• Corpus ID: 236912605

Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization

  title={Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization},
  author={Wei Feng and Lie Ju and Lin Wang and Kaimin Song and Xin Wang and Xin Zhao and Qingyi Tao and Zongyuan Ge},
Retinal vessel segmentation plays a key role in computer-aided screening, diagnosis, and treatment of various cardiovascular and ophthalmic diseases. Recently, deep learning-based retinal vessel segmentation algorithms have achieved remarkable performance. However, due to the domain shift problem, the performance of these algorithms often degrades when they are applied to new data that is different from the training data. Manually labeling new data for each test domain is often a timeconsuming… 

Figures and Tables from this paper

Disentangled Representation for Cross-Domain Medical Image Segmentation

A novel feature disentanglement (FD)-based unsupervised domain adaptation (UDA) method to improve the robustness of the trained model in the target domain and incorporate the adversarial training to predict shape-invariant segmentation masks across domains is proposed.



Domain adaptation for retinal vessel segmentation using asymmetrical maximum classifier discrepancy

This work uses three classifiers asymmetrically which means that two assist classifiers are used to maximize the discrepancy on target samples and one main classifier is trained only by the source samples to achieve significantly accuracy in the setting of unsupervised domain adaptation.

Robust Retinal Vessel Segmentation from a Data Augmentation Perspective

Experimental results on both real-world and synthetic datasets demonstrate that the proposed two new data augmentation modules can improve the performance and robustness of a classic convolutional neural network architecture.

Learning to Adapt Structured Output Space for Semantic Segmentation

A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.

Domain adaptation for biomedical image segmentation using adversarial training

This work uses an adversarial based training approach to train CNNs to achieve good accuracy on the target domain and shows improvements on membrane detection between MIC-CAI 2016 CREMI challenge and ISBI2013 EM segmentation challenge datasets.

Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation

A new segment-level loss which emphasizes more on the thickness consistency of thin vessels in the training process is proposed which can bring consistent performance improvement for both deep and shallow network architectures.

Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling

This paper proposes the use of a modified cycle generative adversarial network (CycleGAN) model to bridge the gap between regular and UWF fundus and generate additional UWF Fundus images for training, and shows that the method is robust to noise and errors introduced by the generated unlabeled data with the pseudo-labeling technique.

DUNet: A deformable network for retinal vessel segmentation

A Global and Local Enhanced Residual U-Net for Accurate Retinal Vessel Segmentation

A Global and Local enhanced residual U-nEt (GLUE) for accurate retinal vessel segmentation, which benefits from both the globally and locally enhanced information inside the retinal region is proposed.

Weakly-Supervised Vessel Detection in Ultra-Widefield Fundus Photography via Iterative Multi-Modal Registration and Learning

Experimental evaluation, using both pixel-wise metrics and the CAL metrics designed to provide better agreement with human assessment, shows that the proposed approach provides accurate vessel detection, without requiring manually labeled UWF FP training data.

Revisiting Batch Normalization For Practical Domain Adaptation

This paper proposes a simple yet powerful remedy, called Adaptive Batch Normalization (AdaBN) to increase the generalization ability of a DNN, and demonstrates that the method is complementary with other existing methods and may further improve model performance.