, Yu Z, Ling S, Zhang X, Yu D, et al. Prediction model for asymptomatic carotid atherosclerosis using retinal microvascular intelligent analysis: A retrospective study. J Stroke Cerebrovasc Dis. 2024;33(8):107780. doi: 10.1016/j.jstrokecerebrovasdis.2024.107780 [DOI] [PubMed] [Google Scholar]
20.Ziukelis ET, Mak E, Dounavi M-E, Su L, T O’Brien J. Fractal dimension of the brain in neurodegenerative disease and dementia: A systematic review. Ageing Res Rev. 2022;79:101651. doi: 10.1016/j.arr.2022.101651 [DOI] [PubMed] [Google Scholar]
21.Raffa L, Abudawd O, Bugshan N, Fageeh S, Ramos L, Novo J, et al. Computer-assisted evaluation of retinal vessel tortuosity in moderate-to-late preterm children. Eur J Ophthalmol. 2023;33(5):1874–82. doi: 10.1177/11206721231157262 [DOI] [PubMed] [Google Scholar]
22.Qiao Y, Cheng D, Zhu X, Ruan K, Ye Y, Yu J, et al. Characteristics of the Peripapillary Structure and Vasculature in Patients With Myopic Anisometropia. Transl Vis Sci Technol. 2023;12(10):16. doi: 10.1167/tvst.12.10.16 [DOI] [PMC free article] [PubMed] [Google Scholar]
23.Cheng T, Deng J, Xu X, Zhang B, Wang J, Xiong S, et al. Prevalence of fundus tessellation and its associated factors in Chinese children and adolescents with high myopia. Acta Ophthalmol. 2021;99(8):e1524–33. doi: 10.1111/aos.14826 [DOI] [PMC free article] [PubMed] [Google Scholar]
24.He H-L, Liu Y-X, Chen X-Y, Ling S-G, Qi Y, Xiong Y, et al. Fundus Tessellated Density of Pathologic Myopia. Asia Pac J Ophthalmol (Phila). 2023;12(6):604–13. doi: 10.1097/APO.0000000000000642 [DOI] [PubMed] [Google Scholar]
25.La Spina C, Corvi F, Bandello F, Querques G. Static characteristics and dynamic functionality of retinal vessels in longer eyes with or without pathologic myopia. Graefes Arch Clin Exp Ophthalmol. 2016;254(5):827–34. doi: 10.1007/s00417-015-3122-z [DOI] [PubMed] [Google Scholar]
26.Tai ELM, Li L-J, Wan-Hazabbah WH, Wong T-Y, Shatriah I. Effect of Axial Eye Length on Retinal Vessel Parameters in 6 to 12-Year-Old Malay Girls. PLoS One. 2017;12(1):e0170014. doi: 10.1371/journal.pone.0170014 [DOI] [PMC free article] [PubMed] [Google Scholar]
27.Lim LS, Cheung CY, Lin X, Mitchell P, Wong TY, Mei-Saw S. Influence of refractive error and axial length on retinal vessel geometric characteristics. Invest Ophthalmol Vis Sci. 2011;52(2):669–78. doi: 10.1167/iovs.10-6184 [DOI] [PubMed] [Google Scholar]
28.Wei Q, Zhou X, Chang W, Jiang R, Zhou X, Yu Z. Retinal and Choroidal Changes Following Implantable Collamer Lens V4c Implantation in High Myopia Patients-A 1-Year Follow-Up Study. Diagnostics (Basel). 2023;13(19):3097. doi: 10.3390/diagnostics13193097 [DOI] [PMC free article] [PubMed] [Google Scholar]
29.Qiao Y, Cheng D, Zhu X, Ruan K, Ye Y, Yu J, et al. Characteristics of the Peripapillary Structure and Vasculature in Patients With Myopic Anisometropia. Transl Vis Sci Technol. 2023;12(10):16. doi: 10.1167/tvst.12.10.16 [DOI] [PMC free article] [PubMed] [Google Scholar]
30.Yii F, Bernabeu MO, Dhillon B, Strang N, MacGillivray T. Retinal Changes From Hyperopia to Myopia: Not All Diopters Are Created Equal. Invest Ophthalmol Vis Sci. 2024;65(5):25. doi: 10.1167/iovs.65.5.25 [DOI] [PMC free article] [PubMed] [Google Scholar]
31.Zhao M, Lam AK-C, Ying MT-C, Cheong AM-Y. Hemodynamic and morphological changes of the central retinal artery in myopic eyes [published correction appears in Sci Rep. Sci Rep. 2022;12(1):7104. doi: 10.1038/s41598-022-11087-x [DOI] [PMC free article] [PubMed] [Google Scholar]
32.Dimitrova G, Tamaki Y, Kato S, Nagahara M. Retrobulbar circulation in myopic patients with or without myopic choroidal neovascularisation. Br J Ophthalmol. 2002;86(7):771–3. doi: 10.1136/bjo.86.7.771 [DOI] [PMC free article] [PubMed] [Google Scholar]
