基于人工智能的定量分析识别临床显著重度早产儿视网膜病变的评估
本研究收集2801名婴儿的9882次检查共54626张眼底照片,用深度学习算法生成1-100分的DeepROP评分,评估其检测临床显著重度早产儿视网膜病变(ROP)的能力。DeepROP评分检测1型ROP的AUC为0.981,检测2型ROP的AUC为0.986,与专家严重度排序显著相关(相关系数0.758,P<0.001)。以35分为转诊截断值时,捕获全部重度ROP并排除87.6%无或轻度ROP患眼。
要点
- DeepROP评分检测1型ROP的AUC为0.981,检测2型ROP的AUC为0.986。
- DeepROP评分与专家整体严重度排序显著相关(相关系数0.758,P<0.001)。
- 假设转诊截断值35分时,捕获全部重度ROP并排除87.6%无或轻度ROP患眼。
核心结论
- DeepROP评分是客观定量的ROP严重度指标,在自动检测临床显著重度ROP方面有潜力。
研究设计与样本
- 回顾性分析2801名婴儿的9882次检查共54626张眼底照片,以三次独立图像分级组合生成标准面板诊断。
- 所有图像经深度学习算法分析,生成1-100分的视网膜血管异常定量评分(DeepROP评分)。
主要发现
- 共56次检查(0.6%)为1型ROP,54次检查(0.5%)为2型ROP。
- DeepROP评分检测1型ROP的AUC为0.981,检测2型ROP的AUC为0.986。
- DeepROP评分与50次检查的专家整体严重度排序显著相关(相关系数0.758,P<0.001)。
- 假设转诊截断值35分时,捕获全部1型和2型ROP,并排除8562眼(87.6%)无或轻度ROP。
关键数值与推荐
- DeepROP评分采用1至100分标度定量评估视网膜血管异常。
- 假设转诊截断值为35分时,重度ROP(1型和2型)全部被捕获,87.6%无或轻度ROP眼被排除。
临床怎么用
- DeepROP评分可作为客观定量指标辅助识别需转诊的临床显著重度ROP。
- 假设截断值35分在研究中显示高敏感性和特异性,但需进一步验证后用于临床决策。
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 evaluate the screening potential of a deep learning algorithm-derived severity score by determining its ability to detect clinically significant severe retinopathy of prematurity (ROP). METHODS: Fundus photographs were collected, and standard panel diagnosis was generated for each examination by combining three independent image-based gradings. All images were analyzed using a deep learning algorithm, and a quantitative assessment of retinal vascular abnormality (DeepROP score) was assigned on a 1 to 100 scale. The area under the receiver operating curve and distribution pattern of all diagnostic parameters and categories of ROP were analyzed. The correlation between the DeepROP score and expert rank ordering according to overall ROP severity of 50 examinations was calculated. RESULTS: A total of 9,882 individual examinations with 54,626 images from 2,801 infants were analyzed. Fifty-six examinations (0.6%) demonstrated Type 1 ROP and 54 examinations (0.5%) demonstrated Type 2 ROP. The DeepROP score had an area under the receiver operating curve of 0.981 for detecting Type 1 ROP and 0.986 for Type 2 ROP. There was a statistically significant correlation between the expert rank ordering of overall disease severity and the DeepROP score (correlation coefficient 0.758, P < 0.001). When hypothetical referral cutoff score of 35 was selected, all cases of severe ROP (Type 1 and Type 2 ROP) was captured and 8,562 eyes (87.6%) with no or mild ROP were excluded. CONCLUSION: The DeepROP score determined by deep learning algorithm was an objective and quantitative indicator for the severity of ROP, and it had potential in automated detecting clinically significant severe ROP.
引用
- Li J, Huang K, Ju R, et al. EVALUATION OF ARTIFICIAL INTELLIGENCE-BASED QUANTITATIVE ANALYSIS TO IDENTIFY CLINICALLY SIGNIFICANT SEVERE RETINOPATHY OF PREMATURITY. Retina. 2022. PMID: 34387234. doi:10.1097/IAE.0000000000003284
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。