文献速递眼底病与葡萄膜炎

验证一种深度学习模型用于自动检测和量化与新生血管性年龄相关性黄斑变性相关的五项OCT关键视网膜特征

Validation of a deep learning model for automatic detection and quantification of five OCT critical retinal features associated with neovascular age-related macular degeneration.
PubMed 文献 · Br J Ophthalmol · 2024-09-20

本研究收集300份新生血管性年龄相关性黄斑变性(nAMD)患眼的OCT容积数据,人工分割五项关键特征并训练基于U-Net的深度学习模型进行自动分割与验证。模型检测积液的每层平均AUC为0.93(±0.04),每容积为0.88(±0.07)。作者认为该全自动分割模型性能达到有经验分级者水平,有助于真实世界研究和临床结构化报告。

要点

  • 模型检测积液的每层平均AUC为0.93(±0.04),每容积为0.88(±0.07)。
  • 自动与人工分割的相关评分(R2)平均为0.89(±0.05)。
  • 平均2D相关评分为0.69(±0.04),平均Dice评分为0.61(±0.10)。

核心结论

  • 作者提出一种针对nAMD五项特征的全自动分割模型,其性能达到有经验分级者水平。
  • 该模型的应用有望为真实世界环境中研究形态学变化和治疗疗效提供机会。
  • 该模型可促进临床结构化报告并减少临床医生评估的主观性。

研究设计与样本

  • 收集300份nAMD患眼的OCT容积数据,对五项nAMD关键特征进行人工分割。
  • 五项特征为:视网膜内液、视网膜下液、视网膜下高反射物质、玻璃膜疣/玻璃膜疣性色素上皮脱离(PED)和新生血管性PED。
  • 训练基于U-Net的深度学习架构进行自动分割,并在隔离数据上评估。
  • 主要结局指标为检测的受试者工作特征曲线(以每层和每容积的曲线下面积AUC汇总)、相关评分、enface地形重叠(以二维(2D)相关评分报告)和Dice系数。

主要发现

  • 模型检测积液的每层平均(±SD)AUC为0.93(±0.04),每容积为0.88(±0.07)。
  • 模型自动与人工分割的相关评分(R2)平均(±SD)为0.89(±0.05)。
  • 平均(±SD)2D相关评分为0.69(±0.04)。
  • 平均(±SD)Dice评分为0.61(±0.10)。

临床怎么用

  • 作者认为该模型的应用可为真实世界环境中研究形态学变化和治疗疗效提供机会。
  • 作者认为该模型可促进临床结构化报告并减少临床医生评估的主观性。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: To develop and validate a deep learning model for the segmentation of five retinal biomarkers associated with neovascular age-related macular degeneration (nAMD). METHODS: 300 optical coherence tomography volumes from subject eyes with nAMD were collected. Images were manually segmented for the presence of five crucial nAMD features: intraretinal fluid, subretinal fluid, subretinal hyperreflective material, drusen/drusenoid pigment epithelium detachment (PED) and neovascular PED. A deep learning architecture based on a U-Net was trained to perform automatic segmentation of these retinal biomarkers and evaluated on the sequestered data. The main outcome measures were receiver operating characteristic curves for detection, summarised using the area under the curves (AUCs) both on a per slice and per volume basis, correlation score, enface topography overlap (reported as two-dimensional (2D) correlation score) and Dice coefficients. RESULTS: The model obtained a mean (±SD) AUC of 0.93 (±0.04) per slice and 0.88 (±0.07) per volume for fluid detection. The correlation score (R2) between automatic and manual segmentation obtained by the model resulted in a mean (±SD) of 0.89 (±0.05). The mean (±SD) 2D correlation score was 0.69 (±0.04). The mean (±SD) Dice score resulted in 0.61 (±0.10). CONCLUSIONS: We present a fully automated segmentation model for five features related to nAMD that performs at the level of experienced graders. The application of this model will open opportunities for the study of morphological changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic and reduce subjectivity in clinicians' assessments.

来源:Br J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Ricardi F, Oakley J, Russakoff D, et al. Validation of a deep learning model for automatic detection and quantification of five OCT critical retinal features associated with neovascular age-related macular degeneration. Br J Ophthalmol. 2024. PMID: 38485214. doi:10.1136/bjo-2023-324647

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。