■通过深度学习(DL)模型的遮挡分析,在结构和功能之间建立可推广的逐点空间关系,以预测3维(3D)OCT扫描的视野(VF)敏感性。
■回顾性横断面研究。
■1129例患者共2151只眼。
■对DL模型进行了训练,以通过12915对OCT-VF对的视神经头(ONH)的3D谱域OCT图像预测24-2标准自动视野检查的52VF敏感性。使用遮挡分析,在由996对OCT-VF对组成的单独测试集中,系统评估了覆盖ONH240×240×31.25μm区域的每个单独立方体对模型预测的贡献.在简单的平移(在X轴和Y轴移动以匹配ONH中心)之后,得出组t统计图,以可视化组内每个VF测试点的统计学显著ONH区域.此分析可以了解每个超体素(覆盖整个4.32×4.32×1.125mmONH立方体的240×240×31.25μm)在预测特定患者组的VF测试点中的重要性。
■对应于每个VF测试点的ONH处的区域以及前者对后者的影响。
■将测试集分为2组,健康至早期青光眼组(792对OCT-VF,VF平均偏差[MD]:-1.32±1.90分贝[dB])和中度至晚期青光眼组(204对OCT-VF,VFMD:-17.93±7.68dB)。二维组t统计图(x,Y投影)为两组生成,将相关的ONH区域分配给视野测试点。在每个测试点确定的用于VF敏感性预测的有影响的结构位置与现有知识和对结构-功能空间关系的理解很好地吻合。
■这项研究成功地可视化了基于OCT的结构和基于VF的功能之间的逐点空间关系的全球趋势,而无需对OCT进行先验知识或分割。揭示的空间相关性与先前发布的映射一致。这提供了在不应用任何先验知识的情况下从训练过的机器学习模型中学习的可能性,潜在的鲁棒性,没有偏见。
■专有或商业披露可在本文末尾的脚注和披露中找到。
UNASSIGNED: To establish generalizable pointwise spatial relationship between structure and function through occlusion analysis of a deep-learning (DL) model for predicting the visual field (VF) sensitivities from 3-dimensional (3D) OCT scan.
UNASSIGNED: Retrospective cross-sectional study.
UNASSIGNED: A total of 2151 eyes from 1129 patients.
UNASSIGNED: A DL model was trained to predict 52 VF sensitivities of 24-2 standard automated perimetry from 3D spectral-domain OCT images of the optic nerve head (ONH) with 12 915 OCT-VF pairs. Using occlusion analysis, the contribution of each individual cube covering a 240 × 240 × 31.25 μm region of the ONH to the model\'s prediction was systematically evaluated for each OCT-VF pair in a separate test set that consisted of 996 OCT-VF pairs. After simple translation (shifting in x- and y-axes to match the ONH center), group t-statistic maps were derived to visualize statistically significant ONH regions for each VF test point within a group. This analysis allowed for understanding the importance of each super voxel (240 × 240 × 31.25 μm covering the entire 4.32 × 4.32 × 1.125 mm ONH cube) in predicting VF test points for specific patient groups.
UNASSIGNED: The region at the ONH corresponding to each VF test point and the effect of the former on the latter.
UNASSIGNED: The test set was divided to 2 groups, the healthy-to-early-glaucoma group (792 OCT-VF pairs, VF mean deviation [MD]: -1.32 ± 1.90 decibels [dB]) and the moderate-to-advanced-glaucoma group (204 OCT-VF pairs, VF MD: -17.93 ± 7.68 dB). Two-dimensional group t-statistic maps (x, y projection) were generated for both groups, assigning related ONH regions to visual field test points. The identified influential structural locations for VF sensitivity prediction at each test point aligned well with existing knowledge and understanding of structure-function spatial relationships.
UNASSIGNED: This study successfully visualized the global trend of point-by-point spatial relationships between OCT-based structure and VF-based function without the need for prior knowledge or segmentation of OCTs. The revealed spatial correlations were consistent with previously published mappings. This presents possibilities of learning from trained machine learning models without applying any prior knowledge, potentially robust, and free from bias.
UNASSIGNED: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.