33.Wang X, Kong X, Jiang C, Li M, Yu J, Sun X. Is the peripapillary retinal perfusion related to myopia in healthy eyes? A prospective comparative study. BMJ Open. 2016;6(3):e010791. doi: 10.1136/bmjopen-2015-010791 [DOI] [PMC free article] [PubMed] [Google Scholar]
34.Wu Q, Chen Q, Lin B, Huang S, Wang Y, Zhang L, et al. Relationships among retinal/choroidal thickness, retinal microvascular network and visual field in high myopia. Acta Ophthalmol. 2020;98(6):e709–14. doi: 10.1111/aos.14372 [DOI] [PubMed] [Google Scholar]
35.Hammes H-P, Feng Y, Pfister F, Brownlee M. Diabetic retinopathy: targeting vasoregression. Diabetes. 2011;60(1):9–16. doi: 10.2337/db10-0454 [DOI] [PMC free article] [PubMed] [Google Scholar]
36.Hervella ÁS, Ramos L, Rouco J, Novo J, Ortega M. Explainable artificial intelligence for the automated assessment of the retinal vascular tortuosity. Med Biol Eng Comput. 2024;62(3):865–81. doi: 10.1007/s11517-023-02978-w [DOI] [PMC free article] [PubMed] [Google Scholar]
37.Naidu VV, Ismail K, Amiel S, Kohli R, Crosby-Nwaobi R, Sivaprasad S, et al. Associations between Retinal Markers of Microvascular Disease and Cognitive Impairment in Newly Diagnosed Type 2 Diabetes Mellitus: A Case Control Study. PLoS One. 2016;11(1):e0147160. doi: 10.1371/journal.pone.0147160 [DOI] [PMC free article] [PubMed] [Google Scholar]
38.Lv L, Li M, Chang X, Zhu M, Liu Y, Wang P, et al. Macular Retinal Microvasculature of Hyperopia, Emmetropia, and Myopia in Children. Front Med (Lausanne). 2022;9:900486. doi: 10.3389/fmed.2022.900486 [DOI] [PMC free article] [PubMed] [Google Scholar]
39.Wu R, Cheung CY-L, Saw SM, Mitchell P, Aung T, Wong TY. Retinal vascular geometry and glaucoma: the Singapore Malay Eye Study. Ophthalmology. 2013;120(1):77–83. doi: 10.1016/j.ophtha.2012.07.063 [DOI] [PubMed] [Google Scholar]
40.Moon Y, Lim HT. Relationship between peripapillary atrophy and myopia progression in the eyes of young school children. Eye (Lond). 2021;35(2):665–71. doi: 10.1038/s41433-020-0945-6 [DOI] [PMC free article] [PubMed] [Google Scholar]
41.He X, Deng J, Xu X, Wang J, Cheng T, Zhang B, et al. Design and Pilot data of the high myopia registration study: Shanghai Child and Adolescent Large-scale Eye Study (SCALE-HM). Acta Ophthalmol. 2021;99(4):e489–500. doi: 10.1111/aos.14617 [DOI] [PMC free article] [PubMed] [Google Scholar]
42.He H-L, Liu Y-X, Liu H, Zhang X, Song H, Xu T-Z, et al. Deep Learning-Enabled Vasculometry Depicts Phased Lesion Patterns in High Myopia Progression. Asia Pac J Ophthalmol (Phila). 2024;13(4):100086. doi: 10.1016/j.apjo.2024.100086 [DOI] [PubMed] [Google Scholar]
43.Han YE, Kim YJ, Yang HS, Moon BG, Lee JY, Kim J-G, et al. Prognostic value of myopic disk deformation in myopic choroidal neovascularization: A 6-year follow-up study. Front Med (Lausanne). 2022;9:947632. doi: 10.3389/fmed.2022.947632 [DOI] [PMC free article] [PubMed] [Google Scholar]
44.Tey KY, Hoang QV, Loh IQ, Dan YS, Wong QY, Yu DJG, et al. Multimodal Imaging-Based Phenotyping of a Singaporean Hospital-Based Cohort of High Myopia Patients. Front Med (Lausanne). 2022;8:670229. doi: 10.3389/fmed.2021.670229 [DOI] [PMC free article] [PubMed] [Google Scholar]
45.He J, Ye L, Chu C, Chen Q, Sun D, Xie J, et al. Using a combination of peripapillary atrophy area and choroidal thickness for the prediction of different types of myopic maculopathy. Eye (Lond). 2023;37(13):2801–9. doi: 10.1038/s41433-023-02423-0 [DOI] [PMC free article] [PubMed] [Google Scholar]
46.Guo Y, Liu L, Zheng D, Duan J, Wang Y, Jonas JB, et al. Prevalence and Associations of Fundus Tessellation Among Junior Students From Greater Beijing. Invest Ophthalmol Vis Sci. 2019;60(12):4033–40. doi: 10.1167/iovs.19-27382 [DOI] [PubMed] [Google Scholar]
47.Yan YN, Wang YX, Xu L, Xu J, Wei WB, Jonas JB. Fundus Tessellation: Prevalence and Associated Factors: The Beijing Eye Study 2011. Ophthalmology. 2015;122(9):1873–80. doi: 10.1016/j.ophtha.2015.05.031 [DOI] [PubMed] [Google Scholar]

