Liver segmentationSemi-supervisedDeep Atlas PriorAdversarial learningMedical image segmentation is one of the most important steps in computer-aided intervention and diagnosis. Although deep learning-based segmentation methods have achieved great success in computer vision domain, there are still several ...
Semi-supervised Segmentation of Liver Using Adversarial Learning with Deep Atlas PriorMedical image segmentation is one of the most important steps in computer-aided intervention and diagnosis. Although deep learning-based segmentation methods have achieved great success in computer......
The challenge of limited labeled data has driven the creation of training approaches, like semi-supervised learning, that can leverage data more effectively. Semi-supervised semantic segmentation approaches Strategies like data augmentation, semi-supervised learning, and active learning are some of the ...
参考论文 1、Recurrent Mask Refinement for Few-Shot Medical Image Segmentation (ICCV2021) 2、Edge-competing Pathological Liver Vessel Segmentation with Limited Labels (AAAI2021)1、上下文关系编码器(CR…
One work (Hu et al., 2021) explores this supervised approach on medical image segmentation with limited annotations and get some improvements. In this work, we focus on the scenario where only limited labels are available. (b) Unsupervised local contrastive learning: Here, the authors do not ...
{Semi-supervised medical image segmentation via cross teaching between cnn and transformer}, author={Luo, Xiangde and Hu, Minhao and Song, Tao and Wang, Guotai and Zhang, Shaoting}, booktitle={International Conference on Medical Imaging with Deep Learning}, pages={820--833}, year={2022}, ...
Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation SALAD: Self-Supervised Aggregation Learning for Anomaly Detection on X-Ray...
(i.e., reconstruction) task. Among four supervised segmentation tasks, only one is considered as the primary task during training and the rest are trained as auxiliary tasks along with the unsupervised reconstruction task. In Eq. (2), we present the SSMD-UNet loss\({\mathcal {L}}_{\...
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 ex
Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such learning framework is built on laborious manual annotation with restrict demands for expertise, leading to insufficient high-quality labels. To overcome such limitation and exploit ...