Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Aug 18;17(8):1453-1461.
doi: 10.18240/ijo.2024.08.10. eCollection 2024.

Changes of the peripapillary vascular parameters in premature infants without retinopathy of prematurity using U-net segmentation

Shuai Liu  1   2 , Lei Liu  1   3 , Cui-Xia Ma  4 , Liu-Hui Huang  5 , Bin Li  1
Affiliations

Changes of the peripapillary vascular parameters in premature infants without retinopathy of prematurity using U-net segmentation

Shuai Liu et al. Int J Ophthalmol. .

Abstract

Aim: To quantitatively assess the changes in mean vascular tortuosity (mVT) and mean vascular width (mVW) around the optic disc and their correlation with gestational age (GA) and birth weight (BW) in premature infants without retinopathy of prematurity (ROP).

Methods: A single-center retrospective study included a total of 133 (133 eyes) premature infants [mean corrected gestational age (CGA) 43.6wk] without ROP as the premature group and 130 (130 eyes) CGA-matched full-term infants as the control group. The peripapillary mVT and mVW were quantitatively measured using computer-assisted techniques.

Results: Premature infants had significantly higher mVT (P=0.0032) and lower mVW (P=0.0086) by 2.68 (104 cm-3) and 1.85 µm, respectively. Subgroup analysis with GA showed significant differences (P=0.0244) in mVT between the early preterm and middle to late preterm groups, but the differences between mVW were not significant (P=0.6652). The results of the multiple linear regression model showed a significant negative correlation between GA and BW with mVT after adjusting sex and CGA (P=0.0211 and P=0.0006, respectively). For each day increase in GA at birth, mVT decreased by 0.1281 (104 cm-3) and for each 1 g increase in BW, mVT decreased by 0.006 (104 cm-3). However, GA (P=0.9402) and BW (P=0.7275) were not significantly correlated with mVW.

Conclusion: Preterm birth significantly affects the peripapillary vascular parameters that indicate higher mVT and narrower mVW in premature infants without ROP. Alterations in these parameters may provide new insights into the pathogenesis of ocular vascular disease.

Keywords: computer-assisted techniques; premature infants; retinal vessels parameter; retinopathy of prematurity.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: Liu S, None; Liu L, None; Ma CX, None; Huang LH, None; Li B, None.

Figures

Figure 1
Figure 1. Representative fundus images of normal full-term newborns and premature infants without ROP taken by RetCam 3
A: Fundus image of a full-term neonate born at 41+1wk of gestational age (GA). Corrected gestational age (CGA) 45+1wk. No significant abnormalities in the posterior pole vessels of the retina. B: Fundus of a preterm neonate born at GA 31wk. CGA 31wk, no significant abnormalities in the posterior pole vessels of the retina. C: Fundus image of the same eye as in Figure B. CGA 43+3wk. Although no ROP was found during the entire follow-up period, significant tortuosity of the arteries could be observed in the posterior pole of the retina (black arrow). ROP: Retinopathy of prematurity.
Figure 2
Figure 2. The pipeline of quantitative assessment in premature infants without retinopathy of prematurity
OD: Optic disc; BV: Blood vessel; ROI: Region of interest.
Figure 3
Figure 3. U-net model for BV and OD segmentation
OD: Optic disc; BV: Blood vessel.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Jang JH, Kim YC. Retinal vascular development in an immature retina at 33-34 weeks postmenstrual age predicts retinopathy of prematurity. Sci Rep. 2020;10(1):18111. - PMC - PubMed
    1. Bai YC, Wu R, Chen SZ, Wei SY, Chen HJ, Chen YC, Feng SF, Lu XH. Efficacy of the WINROP algorithm for retinopathy of prematurity screening in Southern China. Int J Ophthalmol. 2021;14(1):127–132. - PMC - PubMed
    1. Wu FY, Yu WT, Zhao DX, Pu W, Zhang X, Gai CL. Recurrence risk factors of intravitreal ranibizumab monotherapy in retinopathy of prematurity: a retrospective study at one center. Int J Ophthalmol. 2023;16(1):95–101. - PMC - PubMed
    1. Gupta K, Campbell JP, Taylor S, Brown JM, Ostmo S, Paul Chan RVP, Dy J, Erdogmus D, Ioannidis S, Kalpathy-Cramer J, Kim SJ, Chiang MF, Imaging and Informatics in Retinopathy of Prematurity Consortium A quantitative severity scale for retinopathy of prematurity using deep learning to monitor disease regression after treatment. JAMA Ophthalmol. 2019;137(9):1029–1036. - PMC - PubMed
    1. Taylor S, Brown JM, Gupta K, Campbell JP, Ostmo S, Paul Chan RVP, Dy J, Erdogmus D, Ioannidis S, Kim SJ, Kalpathy-Cramer J, Chiang MF, Imaging and Informatics in Retinopathy of Prematurity Consortium Monitoring disease progression with a quantitative severity scale for retinopathy of prematurity using deep learning. JAMA Ophthalmol. 2019;137(9):1022–1028. - PMC - PubMed

LinkOut - more resources