PLoS One. 2025 Jun 17;20(6):e0324352. doi: 10.1371/journal.pone.0324352.r001

Author response to Decision Letter 0

15 Nov 2024

PLoS One. doi: 10.1371/journal.pone.0324352.r002

Decision Letter 0

Xu Yanwu

22 Dec 2024

PONE-D-24-50749Research on the Correlation between Retinal Vascular Parameters and Axial Length in Children Based on Artificial IntelligencePLOS ONE

Dear Dr. Hao,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Feb 05 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols .

We look forward to receiving your revised manuscript.

Kind regards,

Xu Yanwu

Academic Editor

PLOS ONE

Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Thank you for stating the following financial disclosure: "Major Scientific and Technological Key Project of the "Four Batches" Initiative by the Shanxi Provincial Health Commission (2022XM18)." Please state what role the funders took in the study. If the funders had no role, please state: ""The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."" If this statement is not correct you must amend it as needed. Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. 3. We note that your Data Availability Statement is currently as follows: All relevant data are within the manuscript and its Supporting Information files. Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition). For example, authors should submit the following data: - The values behind the means, standard deviations and other measures reported;- The values used to build graphs;- The points extracted from images for analysis. Authors do not need to submit their entire data set if only a portion of the data was used in the reported study. If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access.

4. Please include captions for your Supporting Information files at the end of your manuscript, and update any in-text citations to match accordingly. Please see our Supporting Information guidelines for more information: http://journals.plos.org/plosone/s/supporting-information.

Additional Editor Comments:

Please follow reviewers' comments to revise your manuscript. The format should also be improved. For example, the 'Introduction' should be numbered as the first section. Please also double-check your references. For example, the citation of EVision seems to be linked to a wrong article.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: No

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: - The paper is written well

- The title artificial intelligence is misleading because the authors use the readily available algorithm inside the commercially available machine.

- However, there is no mention about the algorithm of AI or contribution towards AI research.

Reviewer #2: Generally, the study provided a study using transparent methodology backed with existing research. It presented the relationship between various retinal vascular parameters and axial length, leading to an interpretation of how these factors may interact and a discussion of the potential guiding significance. However, there are still a few flaws which should be paying more attention to.

1. (Page 7, lines 12-20) The imaging process requires more detailed explanation, better with flow charts or other diagrams. The legends of Figure 1-4 could be more concise by transferring some of the explanatory details to the main text.

2. (Page 10, lines 19-21) The discussion regarding the reduction of errors caused by manual measurements lacks sufficient detail. More specific data should be presented to support the argument.

3. The content in the “3. Conclusion” section overlaps too much with the result section and the final “Conclusion” section. This redundancy could be reduced to improve the structure and focus of the paper.

4. The readability of the tables could be improved. For example, P-values less than 0.05 should be bolded or presented as superscripts to distinguish their significance. Formatting adjustments could further enhance the clarity and presentation of the data.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy .

Reviewer #1: No

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org . Please note that Supporting Information files do not need this step.

PLoS One. 2025 Jun 17;20(6):e0324352. doi: 10.1371/journal.pone.0324352.r003

Author response to Decision Letter 1

13 Feb 2025

Dear Reviewers,

We deeply appreciate your invaluable feedback on our manuscript, titled "Research on the Correlation between Retinal Vascular Parameters and Axial Length in Children Based on Artificial Intelligence." Recognizing the effort and time you've invested in the review, we sincerely thank you. Your insightful comments have enriched our understanding of the research and provided us with valuable suggestions. We have carefully considered all your recommendations and will address them in the revised manuscript. Here are our point-by-point responses to your main comments:

Reviewer 1:

1.We sincerely appreciate your affirmation of our paper titled "Research on the Correlation between Retinal Vascular Parameters and Axial Length in Children Using an AI-Based Fundus Image Analysis System" [Note: The title has been updated accordingly in this response for consistency]. Your recognition serves as a great encouragement for us.

2.Regarding your concern that the use of the term "Artificial Intelligence" in the title may be misleading, we have carefully considered and revised it. You pointed out that we utilized readily available algorithms within a commercial machine, rather than developing or conducting in-depth research on AI algorithms ourselves. Your observation is highly accurate, and we fully concur with your perspective. Therefore, we have modified the title from "Based on Artificial Intelligence" to "Using an AI-Based Fundus Image Analysis System," to more accurately reflect that we actually employed an AI-based fundus image analysis system in our research, rather than specifically referring to our research or development of AI algorithms.

