Predictive, preventive, and personalized management of retinal fluid via computer-aided detection app for optical coherence tomography scans
Predictive, preventive, and personalized management of retinal fluid via computer-aided detection app for optical coherence tomography scans
复制标题
DOI：
10.1007/s13167-022-00301-5
复制
发表时间：
2022-11-19
期刊：
影响因子：
6.5
通讯作者：
Cheng，Ching-Yu
中科院分区：
文献类型：
--
作者：
Quek，Ten Cheer;Takahashi，Kengo;Cheng，Ching-Yu
目的视网膜积液的计算机辅助检测系统有助于慢性老年性黄斑变性(AMD)和糖尿病视网膜病变(DR)患者的疾病监测和治疗，在疾病发展为湿性AMD或糖尿病黄斑水肿(DME)需要治疗之前，通过早期检测来辅助疾病预防。我们提出了一种基于人工智能的概念验证应用程序，在预测、预防和个性化药物(PPPM)的背景下，帮助预测液体流动，防止液体进展，并在预测、预防和个性化药物(PPPM)的背景下为有视网膜液体并发症风险的患者提供个性化的连续监测。方法该应用程序包括基于卷积神经网络-视觉转换器(CNN-VIT)的分割深度学习(DL)网络，在来自新加坡眼病流行病学(SEED)研究的100个训练图像(扩大到992个图像)的小数据集上进行训练，以及基于CNN的分类网络，该网络基于8497张图像训练，它可以检测流体与非流体光学相干断层扫描(OCT)。结果内部测试结果为83.0%(95%CI = 76.7-89.3%)，骰子得分为90.4%(86.3-94.4%)；外部测试为66.7%(63.5-70.0%)，骰子得分为78.7%(76.0-81.4%)。对我们的分类网络进行的内部测试产生了接收器工作特性曲线下面积为99.18%，约登指数阈值为0.3806；对于外部测试，我们获得了94.55%的AUC，94.98%的准确率和85.73%的F1评分，Youden指数。结论我们开发了一个基于AI的应用程序，使用替代的基于变压器的分割算法，可以潜在地应用于临床，使用PPPM方法进行连续监测，并可以生成回溯性数据，研究AMD和DR的各种治疗方法。我们的应用程序的模块化系统可以根据用户反馈添加更多迭代功能，以实现更有效的监测。算法数据集的进一步研究和放大可能会潜在地提高其在现实世界临床环境中的可用性。
AimsComputer-aided detection systems for retinal fluid could be beneficial for disease monitoring and management by chronic age-related macular degeneration (AMD) and diabetic retinopathy (DR) patients, to assist in disease prevention via early detection before the disease progresses to a “wet AMD” pathology or diabetic macular edema (DME), requiring treatment. We propose a proof-of-concept AI-based app to help predict fluid via a “fluid score”, prevent fluid progression, and provide personalized, serial monitoring, in the context of predictive, preventive, and personalized medicine (PPPM) for patients at risk of retinal fluid complications.MethodsThe app comprises a convolutional neural network–Vision Transformer (CNN-ViT)–based segmentation deep learning (DL) network, trained on a small dataset of 100 training images (augmented to 992 images) from the Singapore Epidemiology of Eye Diseases (SEED) study, together with a CNN-based classification network trained on 8497 images, that can detect fluid vs. non-fluid optical coherence tomography (OCT) scans. Both networks are validated on external datasets.ResultsInternal testing for our segmentation network produced an IoU score of 83.0% (95% CI = 76.7–89.3%) and a DICE score of 90.4% (86.3–94.4%); for external testing, we obtained an IoU score of 66.7% (63.5–70.0%) and a DICE score of 78.7% (76.0–81.4%). Internal testing of our classification network produced an area under the receiver operating characteristics curve (AUC) of 99.18%, and a Youden index threshold of 0.3806; for external testing, we obtained an AUC of 94.55%, and an accuracy of 94.98% and an F1 score of 85.73% with Youden index.ConclusionWe have developed an AI-based app with an alternative transformer-based segmentation algorithm that could potentially be applied in the clinic with a PPPM approach for serial monitoring, and could allow for the generation of retrospective data to research into the varied use of treatments for AMD and DR. The modular system of our app can be scaled to add more iterative features based on user feedback for more efficient monitoring. Further study and scaling up of the algorithm dataset could potentially boost its usability in a real-world clinical setting.