Corneal endothelium (CE) images provide valuable clinical information regarding the health state of the cornea. Computation of the clinical morphometric parameters requires the segmentation of endothelial cell images. Current techniques to image the endothelium in vivo deliver low quality images, which makes automatic segmentation a complicated task. Here, we present two convolutional neural networks (CNN) to segment CE images: a global fully convolutional approach based on U-net, and a local sliding-window network (SW-net). We propose to use probabilistic labels instead of binary, we evaluate a preprocessing method to enhance the contrast of images, and we introduce a postprocessing method based on Fourier analysis and watershed to convert the CNN output images into the final cell segmentation. Both methods are applied to 50 images acquired with an SP-1P Topcon specular microscope. Estimates are compared against a manual delineation made by a trained observer. U-net (AUC=0.9938) yields slightly sharper, clearer images than SW-net (AUC=0.9921). After postprocessing, U-net obtains a DICE=0.981 and a MHD=0.22 (modified Hausdorff distance), whereas SW-net yields a DICE=0.978 and a MHD=0.30. U-net generates a wrong cell segmentation in only 0.48% of the cells, versus 0.92% for the SW-net. U-net achieves statistically significant better precision and accuracy than both, Topcon and SW-net, for the estimates of three clinical parameters: cell density (ECD), polymegethism (CV), and pleomorphism (HEX). The mean relative error in U-net for the parameters is 0.4% in ECD, 2.8% in CV, and 1.3% in HEX. The computation time to segment an image and estimate the parameters is barely a few seconds. Both methods presented here provide a statistically significant improvement over the state of the art. U-net has reached the smallest error rate. We suggest a segmentation refinement based on our previous work to further improve the performance.

中文翻译：

---

用于角膜内皮细胞分割的完全卷积架构与滑动窗口 CNN。

角膜内皮 (CE) 图像提供了有关角膜健康状况的有价值的临床信息。临床形态学参数的计算需要对内皮细胞图像进行分割。当前的体内内皮成像技术提供低质量的图像，这使得自动分割成为一项复杂的任务。在这里，我们提出了两个卷积神经网络 (CNN) 来分割 CE 图像：基于 U-net 的全局全卷积方法和局部滑动窗口网络 (SW-net)。我们建议使用概率标签而不是二进制，我们评估了一种预处理方法来增强图像的对比度，我们引入了一种基于傅里叶分析和分水岭的后处理方法，将 CNN 输出图像转换为最终的细胞分割。这两种方法都适用于使用 SP-1P Topcon 镜面显微镜采集的 50 张图像。将估计值与受过训练的观察者的人工描述进行比较。U-net (AUC=0.9938) 产生的图像比 SW-net (AUC=0.9921) 更清晰、更清晰。后处理后，U-net 得到 DICE=0.981 和 MHD=0.22（修改后的 Hausdorff 距离），而 SW-net 得到 DICE=0.978 和 MHD=0.30。U-net 仅在 0.48% 的单元格中生成错误的单元格分割，而 SW-net 则为 0.92%。在估计三个临床参数：细胞密度 (ECD)、多聚体 (CV) 和多形性 (HEX) 时，U-net 比 Topcon 和 SW-net 实现了具有统计学意义的更好的精度和准确度。U-net 中参数的平均相对误差在 ECD 中为 0.4%，在 CV 中为 2.8%，在 HEX 中为 1.3%。分割图像和估计参数的计算时间只有几秒钟。这里介绍的两种方法都比现有技术提供了统计学上的显着改进。U-net 已经达到了最小的错误率。我们建议基于我们之前的工作进行细分改进，以进一步提高性能。