U-Net has been providing state-of-the-art performance in many medical image segmentation problems. Many modifications have been proposed for U-Net, such as attention U-Net, recurrent residual convolutional U-Net (R2-UNet), and U-Net with residual blocks or blocks with dense connections. However, all these modifications have an encoder-decoder structure with skip connections, and the number of paths for information flow is limited. We propose LadderNet in this paper, which can be viewed as a chain of multiple U-Nets. Instead of only one pair of encoder branch and decoder branch in U-Net, a LadderNet has multiple pairs of encoder-decoder branches, and has skip connections between every pair of adjacent decoder and decoder branches in each level. Inspired by the success of ResNet and R2-UNet, we use modified residual blocks where two convolutional layers in one block share the same weights. A LadderNet has more paths for information flow because of skip connections and residual blocks, and can be viewed as an ensemble of Fully Convolutional Networks (FCN). The equivalence to an ensemble of FCNs improves segmentation accuracy, while the shared weights within each residual block reduce parameter number. Semantic segmentation is essential for retinal disease detection. We tested LadderNet on two benchmark datasets for blood vessel segmentation in retinal images, and achieved superior performance over methods in the literature. The implementation is provided \url{https://github.com/juntang-zhuang/LadderNet}

翻译：U- Net 在许多医学图像分割问题中一直提供最先进的性能。 已经建议对 U- Net 进行许多修改, 如注意 U- Net 、 重复残留的富集U- UNet (R2- UNet) 和 带有残余块或密连的块的 U- Net 。 然而, 所有这些修改都有一个连接跳过的编码器- 解码器结构, 信息流路径数量有限 。 我们在此文件中建议 Ladder Net, 它可以被视为多个 U- Net 的链条。 一个 LadderNet, 而不是仅仅对一对编码器分支和 U- Net 的解码分支, 而是对编码解码器(R2- UNet ) 和 U- Net 的复数组进行多次修改, 而 Ladder Net 则使用修改后的残存区块, 将信息流视为信息流流的路径路径, 因为连接和残余部分, 并且可以被看成是Senqual Reval 的精度 。