ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks
ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks
复制标题
DOI：
10.1364/boe.8.003627
复制
发表时间：
2017-08-01
影响因子：
3.4
通讯作者：
Navab, Nassir
中科院分区：
文献类型：
--
作者：
Roy, Abhijit Guha;Conjeti, Sailesh;Navab, Nassir
光学相干断层扫描（OCT）用于评估视网膜层的糖尿病黄斑水肿的非侵入性诊断。在本文中，我们提出了一种新的全卷积深度架构，称为ReLayNet，用于眼睛OCT扫描中视网膜层和流体块的端到端分割。ReLayNet使用卷积块（编码器）的收缩路径来学习上下文特征的层次结构，然后使用卷积块（解码器）的扩展路径进行语义分割。ReLayNet被训练来优化由加权逻辑回归和Dice重叠损失组成的联合损失函数。该框架在公开的基准数据集上进行了验证，并与五种最先进的分割方法进行了比较，包括两种基于深度学习的方法，以证实其有效性。(C)2017美国光学学会
Optical coherence tomography (OCT) is used for non- invasive diagnosis of diabetic macular edema assessing the retinal layers. In this paper, we propose a new fully convolutional deep architecture, termed ReLayNet, for end-to-end segmentation of retinal layers and fluid masses in eye OCT scans. ReLayNet uses a contracting path of convolutional blocks (encoders) to learn a hierarchy of contextual features, followed by an expansive path of convolutional blocks (decoders) for semantic segmentation. ReLayNet is trained to optimize a joint loss function comprising of weighted logistic regression and Dice overlap loss. The framework is validated on a publicly available benchmark dataset with comparisons against five state-of-the-art segmentation methods including two deep learning based approaches to substantiate its effectiveness. (C) 2017 Optical Society of America