Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
复制标题
DOI：
10.1038/s41598-019-42042-y
复制
发表时间：
2019-04-05
影响因子：
4.6
通讯作者：
Lee, Aaron Y.
中科院分区：
文献类型：
--
作者：
Lee, Cecilia S.;Tyring, Ariel J.;Lee, Aaron Y.
尽管人工智能（AI）取得了进展，但其在医学成像中的应用一直受到专家生成标签的负担和限制。我们使用来自光学相干断层扫描血管造影（OCTA）的图像，这是一种测量视网膜血流的相对较新的成像模式，用于训练AI算法，以从标准光学相干断层扫描（OCT）图像生成流图，超出了能力并绕过了对专家标记的需求。深度学习能够从单一结构OCT图像中推断出血流，其保真度与OCTA相似，并且明显优于专家临床医生（P < 0.00001）。我们的模型允许从现有临床试验和临床实践中收集的大量OCT数据生成流图。这一发现表明了一种新的应用Al医学成像，从而微妙的不同模态之间的重叠被用来成像相同的身体部位和Al是用来生成详细的推断组织功能的结构成像。
Despite advances in artificial intelligence (AI), its application in medical imaging has been burdened and limited by expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures retinal blood flow, to train an Al algorithm to generate flow maps from standard optical coherence tomography (OCT) images, exceeding the ability and bypassing the need for expert labeling. Deep learning was able to infer flow from single structural OCT images with similar fidelity to OCTA and significantly better than expert clinicians (P < 0.00001). Our model allows generating flow maps from large volumes of previously collected OCT data in existing clinical trials and clinical practice. This finding demonstrates a novel application of Al to medical imaging, whereby subtle regularities between different modalities are used to image the same body part and Al is used to generate detailed inferences of tissue function from structure imaging.