基于彩色眼底照相预测年龄相关性眼病研究严重程度分级的年龄相关性黄斑变性深度学习算法
本研究基于3654名年龄相关性眼病研究参与者的120656张人工分级彩色眼底图像,开发了13类(9个AREDS步骤、3个晚期AMD阶段、1个不可分级)的深度学习分类算法,并在5555张KORA人群研究图像中验证。在AREDS测试集中,6种神经网络集成达到二次加权κ值92%(95%CI 89%-92%)和总体准确率63.3%;在KORA研究中,限制年龄>55岁并排除其他视网膜病变后,加权κ值升至50%,算法检出84.2%的明确早或晚期AMD图像、94.3%的健康图像分类正确。
要点
- 算法在AREDS测试集预测13类的二次加权κ值为92%(95%CI 89%-92%),总体准确率63.3%。
- 在KORA数据集中限制年龄>55岁并排除其他视网膜病变后,加权κ值50%,非加权κ值63%。
- 算法检出84.2%的明确早或晚期AMD图像,94.3%的健康眼底图像被正确分类。
核心结论
- 深度学习算法的加权κ值在AREDS研究中优于人类分级者,适用于对年龄>55岁个体的其他数据集AMD眼底图像进行分类。
研究设计与样本
- 基于3654名年龄相关性眼病研究参与者的120656张人工分级彩色眼底图像开发AMD分类算法,参与者在招募时>55岁且排除非AMD的威胁视力疾病。
- 在KORA人群研究的5555张眼底图像中评估算法性能。
- 定义13个类别(9个AREDS步骤、3个晚期AMD阶段、1个不可分级图像),训练多种卷积深度学习架构,采用网络架构集成提高预测准确性。
- 主要结局指标为预测分类与专家人工分级之间一致性的κ统计量和准确率。
主要发现
- 6种不同神经网络架构的集成在AREDS测试集中预测13个类别,二次加权κ值为92%(95%CI 89%-92%),总体准确率63.3%。
- 在独立KORA数据集中,被错误分类为AMD的图像主要源于年轻个体中观察到的黄斑反射。
- 将KORA分析限制于年龄>55岁个体并预先排除其他视网膜病变后,加权κ值和非加权κ值分别增至50%和63%。
- 算法检出所有具有明确早或晚期AMD体征的眼底图像中的84.2%,94.3%的健康眼底图像被正确分类。
关键数值与推荐
- 13个分类类别包括9个AREDS步骤、3个晚期AMD阶段和1个不可分级图像类别。
- AREDS测试集:二次加权κ值92%(95%CI 89%-92%),总体准确率63.3%。
- KORA数据集限制年龄>55岁并排除其他视网膜病变后:加权κ值50%,非加权κ值63%。
- 算法对明确早或晚期AMD眼底图像的检出率为84.2%,健康眼底图像正确分类率为94.3%。
临床怎么用
- 作者结论认为该深度学习算法适用于对年龄>55岁个体的其他数据集AMD眼底图像进行分类。
局限性
- 在独立KORA数据集中,被错误分类为AMD的图像主要源于年轻个体中观察到的黄斑反射。
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: Age-related macular degeneration (AMD) is a common threat to vision. While classification of disease stages is critical to understanding disease risk and progression, several systems based on color fundus photographs are known. Most of these require in-depth and time-consuming analysis of fundus images. Herein, we present an automated computer-based classification algorithm. DESIGN: Algorithm development for AMD classification based on a large collection of color fundus images. Validation is performed on a cross-sectional, population-based study. PARTICIPANTS: We included 120 656 manually graded color fundus images from 3654 Age-Related Eye Disease Study (AREDS) participants. AREDS participants were >55 years of age, and non-AMD sight-threatening diseases were excluded at recruitment. In addition, performance of our algorithm was evaluated in 5555 fundus images from the population-based Kooperative Gesundheitsforschung in der Region Augsburg (KORA; Cooperative Health Research in the Region of Augsburg) study. METHODS: We defined 13 classes (9 AREDS steps, 3 late AMD stages, and 1 for ungradable images) and trained several convolution deep learning architectures. An ensemble of network architectures improved prediction accuracy. An independent dataset was used to evaluate the performance of our algorithm in a population-based study. MAIN OUTCOME MEASURES: κ Statistics and accuracy to evaluate the concordance between predicted and expert human grader classification. RESULTS: A network ensemble of 6 different neural net architectures predicted the 13 classes in the AREDS test set with a quadratic weighted κ of 92% (95% confidence interval, 89%-92%) and an overall accuracy of 63.3%. In the independent KORA dataset, images wrongly classified as AMD were mainly the result of a macular reflex observed in young individuals. By restricting the KORA analysis to individuals >55 years of age and prior exclusion of other retinopathies, the weighted and unweighted κ increased to 50% and 63%, respectively. Importantly, the algorithm detected 84.2% of all fundus images with definite signs of early or late AMD. Overall, 94.3% of healthy fundus images were classified correctly. CONCLUSIONS: Our deep learning algoritm revealed a weighted κ outperforming human graders in the AREDS study and is suitable to classify AMD fundus images in other datasets using individuals >55 years of age.
引用
- Grassmann F, Mengelkamp J, Brandl C, et al. A Deep Learning Algorithm for Prediction of Age-Related Eye Disease Study Severity Scale for Age-Related Macular Degeneration from Color Fundus Photography. Ophthalmology. 2018. PMID: 29653860. doi:10.1016/j.ophtha.2018.02.037
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。