3.In the Methods section, to directly address your comments, we have provided a more detailed description of the AI system's usage and included a brief explanation of the AI system. We explicitly state that the EVision AI Fundus Image Analysis System is a commercial software that utilizes pre-trained algorithms for automatic extraction of retinal vascular parameters. This description helps eliminate potential misunderstandings and more clearly presents the technical means adopted in our research.

Reviewer 2

1.We have provided a more detailed description of the imaging process and inserted a flowchart to clearly illustrate the various stages of imaging. These modifications will aid readers in better understanding our research methodology and results. Additionally, we have taken note of the reviewer's suggestions regarding the legends of Figures 1-4 and have made corresponding revisions. We have transferred some explanatory details to the main text to make the legends more concise and straightforward. These changes will enhance the readability and clarity of the figures.

2.In response to your comment on page 10, lines 19-21, regarding the lack of sufficient detail and the need for more concrete data in the discussion about mitigating manual measurement errors, we have conducted thorough reflections and made corresponding revisions.To strengthen the argumentation in this section, we have revisited the experimental data and extracted specific statistical indicators related to manual measurement errors. By comparing the results of automatic measurements with those of manual measurements, we found that the artificial intelligence-based system reduced the standard deviation of retinal vessel diameter measurements by 0.12 mm (p < 0.05). This result significantly demonstrates the improvement in accuracy and consistency of automatic measurements. We have included this finding in the discussion section for further elucidation.

3.Regarding the issue you previously pointed out concerning the overlap between the conclusion and results sections, we have conducted thorough reflections and made the necessary revisions. Following your advice, I have endeavored to streamline the restatement of specific research findings, instead emphasizing more on the significance of this study, its contributions to the field, and potential future research directions. Additionally, I have retained the mention of AI technology's potential in the conclusion section and expanded on specific suggestions for areas that future research could explore, aiming to provide readers with a broader perspective and room for contemplation.Furthermore, during the revision process, we paid particular attention to maintaining the paper's logical flow and coherence, ensuring that the conclusion section is both concise and clear while accurately reflecting the research's core value and potential impact. We hope that these adjustments will further enhance the clarity and focus of the paper's conclusion section, making it better serve the understanding and inspiration of readers.

4.Based on your suggestions, we have made the following modifications to the tables in the paper: For data with P-values less than 0.05, we have bolded them (or converted them to superscript format, depending on the format you prefer) to more clearly showcase the significance of these data. Additionally, we have adjusted other table formats to enhance overall readability and data clarity.

Best regards,

Chaoyang Zhao

Attachment

Submitted filename: Response to Reviewers.docx

pone.0324352.s007.docx^{(13.7KB, docx)}

PLoS One. doi: 10.1371/journal.pone.0324352.r004

Decision Letter 1

Xu Yanwu

24 Feb 2025

<div>PONE-D-24-50749R1Research on the Correlation between Retinal Vascular Parameters and Axial Length in Children Using an AI-Based Fundus Image Analysis SystemPLOS ONE

Dear Dr. Hao,

Please submit your revised manuscript by Apr 10 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

We look forward to receiving your revised manuscript.

Kind regards,

Xu Yanwu

Academic Editor

PLOS ONE

Additional Editor Comments:

Please improve the manuscript following the suggestions form Reviewer 2. Specifically, you should make your manuscript more concise and accurate to improve its readability.

[Note: HTML markup is below. Please do not edit.]

PLoS One. 2025 Jun 17;20(6):e0324352. doi: 10.1371/journal.pone.0324352.r005

Author response to Decision Letter 2

14 Apr 2025

Dear Reviewers,

Thank you for the constructive feedback on our manuscript. We sincerely appreciate the time and effort you dedicated to reviewing our work. Below are our responses to the comments and the corresponding revisions made to the manuscript.

Comment:

"The content in the ‘3. Conclusion’ section overlaps too much with the Result section and the final ‘Conclusion’ section. This redundancy could be reduced to improve the structure and focus of the paper."

Response:We fully agree with the reviewer’s observation regarding the redundancy in the original "3. Conclusion" section. To address this concern, we have implemented the following revisions:

1.Restructured the "3. Conclusion" section (now titled "3. Discussion"):

Refocused this section on interpreting the results, linking findings to hypotheses, and discussing their implications.Removed repetitive summaries of results and technical details to avoid overlap with the Results section.

2.Streamlined the final Conclusion:

Highlighted the key contributions of the study and their broader significance.Ensured the final Conclusion serves as a standalone summary of the paper’s core message, distinct from the Discussion.

3.Key Revisions:

Renamed "3. Conclusion" to "3. Discussion" to better align with its purpose.

Condensed overlapping content between the Discussion and the final Conclusion.

Added transitional sentences to enhance flow and coherence between sections.

4.Comprehensive Refinement of the Results Section:

A thorough review consolidated redundant experimental data, streamlined statistical reporting, and ensured the Results section exclusively presents data, reserving analysis for the Discussion, thereby enhancing clarity, structural coherence, and adherence to academic standards.

