Corpus ID: 232110730

Semi-supervised Left Atrium Segmentation with Mutual Consistency Training

@article{Wu2021SemisupervisedLA,
  title={Semi-supervised Left Atrium Segmentation with Mutual Consistency Training},
  author={Yicheng Wu and Minfeng Xu and Zongyuan Ge and Jianfei Cai and Lei Zhang},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.02911}
}
Semi-supervised learning has attracted great attention in the field of machine learning, especially for medical image segmentation tasks, since it alleviates the heavy burden of collecting abundant densely annotated data for training. However, most of existing methods underestimate the importance of challenging regions (e.g. small branches or blurred edges) during training. We believe that these unlabeled regions may contain more crucial information to minimize the uncertainty prediction for… Expand

Figures and Tables from this paper

Enforcing Mutual Consistency of Hard Regions for Semi-supervised Medical Image Segmentation
  • Yicheng Wu, Zongyuan Ge, +4 authors Jianfei Cai
  • Computer Science
  • 2021
In this paper, we proposed a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled hard regions for semi-supervised medical image segmentation. The MC-Net+ model isExpand

References

SHOWING 1-10 OF 21 REFERENCES
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
TLDR
A novel uncertainty-aware semi-supervised framework for left atrium segmentation from 3D MR images that can effectively leverage the unlabeled data by encouraging consistent predictions of the same input under different perturbations. Expand
DMNet: Difference Minimization Network for Semi-supervised Segmentation in Medical Images
TLDR
A novel end-to-end approach, called difference minimization network (DMNet), for semi-supervised semantic segmentation, which adopts two decoder branches and minimizes the difference between soft masks generated by the two decoders. Expand
Semi-supervised Medical Image Segmentation through Dual-task Consistency
TLDR
This work proposes a novel dual-task-consistency semi-supervised framework that can largely improve the performance by incorporating the unlabeled data and outperforms the state-of-the-art semi- supervised medical image segmentation methods. Expand
Pairwise Relation Learning for Semi-supervised Gland Segmentation
TLDR
The results indicate that the proposed pairwise relation-based semi-supervised PRS-Net and object-level Dice loss model achieves the state-of-the-art gland segmentation performance on both benchmarks. Expand
Double-Uncertainty Weighted Method for Semi-supervised Learning
TLDR
This paper proposes a double-uncertainty weighted method for semi-supervised segmentation based on the teacher-student model, which is the first to extend segmentation uncertainty estimation to feature uncertainty, which reveals the capability to capture information among channels. Expand
Local and Global Structure-Aware Entropy Regularized Mean Teacher Model for 3D Left Atrium Segmentation
TLDR
This work introduces the entropy minimization principle to the student network, thereby adjusting itself to produce high-confident predictions of unannotated images and designs a local structural consistency loss to encourage the consistency of inter-voxel similarities within the same local region of predictions from teacher and student networks. Expand
3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training
TLDR
A novel framework, uncertainty-aware multi-view co-training (UMCT), to address semi-supervised learning on 3D data, such as volumetric data from medical imaging, and proposes an uncertainty-weighted label fusion mechanism to estimate the reliability of each view’s prediction with Bayesian deep learning. Expand
Semi-supervised Segmentation of Liver Using Adversarial Learning with Deep Atlas Prior
TLDR
A semi-supervised adversarial learning model with Deep Atlas Prior (DAP), which is based on the probability atlas of organ (liver) and contains prior information such as the shape and position, is proposed to improve the accuracy of liver segmentation in CT images. Expand
Unsupervised Data Augmentation for Consistency Training
TLDR
A new perspective on how to effectively noise unlabeled examples is presented and it is argued that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning. Expand
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TLDR
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once. Expand
...
1
2
3
...