Spectral-domain optical coherence tomography (SDOCT) is a noncontact and noninvasive imaging technology offering three-dimensional (3-D), objective, and quantitative assessment of optic nerve head (ONH) in human eyes in vivo. The image quality of SDOCT scans is crucial for an accurate and reliable interpretation of ONH structure and for further detection of diseases. Traditionally, signal strength (SS) is used as an index to include or exclude SDOCT scans for further analysis. However, it is insufficient to assess other image quality issues such as off-centration, out of registration, missing data, motion artifacts, mirror artifacts, or blurriness, which require specialized knowledge in SDOCT for such assessment. We proposed a deep learning system (DLS) as an automated tool for filtering out ungradable SDOCT volumes. In total, 5599 SDOCT ONH volumes were collected for training (80%) and primary validation (20%). Other 711 and 298 volumes from two independent datasets, respectively, were used for external validation. An SDOCT volume was labeled as ungradable when SS was < 5 or when any artifacts influenced the measurement circle or > 25 % of the peripheral area. Artifacts included (1) off-centration, (2) out of registration, (3) missing signal, (4) motion artifacts, (5) mirror artifacts, and (6) blurriness. An SDOCT volume was labeled as gradable when SS was ≥ 5 , and there was an absence of any artifacts or artifacts only influenced < 25 % peripheral area but not the retinal nerve fiber layer calculation circle. We developed and validated a 3-D DLS based on squeeze-and-excitation ResNeXt blocks and experimented with different training strategies. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy were calculated to evaluate the performance. Heatmaps were generated by gradient-weighted class activation map. Our findings show that the presented DLS achieved a good performance in both primary and external validations, which could potentially increase the efficiency and accuracy of SDOCT volumetric scans quality control by filtering out ungradable ones automatically.

中文翻译：

---

用于区分不可分级光学相干断层扫描三维体积视盘扫描的人工智能深度学习算法。

谱域光学相干断层扫描 (SDOCT) 是一种非接触式、非侵入性成像技术，可对人眼体内视神经乳头 (ONH) 进行三维 (3-D)、客观和定量评估。SDOCT 扫描的图像质量对于准确可靠地解释 ONH 结构以及进一步检测疾病至关重要。传统上，信号强度 (SS) 被用作包含或排除 SDOCT 扫描的指标，以供进一步分析。然而，它不足以评估其他图像质量问题，例如偏心、未配准、数据丢失、运动伪影、镜像伪影或模糊，这些问题需要 SDOCT 的专业知识才能进行此类评估。我们提出了一种深度学习系统（DLS）作为过滤不可分级的 SDOCT 卷的自动化工具。总共收集了 5599 个 SDOCT ONH 卷用于训练 (80%) 和初步验证 (20%)。来自两个独立数据集的其他 711 卷和 298 卷分别用于外部验证。当 SS < 5 或任何伪影影响测量圈或 > 25% 的外围区域时，SDOCT 体积被标记为不可分级。伪影包括 (1) 偏心、(2) 未配准、(3) 信号丢失、(4) 运动伪影、(5) 镜像伪影和 (6) 模糊。当 SS ≥ 5 时，SDOCT 体积被标记为可分级，并且不存在任何伪影或伪影仅影响 < 25% 的周边区域，但不影响视网膜神经纤维层计算圈。我们开发并验证了基于挤压和激励 ResNeXt 模块的 3-D DLS，并尝试了不同的训练策略。计算受试者工作特征曲线下面积 (AUC)、敏感性、特异性和准确性来评估性能。热图是通过梯度加权类激活图生成的。我们的研究结果表明，所提出的 DLS 在主要验证和外部验证中都取得了良好的性能，这可能通过自动过滤掉不可分级的扫描来提高 SDOCT 体积扫描质量控制的效率和准确性。