arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.05052eess.IVcs.CVcs.LG
收藏

将边缘信息整合到真值中,用于从眼底图像分割视盘和视杯

Integrating Edge Information into Ground Truth for the Segmentation of the Optic Disc and Cup from Fundus Images

Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram(印度信息技术、设计与制造学院(坎奇普兰))

Yoga Sri Varshan, Hitesh Gupta Kattamuri, Subin Sahayam, Umarani Jayaraman

AI总结:

本文提出用 Laplacian 滤波器从视盘、视杯真值中提取并重建边缘真值,将其与区域真值共同用于 U-Net 系列模型训练,在 REFUGE 和 Drishti-GS 上显著提升 dice 并降低 Hausdorff 距离。

摘要:

视盘和视杯分割有助于诊断青光眼、心肌梗死和糖尿病视网膜病变。大多数为执行分割任务而开发的深度学习方法都建立在基于 U-Net 的模型架构之上。然而,U-Net 及其变体往往会对所需感兴趣区域产生过分割或欠分割。由于最重要的结果是杯盘比的值,而不是分割区域本身,因此我们更关注边界,而不是边界下方的区域。与学习区域相比,这使得学习边缘非常重要。在所提出的工作中,作者旨在使用 Laplacian 滤波器从真值中提取视盘和视杯的边缘。接下来,对边缘进行重建,以在视盘-视杯真值之外获得边缘真值。利用这两种真值,作者研究了若干 U-Net 及其变体架构,比较其在分割时是否将视盘和视杯边缘与视盘-视杯真值一起作为目标。作者使用 REFUGE 基准数据集和 Drishti-GS 数据集开展研究,并以 dice 和 Hausdorff 距离指标将结果制成表格。在 REFUGE 数据集上,对于基线 U-Net 模型,视盘平均 dice 分数从 0.7425 提升到 0.8859,而平均 Hausdorff 距离从 6.5810 降低到 3.0540。同样,同一模型的视杯平均 dice 分数从 0.6970 提升到 0.8639,而平均 Hausdorff 距离从 5.2340 降低到 2.6323。在 Drishti-GS 数据集上也观察到类似的改进。与基线 U-Net 及其变体(即 Attention U-Net 和 U-Net++)相比,在学习视盘和视杯区域的同时学习整合边缘的模型在验证集和测试集上均表现良好。

英文摘要:

Optic disc and cup segmentation helps in the diagnosis of glaucoma, myocardial infarction, and diabetic retinopathy. Most deep learning methods developed to perform segmentation tasks are built on top of a U-Net-based model architecture. Nevertheless, U-Net and its variants have a tendency to over-segment/ under-segment the required regions of interest. Since the most important outcome is the value of cup-to-disc ratio and not the segmented regions themselves, we are more concerned about the boundaries rather than the regions under the boundaries. This makes learning edges important as compared to learning the regions. In the proposed work, the authors aim to extract both edges of the optic disc and cup from the ground truth using a Laplacian filter. Next, edges are reconstructed to obtain an edge ground truth in addition to the optic disc-cup ground truth. Utilizing both ground truths, the authors study several U-Net and its variant architectures with and without optic disc and cup edges as target, along with the optic disc-cup ground truth for segmentation. The authors have used the REFUGE benchmark dataset and the Drishti-GS dataset to perform the study, and the results are tabulated for the dice and the Hausdorff distance metrics. In the case of the REFUGE dataset, the optic disc mean dice score has improved from 0.7425 to 0.8859 while the mean Hausdorff distance has reduced from 6.5810 to 3.0540 for the baseline U-Net model. Similarly, the optic cup mean dice score has improved from 0.6970 to 0.8639 while the mean Hausdorff distance has reduced from 5.2340 to 2.6323 for the same model. Similar improvement has been observed for the Drishti-GS dataset as well. Compared to the baseline U-Net and its variants (i.e) the Attention U-Net and the U-Net++, the models that learn integrated edges along with the optic disc and cup regions performed well in both validation and testing datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