These changes collectively improve the manuscript’s clarity, structural rigor, and alignment with academic conventions.

Best regards,

Shaofeng Hao

PLoS One. doi: 10.1371/journal.pone.0324352.r006

Decision Letter 2

Xu Yanwu

24 Apr 2025

Research on the Correlation between Retinal Vascular Parameters and Axial Length in Children Using an AI-Based Fundus Image Analysis System

PONE-D-24-50749R2

Dear Dr. Hao,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Xu Yanwu

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

Reviewer #2: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

Reviewer #2: No

**********

6. Review Comments to the Author

Reviewer #2: The authors have addressed all my comments and suggestions. I have no further questions for the revised manuscript.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy .

Reviewer #2: No

**********

PLoS One. doi: 10.1371/journal.pone.0324352.r007

Acceptance letter

Xu Yanwu

PONE-D-24-50749R2

PLOS ONE

Dear Dr. Hao,

I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team.

At this stage, our production department will prepare your paper for publication. This includes ensuring the following:

* All references, tables, and figures are properly cited

* All relevant supporting information is included in the manuscript submission,

* There are no issues that prevent the paper from being properly typeset

You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days to review your paper and let you know the next and final steps.

Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

If we can help with anything else, please email us at customercare@plos.org.

Thank you for submitting your work to PLOS ONE and supporting open access.

Kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Xu Yanwu

Academic Editor

PLOS ONE

Associated Data

This section collects any data citations, data availability statements, or supplementary materials included in this article.

Supplementary Materials

S1 File. Primary Retinal Vasculature Dataset Analyzed by EVision AI.

(XLSX)

pone.0324352.s001.xlsx^{(153.7KB, xlsx)}

S2 File. Statistical Analysis Results Table.

(XLSX)

pone.0324352.s002.xlsx^{(67.1KB, xlsx)}

S3 File. Original fundus photographs (1).

(ZIP)

pone.0324352.s003.zip^{(72.8MB, zip)}

S4 File. Original fundus photographs (2).

(ZIP)

pone.0324352.s004.zip^{(72.1MB, zip)}

S5 File. The original data of vision screening.

(XLS)

pone.0324352.s005.xls^{(95KB, xls)}

Attachment

Submitted filename: Response to Reviewers.docx

pone.0324352.s007.docx^{(13.7KB, docx)}

Data Availability Statement

All relevant data are within the manuscript and its Supporting information files.

