Artificial intelligence assisted panoramic Optical Coherence Tomography Angiography for Retinopathy of Prematurity

项目总结 该项目的长期目标是确定光学相干断层扫描(OCT)和OCT 血管造影术(OCTA)有助于提高诊断的准确性和客观性，有利于早期干预和提高疗效。 早产儿视网膜病变(ROP)的结局。国际共识和国家卫生研究所(NIH) 过去30年资助的临床试验确定了表型分类、自然病史、预后、 和ROP的管理。然而，众所周知，由于检眼镜的主观性 考试与考官之间存在系统性偏差，多数有显著差异的处理方式 现实世界中存在严重的ROP。这导致治疗不足(以及由于视网膜而导致的不良结果 过度治疗(使新生儿暴露在治疗的眼睛和全身风险中)。粗略地 每年有20,000名婴儿因ROP而患上视网膜脱离(RD)，有强有力的证据表明，大多数 这些都是可以预防的。成人视网膜血管疾病，最显著的是糖尿病视网膜病变(DR)、OCT和OCTA 可以检测和量化糖尿病黄斑水肿(DME)和视网膜新生血管等疾病特征 (NV)在临床发现之前，使早期治疗成为可能，并降低RD致盲的风险。 然而，评估这项技术在新生儿中的使用需要高速和便携技术，并且 商业上可用的手持OCT对于超宽带(UWF)OCT和OCTA成像来说太慢了。 几个小组(包括我们自己的)已经发表了使用100到200 khz扫描原型的初步结果- 源(SS)OCT系统，然而，由于缺乏固定，一致的数据获取仍然具有挑战性 以及随后清醒的新生儿的运动，这限制了对该疗法潜在益处的评估 这群人中的技术。最近，人们对使用人工智能(AI)非常感兴趣 (特别是深度学习)，它依赖于高速图形处理单元(GPU)来提供实时 OCT图像处理、分割和跟踪。此应用程序解决了以下两个方面的根本差距 知识：(1)我们能否通过开发更快的超广域来克服技术挑战 View SS-OCT系统与支持GPU的DL软件系统相结合，可在 新生儿？(2)ROP的量化客观指标是否会提高ROP诊断和检测的客观性 疾病进展的亚临床迹象，可能使早期干预和改善预后成为可能 未来。通过利用我们机构的OCT、AI和ROP专业知识，我们将在三个方面解决这些问题 具体目标：(1)开发一套超高速、手持、全景超宽带OCT/OCTA系统。(2) 开发实时GPU加速的智能图像采集软件。(3)评价其临床意义。 OCT衍生的生物标志物。将这项技术成功地转化为ROP人群可以提高 ROP诊断的准确性和客观性，并导致早期干预和改善患者的预后 有严重的ROP。

PROJECT SUMMARY The long-term goal of this project is to determine whether optical coherence tomography (OCT) and OCT angiography (OCTA) might lead more accurate and objective diagnosis, earlier intervention, and improved outcomes in retinopathy of prematurity (ROP). International consensus and National Institute of Health (NIH) funded clinical trials over the last 30 years have defined the phenotypic classifications, natural history, prognosis, and management of ROP. However, it is well established that due to the subjectivity of the ophthalmoscopic examination, and systematic bias between examiners, there is significant variation in treatment of the most severe forms of ROP in the real world. This leads to both under-treatment (and poor outcomes due to retinal detachment) and over-treatment (exposing neonates to the ocular and systemic risks of treatment). Roughly 20,000 babies per year develop retinal detachments (RD) due to ROP and there is strong evidence that most of these are preventable. In adult retinal vascular diseases, most notably diabetic retinopathy (DR), OCT and OCTA can detect and quantify disease features such as diabetic macular edema (DME) and retinal neovascularization (NV) before they are noted clinically, enabling earlier treatment and reducing the risk of blindness from RD. However, evaluating the use of this technology in neonates requires high speed and portable technology, and the commercially available handheld OCTs are too slow for ultra-widefield (UWF) OCT and OCTA imaging. Several groups (including our own) have published preliminary results using prototype 100 to 200 kHz swept- source (SS) OCT systems, however consistent data acquisition remains challenging due to the lack of fixation and subsequent motion in an awake neonate, which has limited the evaluation of the potential benefits of the technology in this population. Recently, there has been much interest in using artificial intelligence (AI) (specifically deep learning), which relies on high speed graphics processing units (GPUs) to provide real time OCT image processing, segmentation, and tracking. This application addresses 2 fundamental gaps in knowledge: (1) Can we overcome the technical challenges through the development of a faster ultrawide-field view SS-OCT system coupled with a GPU-enabled DL software system to enable consistent data acquisition in neonates? (2) Would quantitative objective metrics of ROP improve objectivity of ROP diagnosis and detect subclinical signs of disease progression which may enable earlier intervention and improved outcomes in the future. By leveraging our institution’s OCT, AI, and ROP expertise, we will address these questions in three specific aims: (1) Develop an ultra-high speed, handheld, panoramic ultra-widefield OCT/OCTA system. (2) Develop real time GPU accelerated intelligent image acquisition software. (3) Evaluate the clinical significance OCT derived biomarkers. Successful translation of this technology to the ROP population could improve the accuracy and objectivity of ROP diagnosis, and lead to earlier intervention and improved outcomes in patients with severe ROP.