[论文解读] Mobile Artificial Intelligence Technology for Detecting Macula Edema and Subretinal Fluid on OCT Scans: Initial Results from the DATUM alpha Study

Stephen G. Odaibo, Mikelson MomPremier+4 more|arXiv (Cornell University)|Feb 8, 2019

Retinal Imaging and Analysis参考文献 27被引用 3

一句话总结

本研究评估了Fluid Intelligence，一款基于云的移动人工智能应用程序，可通过分析智能手机拍摄的OCT显示器图像，检测OCT扫描中的黄斑水肿和视网膜下液。在一项包含283份OCT扫描的多中心回顾性分析中，该AI实现了89.3%的加权平均敏感度和81.23%的特异度，证明其作为资源匮乏眼科医疗环境筛查工具的可行性。

ABSTRACT

Artificial Intelligence (AI) is necessary to address the large and growing deficit in retina and healthcare access globally. And mobile AI diagnostic platforms running in the Cloud may effectively and efficiently distribute such AI capability. Here we sought to evaluate the feasibility of Cloud-based mobile artificial intelligence for detection of retinal disease. And to evaluate the accuracy of a particular such system for detection of subretinal fluid (SRF) and macula edema (ME) on OCT scans. A multicenter retrospective image analysis was conducted in which board-certified ophthalmologists with fellowship training in retina evaluated OCT images of the macula. They noted the presence or absence of ME or SRF, then compared their assessment to that obtained from Fluid Intelligence, a mobile AI app that detects SRF and ME on OCT scans. Investigators consecutively selected retinal OCTs, while making effort to balance the number of scans with retinal fluid and scans without. Exclusion criteria included poor scan quality, ambiguous features, macula holes, retinoschisis, and dense epiretinal membranes. Accuracy in the form of sensitivity and specificity of the AI mobile App was determined by comparing its assessments to those of the retina specialists. At the time of this submission, five centers have completed their initial studies. This consists of a total of 283 OCT scans of which 155 had either ME or SRF ("wet") and 128 did not ("dry"). The sensitivity ranged from 82.5% to 97% with a weighted average of 89.3%. The specificity ranged from 52% to 100% with a weighted average of 81.23%. CONCLUSION: Cloud-based Mobile AI technology is feasible for the detection retinal disease. In particular, Fluid Intelligence (alpha version), is sufficiently accurate as a screening tool for SRF and ME, especially in underserved areas. Further studies and technology development is needed.

研究动机与目标

• 解决全球在后极部视网膜专科医生方面的短缺问题，特别是在农村和资源匮乏地区。
• 评估通过移动设备和云计算分发人工智能诊断能力的可行性。
• 评估移动人工智能应用程序（Fluid Intelligence）在与专家眼科医生对比下，检测OCT扫描中视网膜下液和黄斑水肿的准确性。
• 确定拍摄OCT显示器的智能手机图像是否能提供足够的诊断准确性以用于临床筛查。
• 探索移动人工智能作为可扩展、低成本解决方案的潜力，以改善视网膜病变的早期检测。

提出的方法

• 为iOS开发了一款移动人工智能应用程序（Fluid Intelligence），在云端托管的机器学习模型上运行推理。
• 用户拍摄显示在显示器或打印页面上的OCT扫描图像，上传至基于云的人工智能引擎。
• 人工智能模型利用深度学习技术处理图像，以检测是否存在黄斑水肿和视网膜下液。
• 使用NoSQL数据库存储上传至云端的图像，用于推理和审计目的。
• 使用多样化OCT扫描数据集对模型进行训练，并通过云端再训练实现持续更新。
• 开展多中心回顾性分析，由获得认证的视网膜专科医生作为对比的金标准。

实验结果

研究问题

• RQ1 使用智能手机拍摄的OCT扫描图像，移动人工智能应用程序是否能实现检测黄斑水肿和视网膜下液的临床可接受敏感度和特异度？
• RQ2 此类移动人工智能系统的诊断准确性是否在不同临床环境和阅片者专业水平下保持一致？
• RQ3 图像质量、分辨率以及伪影（如眩光、模糊）对真实临床图像采集中人工智能性能的影响如何？
• RQ4 是否能够通过新数据持续更新和改进托管在云端的人工智能模型，而无需本地软件更新？
• RQ5 在初级和社区眼科医疗环境中，移动人工智能在多大程度上可减少不必要的转诊和漏诊？

主要发现

• Fluid Intelligence人工智能应用程序在五个中心的加权平均敏感度为89.3%，表明其在检测黄斑水肿或视网膜下液的真正阳性病例方面能力出色。
• 加权平均特异度为81.23%，各中心间范围从52%至100%，表明假阳性检测存在差异。
• 敏感度在各中心间介于82.5%至97%之间，表明在识别病理病例方面表现一致。
• 在存在大范围融合性玻璃疣或视网膜色素上皮脱离等特征的图像中，假阳性更为常见，这些情况或可通过扩大数据集进行训练优化。
• 图像质量问题（如低分辨率或眩光）导致了假阳性结果，凸显了制定更高质量输入图像标准的必要性。
• 本研究证实，通过智能手机拍摄OCT扫描图像实现的移动人工智能，是向资源匮乏地区分发诊断能力的一种可行且可扩展的方法。