[pone.0324352.ref001] 1.Harb EN, Wildsoet CF. Origins of Refractive Errors: Environmental and Genetic Factors. Annu Rev Vis Sci. 2019;5:47–72. doi: 10.1146/annurev-vision-091718-015027 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref002] 2.Yang J, Ouyang X, Fu H, Hou X, Liu Y, Xie Y, et al. Advances in biomedical study of the myopia-related signaling pathways and mechanisms. Biomed Pharmacother. 2022;145:112472. doi: 10.1016/j.biopha.2021.112472 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref003] 3.Holden BA, Fricke TR, Wilson DA, Jong M, Naidoo KS, Sankaridurg P, et al. Global Prevalence of Myopia and High Myopia and Temporal Trends from 2000 through 2050. Ophthalmology. 2016;123(5):1036–42. doi: 10.1016/j.ophtha.2016.01.006 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref004] 4.Biswas S, El Kareh A, Qureshi M, Lee DMX, Sun C-H, Lam JSH, et al. The influence of the environment and lifestyle on myopia. J Physiol Anthropol. 2024;43(1):7. doi: 10.1186/s40101-024-00354-7 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref005] 5.Zhang S, Chen Y, Li Z, Wang W, Xuan M, Zhang J, et al. Axial Elongation Trajectories in Chinese Children and Adults With High Myopia. JAMA Ophthalmol. 2024;142(2):87–94. doi: 10.1001/jamaophthalmol.2023.5835 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref006] 6.Tian F, Zheng D, Zhang J, Liu L, Duan J, Guo Y, et al. Choroidal and Retinal Thickness and Axial Eye Elongation in Chinese Junior Students. Invest Ophthalmol Vis Sci. 2021;62(9):26. doi: 10.1167/iovs.62.9.26 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref007] 7.Shah R, Vlasak N, Evans BJW. High myopia: Reviews of myopia control strategies and myopia complications. Ophthalmic Physiol Opt. 2024;44(6):1248–60. doi: 10.1111/opo.13366 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref008] 8.Li S, Li M, Wu J, Li Y, Han J, Song Y, et al. Developing and validating a clinlabomics-based machine-learning model for early detection of retinal detachment in patients with high myopia. J Transl Med. 2024;22(1):405. doi: 10.1186/s12967-024-05131-9 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref009] 9.Zhang X, Jiang J, Kong K, Li F, Chen S, Wang P, et al. Optic neuropathy in high myopia: Glaucoma or high myopia or both? Prog Retin Eye Res. 2024;99:101246. doi: 10.1016/j.preteyeres.2024.101246 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref010] 10.Jiang F, Wang D, Xiao O, Guo X, Yin Q, Luo L, et al. Four-Year Progression of Myopic Maculopathy in Children and Adolescents With High Myopia. JAMA Ophthalmol. 2024;142(3):180–6. doi: 10.1001/jamaophthalmol.2023.6319 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref011] 11.Zhang XJ, Chen XN, Tang FY, Szeto S, Ling XT, Lin ZX, et al. Pathogenesis of myopic choroidal neovascularization: A systematic review and meta-analysis. Surv Ophthalmol. 2023;68(6):1011–26. doi: 10.1016/j.survophthal.2023.07.006 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref012] 12.Cheung CY, Xu D, Cheng C-Y, Sabanayagam C, Tham Y-C, Yu M, et al. A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre. Nat Biomed Eng. 2021;5(6):498–508. doi: 10.1038/s41551-020-00626-4 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref013] 13.Ong SS, Peavey JJ, Hiatt KD, Whitlow CT, Sappington RM, Thompson AC, et al. Association of fractal dimension and other retinal vascular network parameters with cognitive performance and neuroimaging biomarkers: The Multi-Ethnic Study of Atherosclerosis (MESA). Alzheimers Dement. 2024;20(2):941–53. doi: 10.1002/alz.13498 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref014] 14.Zhao G, Xu X, Yu X, Sun F, Yang A, Jin Y, et al. Comprehensive retinal vascular measurements: time in range is associated with peripheral retinal venular calibers in type 2 diabetes in China. Acta Diabetol. 2023;60(9):1267–77. doi: 10.1007/s00592-023-02120-0 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref015] 15.Bostan M, Li C, Sim YC, Bujor I, Wong D, Tan B, et al. Combining retinal structural and vascular measurements improves discriminative power for multiple sclerosis patients. Ann N Y Acad Sci. 2023;1529(1):72–83. doi: 10.1111/nyas.15060 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref016] 16.Fu Y, Yusufu M, Wang Y, He M, Shi D, Wang R. Association of retinal microvascular density and complexity with incident coronary heart disease. Atherosclerosis. 2023;380:117196. doi: 10.1016/j.atherosclerosis.2023.117196 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref017] 17.Xu Y, Wang Y, Liu B, Tang L, Lv L, Ke X, et al. The diagnostic accuracy of an intelligent and automated fundus disease image assessment system with lesion quantitative function (SmartEye) in diabetic patients. BMC Ophthalmol. 2019;19(1):184. doi: 10.1186/s12886-019-1196-9 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref018] 18.Shi XH, Dong L, Zhang RH, Zhou DJ, Ling SG, Shao L, et al. Relationships between quantitative retinal microvascular characteristics and cognitive function based on automated artificial intelligence measurements. Front Cell Dev Biol. 2023;11:1174984. doi: 10.3389/fcell.2023.1174984 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref019] 19.Han Y, Zhang L, Yu Z, Ling S, Zhang X, Yu D, et al. Prediction model for asymptomatic carotid atherosclerosis using retinal microvascular intelligent analysis: A retrospective study. J Stroke Cerebrovasc Dis. 2024;33(8):107780. doi: 10.1016/j.jstrokecerebrovasdis.2024.107780 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref020] 20.Ziukelis ET, Mak E, Dounavi M-E, Su L, T O’Brien J. Fractal dimension of the brain in neurodegenerative disease and dementia: A systematic review. Ageing Res Rev. 2022;79:101651. doi: 10.1016/j.arr.2022.101651 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref021] 21.Raffa L, Abudawd O, Bugshan N, Fageeh S, Ramos L, Novo J, et al. Computer-assisted evaluation of retinal vessel tortuosity in moderate-to-late preterm children. Eur J Ophthalmol. 2023;33(5):1874–82. doi: 10.1177/11206721231157262 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref022] 22.Qiao Y, Cheng D, Zhu X, Ruan K, Ye Y, Yu J, et al. Characteristics of the Peripapillary Structure and Vasculature in Patients With Myopic Anisometropia. Transl Vis Sci Technol. 2023;12(10):16. doi: 10.1167/tvst.12.10.16 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref023] 23.Cheng T, Deng J, Xu X, Zhang B, Wang J, Xiong S, et al. Prevalence of fundus tessellation and its associated factors in Chinese children and adolescents with high myopia. Acta Ophthalmol. 