基于深度学习的黄斑光学相干断层扫描图像质量评估:一项多中心研究
本研究开发并外部测试深度学习模型,用于评估Cirrus和Spectralis设备的三维黄斑OCT扫描图像质量。回顾性收集2277份Cirrus和1557份Spectralis扫描用于训练、微调和内部验证,并在来自新加坡、印度、澳大利亚和香港的多个外部数据集上测试。模型在内部验证中AUC分别为0.930和0.906,外部测试中表现稳健,可用于过滤不可分级扫描并整合疾病检测流程。
要点
- 深度学习模型可评估Cirrus和Spectralis三维黄斑OCT扫描的可分级性。
- 内部验证AUC分别为0.930(Cirrus)和0.906(Spectralis)。
- 外部测试AUC范围分别为0.832-0.930(Cirrus)和0.891-0.962(Spectralis)。
核心结论
- 模型可用于过滤不可分级的三维扫描,并与疾病检测深度学习模型结合,实现全自动眼病检测流程。
研究设计与样本
- 回顾性收集2277份Cirrus三维扫描和1557份Spectralis三维扫描,按70%训练、10%微调、20%内部验证划分,数据来自香港中文大学眼科中心及香港眼科医院。
- 纳入多种眼病(如糖尿病黄斑水肿、年龄相关性黄斑变性、息肉状脉络膜血管病变、病理性近视)及成人和儿童正常眼扫描。
- 两名分级者依据标准化标准将每份三维扫描标记为可分级或不可分级。
- Cirrus三维扫描使用三维残差网络(ResNet)-18,Spectralis三维扫描使用基于ResNet-18的多实例学习流程。
- 两个模型分别在来自新加坡的三个未见Cirrus数据集和来自印度、澳大利亚及香港的五个未见Spectralis数据集上进行外部测试。
主要发现
- 内部验证中,模型评估Cirrus三维扫描的AUC为0.930(95%CI 0.885-0.976),评估Spectralis三维扫描的AUC为0.906(95%CI 0.863-0.948)。
- 外部测试中,Cirrus模型AUC范围为0.832(95%CI 0.730-0.934)至0.930(95%CI 0.906-0.953)。
- 外部测试中,Spectralis模型AUC范围为0.891(95%CI 0.836-0.945)至0.962(95%CI 0.918-1.000)。
临床怎么用
- 原文未据此给出推荐。
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
AIMS: To develop and externally test deep learning (DL) models for assessing the image quality of three-dimensional (3D) macular scans from Cirrus and Spectralis optical coherence tomography devices. METHODS: We retrospectively collected two data sets including 2277 Cirrus 3D scans and 1557 Spectralis 3D scans, respectively, for training (70%), fine-tuning (10%) and internal validation (20%) from electronic medical and research records at The Chinese University of Hong Kong Eye Centre and the Hong Kong Eye Hospital. Scans with various eye diseases (eg, diabetic macular oedema, age-related macular degeneration, polypoidal choroidal vasculopathy and pathological myopia), and scans of normal eyes from adults and children were included. Two graders labelled each 3D scan as gradable or ungradable, according to standardised criteria. We used a 3D version of the residual network (ResNet)-18 for Cirrus 3D scans and a multiple-instance learning pipline with ResNet-18 for Spectralis 3D scans. Two deep learning (DL) models were further tested via three unseen Cirrus data sets from Singapore and five unseen Spectralis data sets from India, Australia and Hong Kong, respectively. RESULTS: In the internal validation, the models achieved the area under curves (AUCs) of 0.930 (0.885-0.976) and 0.906 (0.863-0.948) for assessing the Cirrus 3D scans and Spectralis 3D scans, respectively. In the external testing, the models showed robust performance with AUCs ranging from 0.832 (0.730-0.934) to 0.930 (0.906-0.953) and 0.891 (0.836-0.945) to 0.962 (0.918-1.000), respectively. CONCLUSIONS: Our models could be used for filtering out ungradable 3D scans and further incorporated with a disease-detection DL model, allowing a fully automated eye disease detection workflow.
引用
- Tang Z, Wang X, Ran AR, et al. Deep learning-based image quality assessment for optical coherence tomography macular scans: a multicentre study. Br J Ophthalmol. 2024. PMID: 39033014. doi:10.1136/bjo-2023-323871
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。