Ophthalmic Engineering & Innovation Laboratory (OEIL), Singapore Eye Research Institute, Singapore National Eye Centre, Singapore; Department of Biomedical Engineering, National University of Singapore, Singapore.
Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
Am J Ophthalmol. 2022 Aug;240:205-216. doi: 10.1016/j.ajo.2022.02.020. Epub 2022 Mar 2.
To assess whether the 3-dimensional (3D) structural configuration of the central retinal vessel trunk and its branches (CRVT&B) could be used as a diagnostic marker for glaucoma.
Retrospective, deep-learning approach diagnosis study.
We trained a deep learning network to automatically segment the CRVT&B from the B-scans of the optical coherence tomography (OCT) volume of the optic nerve head. Subsequently, 2 different approaches were used for glaucoma diagnosis using the structural configuration of the CRVT&B as extracted from the OCT volumes. In the first approach, we aimed to provide a diagnosis using only 3D convolutional neural networks and the 3D structure of the CRVT&B. For the second approach, we projected the 3D structure of the CRVT&B orthographically onto sagittal, frontal, and transverse planes to obtain 3 two-dimensional (2D) images, and then a 2D convolutional neural network was used for diagnosis. The segmentation accuracy was evaluated using the Dice coefficient, whereas the diagnostic accuracy was assessed using the area under the receiver operating characteristic curves (AUCs). The diagnostic performance of the CRVT&B was also compared with that of retinal nerve fiber layer (RNFL) thickness (calculated in the same cohorts).
Our segmentation network was able to efficiently segment retinal blood vessels from OCT scans. On a test set, we achieved a Dice coefficient of 0.81 ± 0.07. The 3D and 2D diagnostic networks were able to differentiate glaucoma from nonglaucoma subjects with accuracies of 82.7% and 83.3%, respectively. The corresponding AUCs for the CRVT&B were 0.89 and 0.90, higher than those obtained with RNFL thickness alone (AUCs ranging from 0.74 to 0.80).
Our work demonstrated that the diagnostic power of the CRVT&B is superior to that of a gold-standard glaucoma parameter, that is, RNFL thickness. Our work also suggested that the major retinal blood vessels form a "skeleton"-the configuration of which may be representative of major optic nerve head structural changes as typically observed with the development and progression of glaucoma.
评估中央视网膜血管主干及其分支(CRVT&B)的三维(3D)结构构象是否可用作青光眼的诊断标志物。
回顾性、深度学习方法诊断研究。
我们训练了一个深度学习网络,从视神经头的光学相干断层扫描(OCT)体积的 B 扫描中自动分割 CRVT&B。随后,使用从 OCT 体积中提取的 CRVT&B 的结构构象,采用两种不同的方法进行青光眼诊断。在第一种方法中,我们旨在仅使用 3D 卷积神经网络和 CRVT&B 的 3D 结构提供诊断。对于第二种方法,我们将 CRVT&B 的 3D 结构正投影到矢状面、正面和横断面上,以获得 3 个二维(2D)图像,然后使用 2D 卷积神经网络进行诊断。使用 Dice 系数评估分割准确性,而使用接收器工作特征曲线(AUC)下的面积评估诊断准确性。还将 CRVT&B 的诊断性能与视网膜神经纤维层(RNFL)厚度(在相同队列中计算)进行了比较。
我们的分割网络能够有效地从 OCT 扫描中分割视网膜血管。在测试集上,我们达到了 0.81±0.07 的 Dice 系数。3D 和 2D 诊断网络能够以 82.7%和 83.3%的准确率区分青光眼和非青光眼患者。CRVT&B 的相应 AUC 分别为 0.89 和 0.90,高于单独使用 RNFL 厚度获得的 AUC(范围为 0.74 至 0.80)。
我们的工作表明,CRVT&B 的诊断能力优于金标准青光眼参数,即 RNFL 厚度。我们的工作还表明,主要的视网膜血管形成了一个“骨架”——其构象可能代表了主要视神经头结构的变化,这些变化通常与青光眼的发展和进展有关。