LadderNet: Multi-path networks based on U-Net for medical image segmentation

Abstract

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}

References in corpus (1)

• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation

Cited by in corpus (15)

• Skin Cancer Segmentation and Classification with NABLA-N and Inception Recurrent Residual Convolutional Networks
• Towards Safer Robot-Assisted Surgery: A Markerless Augmented Reality Framework
• Deep Learning Methods for Retinal Blood Vessel Segmentation: Evaluation on Images with Retinopathy of Prematurity
• Deep Dilated Convolutional Nets for the Automatic Segmentation of Retinal Vessels
• Hierarchical Attention Networks for Medical Image Segmentation
• Segmentation of Blood Vessels, Optic Disc Localization, Detection of Exudates and Diabetic Retinopathy Diagnosis from Digital Fundus Images
• Retinal Vessel Segmentation based on Fully Convolutional Networks
• BUSU-Net: An Ensemble U-Net Framework for Medical Image Segmentation
• Residual Spatial Attention Network for Retinal Vessel Segmentation
• Deeply Cascaded U-Net for Multi-Task Image Processing
• Contextual Information Enhanced Convolutional Neural Networks for Retinal Vessel Segmentation in Color Fundus Images
• Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels
• The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation
• BEFD: Boundary Enhancement and Feature Denoising for Vessel Segmentation
• Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction