文献速递眼底病与葡萄膜炎

基于深度学习在OCT中全自动检测和量化黄斑积液

Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning.
PubMed 文献 · Ophthalmology · 2017-12-08

本研究开发并验证了一种基于深度学习的全自动方法,用于在常规OCT图像中检测和量化黄斑积液。临床数据集包括新生血管性年龄相关性黄斑变性、糖尿病性黄斑水肿和视网膜静脉阻塞患者共1200个OCT体数据。该方法对层内囊样积液和视网膜下积液的检测均达到高准确度,与人工专家评估高度一致。

要点

  • 深度学习法检测层内囊样积液的AUC为0.94,精确率0.91,召回率0.84。
  • 检测视网膜下积液的AUC为0.92,精确率0.61,召回率0.81。
  • 自动与人工积液量化的平均皮尔逊相关系数:层内囊样积液0.90,视网膜下积液0.96。

核心结论

  • 深度学习在视网膜图像分析中对最常见的渗出性黄斑疾病和OCT设备实现了出色的视网膜积液类型鉴别检测准确度。
  • 积液的量化与人工专家评估达到高度一致性。
  • 对临床常规视网膜OCT图像的全自动分析为改善眼科研究和临床实践中视网膜诊断的准确性和可靠性提供了有前景的方向。

研究设计与样本

  • 诊断性技术开发研究。
  • 临床数据集用于积液检测,包括新生血管性年龄相关性黄斑变性400例、糖尿病性黄斑水肿400例和视网膜静脉阻塞400例患者的1200个OCT体数据,分别使用Zeiss Cirrus设备600个和Heidelberg Spectralis设备600个采集。
  • 开发了基于深度学习的方法自动检测和量化层内囊样积液和视网膜下积液。
  • 以2名设盲阅片中心分级者的手动共识读片为参考,评估算法准确定位和量化积液范围的性能。

主要发现

  • 全自动深度学习方法对3种黄斑病变的层内囊样积液检测和量化达到最佳准确度,平均AUC为0.94(范围0.91-0.97),平均精确率0.91,平均召回率0.84。
  • 视网膜下积液的检测和测量也高度准确,AUC为0.92(范围0.86-0.98),平均精确率0.61,平均召回率0.81,在新生血管性年龄相关性黄斑变性和视网膜静脉阻塞中表现优于糖尿病性黄斑水肿,后者在研究人群中较少见。
  • 自动与手动积液定位和量化之间确认高度线性相关,层内囊样积液的平均皮尔逊相关系数为0.90,视网膜下积液为0.96。

关键数值与推荐

  • 层内囊样积液检测:平均AUC 0.94(范围0.91-0.97),平均精确率0.91,平均召回率0.84。
  • 视网膜下积液检测:AUC 0.92(范围0.86-0.98),平均精确率0.61,平均召回率0.81。
  • 自动与手动量化相关性:层内囊样积液平均皮尔逊相关系数0.90,视网膜下积液0.96。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 视网膜下积液检测在糖尿病性黄斑水肿中表现较差,原文指出糖尿病性黄斑水肿在研究人群中较少见。
  • 原文未报告其他局限性。

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: Development and validation of a fully automated method to detect and quantify macular fluid in conventional OCT images. DESIGN: Development of a diagnostic modality. PARTICIPANTS: The clinical dataset for fluid detection consisted of 1200 OCT volumes of patients with neovascular age-related macular degeneration (AMD, n = 400), diabetic macular edema (DME, n = 400), or retinal vein occlusion (RVO, n = 400) acquired with Zeiss Cirrus (Carl Zeiss Meditec, Dublin, CA) (n = 600) or Heidelberg Spectralis (Heidelberg Engineering, Heidelberg, Germany) (n = 600) OCT devices. METHODS: A method based on deep learning to automatically detect and quantify intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) was developed. The performance of the algorithm in accurately identifying fluid localization and extent was evaluated against a manual consensus reading of 2 masked reading center graders. MAIN OUTCOME MEASURES: Performance of a fully automated method to accurately detect, differentiate, and quantify intraretinal and SRF using area under the receiver operating characteristics curves, precision, and recall. RESULTS: The newly designed, fully automated diagnostic method based on deep learning achieved optimal accuracy for the detection and quantification of IRC for all 3 macular pathologies with a mean accuracy (AUC) of 0.94 (range, 0.91-0.97), a mean precision of 0.91, and a mean recall of 0.84. The detection and measurement of SRF were also highly accurate with an AUC of 0.92 (range, 0.86-0.98), a mean precision of 0.61, and a mean recall of 0.81, with superior performance in neovascular AMD and RVO compared with DME, which was represented rarely in the population studied. High linear correlation was confirmed between automated and manual fluid localization and quantification, yielding an average Pearson's correlation coefficient of 0.90 for IRC and of 0.96 for SRF. CONCLUSIONS: Deep learning in retinal image analysis achieves excellent accuracy for the differential detection of retinal fluid types across the most prevalent exudative macular diseases and OCT devices. Furthermore, quantification of fluid achieves a high level of concordance with manual expert assessment. Fully automated analysis of retinal OCT images from clinical routine provides a promising horizon in improving accuracy and reliability of retinal diagnosis for research and clinical practice in ophthalmology.

来源:Ophthalmology,查看原文。版权归原作者所有。

引用

  1. Schlegl T, Waldstein SM, Bogunovic H, et al. Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning. Ophthalmology. 2017. PMID: 29224926. doi:10.1016/j.ophtha.2017.10.031

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。