2021;99(8):e1524–33. doi: 10.1111/aos.14826 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref024] 24.He H-L, Liu Y-X, Chen X-Y, Ling S-G, Qi Y, Xiong Y, et al. Fundus Tessellated Density of Pathologic Myopia. Asia Pac J Ophthalmol (Phila). 2023;12(6):604–13. doi: 10.1097/APO.0000000000000642 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref025] 25.La Spina C, Corvi F, Bandello F, Querques G. Static characteristics and dynamic functionality of retinal vessels in longer eyes with or without pathologic myopia. Graefes Arch Clin Exp Ophthalmol. 2016;254(5):827–34. doi: 10.1007/s00417-015-3122-z [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref026] 26.Tai ELM, Li L-J, Wan-Hazabbah WH, Wong T-Y, Shatriah I. Effect of Axial Eye Length on Retinal Vessel Parameters in 6 to 12-Year-Old Malay Girls. PLoS One. 2017;12(1):e0170014. doi: 10.1371/journal.pone.0170014 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref027] 27.Lim LS, Cheung CY, Lin X, Mitchell P, Wong TY, Mei-Saw S. Influence of refractive error and axial length on retinal vessel geometric characteristics. Invest Ophthalmol Vis Sci. 2011;52(2):669–78. doi: 10.1167/iovs.10-6184 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref028] 28.Wei Q, Zhou X, Chang W, Jiang R, Zhou X, Yu Z. Retinal and Choroidal Changes Following Implantable Collamer Lens V4c Implantation in High Myopia Patients-A 1-Year Follow-Up Study. Diagnostics (Basel). 2023;13(19):3097. doi: 10.3390/diagnostics13193097 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref029] 29.Qiao Y, Cheng D, Zhu X, Ruan K, Ye Y, Yu J, et al. Characteristics of the Peripapillary Structure and Vasculature in Patients With Myopic Anisometropia. Transl Vis Sci Technol. 2023;12(10):16. doi: 10.1167/tvst.12.10.16 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref030] 30.Yii F, Bernabeu MO, Dhillon B, Strang N, MacGillivray T. Retinal Changes From Hyperopia to Myopia: Not All Diopters Are Created Equal. Invest Ophthalmol Vis Sci. 2024;65(5):25. doi: 10.1167/iovs.65.5.25 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref031] 31.Zhao M, Lam AK-C, Ying MT-C, Cheong AM-Y. Hemodynamic and morphological changes of the central retinal artery in myopic eyes [published correction appears in Sci Rep. Sci Rep. 2022;12(1):7104. doi: 10.1038/s41598-022-11087-x [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref032] 32.Dimitrova G, Tamaki Y, Kato S, Nagahara M. Retrobulbar circulation in myopic patients with or without myopic choroidal neovascularisation. Br J Ophthalmol. 2002;86(7):771–3. doi: 10.1136/bjo.86.7.771 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref033] 33.Wang X, Kong X, Jiang C, Li M, Yu J, Sun X. Is the peripapillary retinal perfusion related to myopia in healthy eyes? A prospective comparative study. BMJ Open. 2016;6(3):e010791. doi: 10.1136/bmjopen-2015-010791 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref034] 34.Wu Q, Chen Q, Lin B, Huang S, Wang Y, Zhang L, et al. Relationships among retinal/choroidal thickness, retinal microvascular network and visual field in high myopia. Acta Ophthalmol. 2020;98(6):e709–14. doi: 10.1111/aos.14372 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref035] 35.Hammes H-P, Feng Y, Pfister F, Brownlee M. Diabetic retinopathy: targeting vasoregression. Diabetes. 2011;60(1):9–16. doi: 10.2337/db10-0454 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref036] 36.Hervella ÁS, Ramos L, Rouco J, Novo J, Ortega M. Explainable artificial intelligence for the automated assessment of the retinal vascular tortuosity. Med Biol Eng Comput. 2024;62(3):865–81. doi: 10.1007/s11517-023-02978-w [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref037] 37.Naidu VV, Ismail K, Amiel S, Kohli R, Crosby-Nwaobi R, Sivaprasad S, et al. Associations between Retinal Markers of Microvascular Disease and Cognitive Impairment in Newly Diagnosed Type 2 Diabetes Mellitus: A Case Control Study. PLoS One. 2016;11(1):e0147160. doi: 10.1371/journal.pone.0147160 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref038] 38.Lv L, Li M, Chang X, Zhu M, Liu Y, Wang P, et al. Macular Retinal Microvasculature of Hyperopia, Emmetropia, and Myopia in Children. Front Med (Lausanne). 2022;9:900486. doi: 10.3389/fmed.2022.900486 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref039] 39.Wu R, Cheung CY-L, Saw SM, Mitchell P, Aung T, Wong TY. Retinal vascular geometry and glaucoma: the Singapore Malay Eye Study. Ophthalmology. 2013;120(1):77–83. doi: 10.1016/j.ophtha.2012.07.063 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref040] 40.Moon Y, Lim HT. Relationship between peripapillary atrophy and myopia progression in the eyes of young school children. Eye (Lond). 2021;35(2):665–71. doi: 10.1038/s41433-020-0945-6 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref041] 41.He X, Deng J, Xu X, Wang J, Cheng T, Zhang B, et al. Design and Pilot data of the high myopia registration study: Shanghai Child and Adolescent Large-scale Eye Study (SCALE-HM). Acta Ophthalmol. 2021;99(4):e489–500. doi: 10.1111/aos.14617 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref042] 42.He H-L, Liu Y-X, Liu H, Zhang X, Song H, Xu T-Z, et al. Deep Learning-Enabled Vasculometry Depicts Phased Lesion Patterns in High Myopia Progression. Asia Pac J Ophthalmol (Phila). 2024;13(4):100086. doi: 10.1016/j.apjo.2024.100086 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref043] 43.Han YE, Kim YJ, Yang HS, Moon BG, Lee JY, Kim J-G, et al. Prognostic value of myopic disk deformation in myopic choroidal neovascularization: A 6-year follow-up study. Front Med (Lausanne). 2022;9:947632. doi: 10.3389/fmed.2022.947632 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref044] 44.Tey KY, Hoang QV, Loh IQ, Dan YS, Wong QY, Yu DJG, et al. Multimodal Imaging-Based Phenotyping of a Singaporean Hospital-Based Cohort of High Myopia Patients. Front Med (Lausanne). 2022;8:670229. doi: 10.3389/fmed.2021.670229 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref045] 45.He J, Ye L, Chu C, Chen Q, Sun D, Xie J, et al. Using a combination of peripapillary atrophy area and choroidal thickness for the prediction of different types of myopic maculopathy. Eye (Lond). 2023;37(13):2801–9. doi: 10.1038/s41433-023-02423-0 [DOI] [PMC free article] [PubMed] [Google Scholar]

