Heslinga Friso G, Alberti Mark, Pluim Josien P W, Cabrerizo Javier, Veta Mitko
Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
Ophthalmology Department, Rigshospitalet - Glostrup, Copenhagen, Denmark.
Transl Vis Sci Technol. 2020 Aug 21;9(2):48. doi: 10.1167/tvst.9.2.48. eCollection 2020 Aug.
We developed a method to automatically locate and quantify graft detachment after Descemet's membrane endothelial keratoplasty (DMEK) in anterior segment optical coherence tomography (AS-OCT) scans.
A total of 1280 AS-OCT B-scans were annotated by a DMEK expert. Using the annotations, a deep learning pipeline was developed to localize scleral spur, center the AS-OCT B-scans and segment the detached graft sections. Detachment segmentation model performance was evaluated per B-scan by comparing (1) length of detachment and (2) horizontal projection of the detached sections with the expert annotations. Horizontal projections were used to construct graft detachment maps. All final evaluations were done on a test set that was set apart during training of the models. A second DMEK expert annotated the test set to determine interrater performance.
Mean scleral spur localization error was 0.155 mm, whereas the interrater difference was 0.090 mm. The estimated graft detachment lengths were in 69% of the cases within a 10-pixel (∼150 µm) difference from the ground truth (77% for the second DMEK expert). Dice scores for the horizontal projections of all B-scans with detachments were 0.896 and 0.880 for our model and the second DMEK expert, respectively.
Our deep learning model can be used to automatically and instantly localize graft detachment in AS-OCT B-scans. Horizontal detachment projections can be determined with the same accuracy as a human DMEK expert, allowing for the construction of accurate graft detachment maps.
Automated localization and quantification of graft detachment can support DMEK research and standardize clinical decision-making.
我们开发了一种方法，用于在前节光学相干断层扫描（AS-OCT）图像中自动定位和量化Descemet膜内皮角膜移植术（DMEK）后移植片脱离情况。
一名DMEK专家对总共1280幅AS-OCT B扫描图像进行了标注。利用这些标注，开发了一个深度学习流程，用于定位巩膜突、将AS-OCT B扫描图像居中并分割脱离的移植片部分。通过将（1）脱离长度和（2）脱离部分的水平投影与专家标注进行比较，对每个B扫描图像的脱离分割模型性能进行评估。水平投影用于构建移植片脱离图。所有最终评估均在模型训练期间留出的测试集上进行。另一名DMEK专家对测试集进行标注，以确定评分者间的一致性。
巩膜突定位的平均误差为0.155毫米，而评分者间差异为0.090毫米。在69%的病例中，估计的移植片脱离长度与真实值的差异在10像素（约150微米）以内（第二名DMEK专家的准确率为77%）。对于所有有脱离情况的B扫描图像，我们的模型和第二名DMEK专家水平投影的Dice分数分别为0.896和0.880。
我们的深度学习模型可用于在AS-OCT B扫描图像中自动且即时地定位移植片脱离情况。水平脱离投影的确定精度与DMEK专家相当，从而能够构建准确的移植片脱离图。
移植片脱离的自动定位和量化可为DMEK研究提供支持，并使临床决策标准化。
