Age and gender-related changes in choroidal thickness: Insights from deep learning analysis of swept-source OCT images

IF 3.1 3区医学 Q2 ONCOLOGY

Photodiagnosis and Photodynamic Therapy Pub Date : 2025-02-01 DOI:10.1016/j.pdpdt.2025.104511

Dan Song , Guanzheng Wang , Guangfeng Liu , Chengxia Zhang , Bin Lv , Yuan Ni , Guotong Xie

{"title":"Age and gender-related changes in choroidal thickness: Insights from deep learning analysis of swept-source OCT images","authors":"Dan Song , Guanzheng Wang , Guangfeng Liu , Chengxia Zhang , Bin Lv , Yuan Ni , Guotong Xie","doi":"10.1016/j.pdpdt.2025.104511","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>The choroid is a vital vascular layer of the eye, essential for maintaining ocular health. Understanding its structural variations, particularly choroidal thickness (CT), is crucial for the early detection of diseases, such as age-related macular degeneration (AMD), high myopia (HM), and diabetes mellitus (DM). Recent advancements in deep learning have significantly improved the segmentation and measurement of choroidal layers.</div></div><div><h3>Objective</h3><div>This study aims to investigate age- and gender-related changes in CT and its components through deep learning analysis of swept-source optical coherence tomography (SS-OCT) images.</div></div><div><h3>Methods</h3><div>A total of 262 participants (136 females and 126 males) were recruited from Peking University International Hospital. Exclusion criteria included ocular pathologies and systemic conditions. SS-OCT was utilized for CT, Sattler layer-choriocapillaris complex thickness (SLCCT), and Haller layer thickness (HLT) measurements. auto-measurement method, based on deep learning algorithms, ensured accuracy. Ethics approval and informed consent were obtained from all participants.</div></div><div><h3>Findings</h3><div>Significant thinning of CT and SLCCT was observed after the age of 60, with HLT declining after the age of 30. Females exhibited marked thinning between the ages of 40 and 50, while males began to show thinning at age 60.</div></div><div><h3>Conclusion and Implications</h3><div>This research highlights age-related changes in choroidal thickness, with a particular emphasis on gender differences. The findings suggest that females experience earlier thinning, potentially attributable to hormonal changes. Additionally, the study validates the efficiency of deep learning algorithms in measuring choroidal thickness, thereby enhancing the reliability of clinical practice.</div></div>","PeriodicalId":20141,"journal":{"name":"Photodiagnosis and Photodynamic Therapy","volume":"52 ","pages":"Article 104511"},"PeriodicalIF":3.1000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Photodiagnosis and Photodynamic Therapy","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1572100025000419","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

The choroid is a vital vascular layer of the eye, essential for maintaining ocular health. Understanding its structural variations, particularly choroidal thickness (CT), is crucial for the early detection of diseases, such as age-related macular degeneration (AMD), high myopia (HM), and diabetes mellitus (DM). Recent advancements in deep learning have significantly improved the segmentation and measurement of choroidal layers.

Objective

This study aims to investigate age- and gender-related changes in CT and its components through deep learning analysis of swept-source optical coherence tomography (SS-OCT) images.

Methods

A total of 262 participants (136 females and 126 males) were recruited from Peking University International Hospital. Exclusion criteria included ocular pathologies and systemic conditions. SS-OCT was utilized for CT, Sattler layer-choriocapillaris complex thickness (SLCCT), and Haller layer thickness (HLT) measurements. auto-measurement method, based on deep learning algorithms, ensured accuracy. Ethics approval and informed consent were obtained from all participants.

Findings

Significant thinning of CT and SLCCT was observed after the age of 60, with HLT declining after the age of 30. Females exhibited marked thinning between the ages of 40 and 50, while males began to show thinning at age 60.

Conclusion and Implications

This research highlights age-related changes in choroidal thickness, with a particular emphasis on gender differences. The findings suggest that females experience earlier thinning, potentially attributable to hormonal changes. Additionally, the study validates the efficiency of deep learning algorithms in measuring choroidal thickness, thereby enhancing the reliability of clinical practice.

查看原文本刊更多论文

年龄和性别相关的脉络膜厚度变化：来自扫描源OCT图像深度学习分析的见解。

背景：脉络膜是眼部重要的血管层，对维持眼部健康至关重要。了解其结构变化，特别是脉络膜厚度（CT），对于早期发现诸如年龄相关性黄斑变性（AMD）、高度近视（HM）和糖尿病（DM）等疾病至关重要。深度学习的最新进展显著改善了脉络膜层的分割和测量。目的：本研究旨在通过对扫源光学相干断层扫描（SS-OCT）图像的深度学习分析，探讨CT及其组成部分的年龄和性别相关变化。方法：从北京大学国际医院招募受试者262人，其中女性136人，男性126人。排除标准包括眼部病变和全身状况。SS-OCT用于CT、Sattler层-绒毛膜复合体厚度（SLCCT）和Haller层厚度（HLT）测量。基于深度学习算法的自动测量方法确保了准确性。获得所有参与者的伦理批准和知情同意。结果：60岁后CT和SLCCT明显变薄，30岁后HLT下降。女性在40岁到50岁之间表现出明显的变薄，而男性在60岁开始变薄。结论和意义：本研究强调了脉络膜厚度与年龄相关的变化，特别强调了性别差异。研究结果表明，女性大脑更早变薄，这可能归因于荷尔蒙的变化。此外，该研究验证了深度学习算法在测量脉络膜厚度方面的效率，从而提高了临床实践的可靠性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Photodiagnosis and Photodynamic Therapy ONCOLOGY-

CiteScore

5.80

自引率

24.20%

发文量

509

审稿时长

50 days

期刊介绍： Photodiagnosis and Photodynamic Therapy is an international journal for the dissemination of scientific knowledge and clinical developments of Photodiagnosis and Photodynamic Therapy in all medical specialties. The journal publishes original articles, review articles, case presentations, "how-to-do-it" articles, Letters to the Editor, short communications and relevant images with short descriptions. All submitted material is subject to a strict peer-review process.