[pone.0324352.ref046] 46.Guo Y, Liu L, Zheng D, Duan J, Wang Y, Jonas JB, et al. Prevalence and Associations of Fundus Tessellation Among Junior Students From Greater Beijing. Invest Ophthalmol Vis Sci. 2019;60(12):4033–40. doi: 10.1167/iovs.19-27382 [DOI] [PubMed] [Google Scholar]

[pone.0324352.ref047] 47.Yan YN, Wang YX, Xu L, Xu J, Wei WB, Jonas JB. Fundus Tessellation: Prevalence and Associated Factors: The Beijing Eye Study 2011. Ophthalmology. 2015;122(9):1873–80. doi: 10.1016/j.ophtha.2015.05.031 [DOI] [PubMed] [Google Scholar]

PERMALINK

Research on the correlation between retinal vascular parameters and axial length in children using an AI-based fundus image analysis system

Chaoyang Zhao

Huilin Li

Ziyou Yuan

Zihan Yang

Tiantian Wang

Yan Wang

Qian Tong

Shaofeng Hao

Roles

Abstract

Objective

Methods

Results

Conclusion

1. Introduction

2. Materials and methods

2.1. General information

2.2. Methods

2.2.1. Examination items and procedures.

2.2.2. Analysis of retinal vascular parameters based on artificial intelligence.

Fig 1. Presents a flowchart of the entire imaging process and EVision AI analysis.

Fig 5. Annotated arteries and veins for parameter extraction.

Fig 2. Raw fundus photograph.

Fig 3. Preprocessed fundus image after denoising and enhancement.

Fig 4. Segmented retinal vessels and optic disc.

2.2.3. Data collection and sample size determination.

2.2.4. Statistical analysis methods.

3. Results

3.1. Basic information analysis of subjects

Table 1. Comparison of Clinical Data Among Participants in the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

3.2. Univariate correlation analysis of axial length and retinal vascular parameters

3.2.1. Axial length and retinal vascular diameters.

Table 2. Comparison of Retinal Vessel Diameters and Axial Length Among the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

3.2.2. Axial length and retinal vascular tortuosity.

Table 3. Comparison of Retinal Vessel Tortuosity and Axial Length Among the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

3.2.3. Axial length and other retinal vascular parameters.

Table 4. Comparison of Other Retinal Vascular Parameters and Axial Length Among the Normal, Low Myopia, and Moderate-to-High Myopia Groups.

3.3. Multiple linear regression analysis of axial length and retinal blood vessel parameters

Table 5. Multiple Linear Regression Analysis of Axial Length and Retinal Vascular Parameters.

4. Discussion

4.1. Relationships between axial length and retinal vascular parameters

4.2. Vascular curvature and axial length

4.3. Parafoveal atrophy, tessellated fundus, and axial length

4.4. Fractal dimension, branching angle, and study limitations

4.5. Study limitations

5. Conclusion

Supporting information

Acknowledgments

Data Availability

Funding Statement

References

Author response to Decision Letter 0

Decision Letter 0

Xu Yanwu

Roles

Author response to Decision Letter 1

Decision Letter 1

Xu Yanwu

Roles

Author response to Decision Letter 2

Decision Letter 2

Xu Yanwu

Roles

Acceptance letter

Xu Yanwu

Roles

Associated Data

Supplementary Materials

Data Availability Statement

ACTIONS

PERMALINK

RESOURCES

Similar articles

Cited by other articles

Links to NCBI Databases