Automated optic disc (OD) and optic cup (OC) segmentation in fundus images is relevant to efficiently measure the vertical cup-to-disc ratio (vCDR), a biomarker commonly used in ophthalmology to determine the degree of glaucomatous optic neuropathy. In general this is solved using coarse-to-fine deep learning algorithms in which a first stage approximates the OD and a second one uses a crop of this area to predict OD/OC masks. While this approach is widely applied in the literature, there are no studies analyzing its real contribution to the results. In this paper we present a comprehensive analysis of different coarse-to-fine designs for OD/OC segmentation using 5 public databases, both from a standard segmentation perspective and for estimating the vCDR for glaucoma assessment. Our analysis shows that these algorithms not necessarily outperfom standard multi-class single-stage models, especially when these are learned from sufficiently large and diverse training sets. Furthermore, we noticed that the coarse stage achieves better OD segmentation results than the fine one, and that providing OD supervision to the second stage is essential to ensure accurate OC masks. Moreover, both the single-stage and two-stage models trained on a multi-dataset setting showed results in pair or even better than other state-of-the-art alternatives, while ranking first in REFUGE for OD/OC segmentation. Finally, we evaluated the models for vCDR prediction in comparison with six ophthalmologists on a subset of AIROGS images, to understand them in the context of inter-observer variability. We noticed that vCDR estimates recovered both from single-stage and coarse-to-fine models can obtain good glaucoma detection results even when they are not highly correlated with manual measurements from experts.
翻译:基金会图像中的自动光学盘(OD)和光杯(OC)分解(OC)对于有效测量垂直杯面与分解比例(VCDR)很重要。 在本文中,我们从标准的分解角度,用5个公共数据库,对用于确定光学神经病的光学分解程度的生物标志(VCDR)进行综合分析。一般而言,这是使用粗略至深层次的学习算法来解决的,第一阶段接近OD和第二阶段使用该地区一种作物来预测OD/OC口罩。虽然这种方法在文献中广泛应用,但没有分析其对结果的真正贡献。在本文中,我们用不同的分解-分解(VC)比例分析,从标准的多层单级模型中,这些算法不一定超出标准,特别是当它们从足够大和多样化的培训中学习的时候。此外,我们注意到,第二个阶段的分解(ODA-O-O-O)分解(VD)的分解(VD-O-OD)的分解(O-O)设计结果比精细的第一次分解结果要好,我们从一个阶段的分解到另一个阶段的分解(OD)的分解(OD)的分解)的分解(OD)的分解(OD)的分解(OD)的分解(OD)的分解(OD)的分解到另一个的分解)的分解)的分解(OD)的分解过程的分解(OD)的分解)的分解)的分解(OD(OD)的分解(OD)的分解)的分解)的分解(OD)的分解(OD)的分解(OD)的分解(OD)的分解(OD)的分解结果(O(O)的分解结果(O)的分解(O),在最后的分解),在两个的分解)的分解(OD)的分解(OD)的分解)的分解)的分解)的分解)的分解)的分解(OD)的分解到第二个的分解(OD)的分解(OD)的分解)的分解到