Reciprocal Learning for Semi-supervised Segmentation

Zeng, Xiangyun; Huang, Rian; Zhong, Yuming; Sun, Dong; Han, Chu; Lin, Di; Ni, Dong; Wang, Yi

doi:10.1007/978-3-030-87196-3_33

Cited by 17 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning other deep learning methods proposed recently, they are mainly classified as three categories: new training and learning strategies [1,22], shape-aware or structure-aware based methods [5,6,9], and consistency regularization based methods [2,10,11,19].…”

Section: Other Deep Learning Methodsmentioning

confidence: 99%

“…During the iterative training process, a conditional random field (CRF) [8] was used to refine the pseudo labels. Zeng et al [22] proposed a reciprocal learning strategy for their teacher-student architecture. The strategy contains a feedback mechanism for the teacher network via observing how pseudo labels would affect the student, which is omitted in previous teacher-student based models.…”

Section: Other Deep Learning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation

Wang¹,

Lukasiewicz²

2022

Preprint

View full text Add to dashboard Cite

Recently, several Bayesian deep learning methods have been proposed for semi-supervised medical image segmentation. Although they have achieved promising results on medical benchmarks, some problems are still existing. Firstly, their overall architectures belong to the discriminative models, and hence, in the early stage of training, they only use labeled data for training, which might make them overfit to the labeled data. Secondly, in fact, they are only partially based on Bayesian deep learning, as their overall architectures are not designed under the Bayesian framework. However, unifying the overall architecture under the Bayesian perspective can make the architecture have a rigorous theoretical basis, so that each part of the architecture can have a clear probabilistic interpretation. Therefore, to solve the problems, we propose a new generative Bayesian deep learning (GBDL) architecture. GBDL belongs to the generative models, whose target is to estimate the joint distribution of input medical volumes and their corresponding labels. Estimating the joint distribution implicitly involves the distribution of data, so both labeled and unlabeled data can be utilized in the early stage of training, which alleviates the potential overfitting problem. Besides, GBDL is completely designed under the Bayesian framework, and thus we give its full Bayesian formulation, which lays a theoretical probabilistic foundation for our architecture. Extensive experiments show that our GBDL outperforms previous state-of-the-art methods in terms of four commonly used evaluation indicators on three public medical datasets.

show abstract

Section: Other Deep Learning Methodsmentioning

confidence: 99%

Section: Other Deep Learning Methodsmentioning

confidence: 99%

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation

Wang¹,

Lukasiewicz²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To issue the problem, Tarvainen et al [50] propose to use a teacher model with the EMA weights of the student model for training and enforce the consistency of predictions from perturbed inputs between student and teacher models. Zeng et al [51] improve the EMA weighted way in teacher models. They add a feedback signal form the performance of the student on the labeled set, through which the teacher model can be updated by gradient descent algorithm autonomously and purposefully.…”

Section: Unsupervised Regularization With Consistency Learningmentioning

confidence: 99%

Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

Jiao¹,

Zhang²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly difficult and costly to obtain especially in the medical imaging domain where only experts can provide reliable and accurate annotations. Semi-supervised learning has emerged as an appealing strategy and been widely applied to medical image segmentation tasks to train deep models with limited annotations. In this paper, we present a comprehensive review of recently proposed semi-supervised learning methods for medical image segmentation and summarized both the technical novelties and empirical results. Furthermore, we analyze and discuss the limitations and several unsolved problems of existing approaches. We hope this review could inspire the research community to explore solutions for this challenge and further promote the developments in medical image segmentation field.

show abstract

“…CAFS introduces a feedback mechanism [61], which allows for more accurate segmentation of nasopharyngeal carcinoma boundaries. As stated in Section 3.1, the student model was trained on unlabeled nasopharyngeal carcinoma data and the pseudo-masks to update the parameters.…”

Section: Feedback Mechanismmentioning

confidence: 99%

CAFS: An Attention-Based Co-Segmentation Semi-Supervised Method for Nasopharyngeal Carcinoma Segmentation

Chen

Han

Lin

et al. 2022

Sensors

View full text Add to dashboard Cite

Accurate segmentation of nasopharyngeal carcinoma is essential to its treatment effect. However, there are several challenges in existing deep learning-based segmentation methods. First, the acquisition of labeled data are challenging. Second, the nasopharyngeal carcinoma is similar to the surrounding tissues. Third, the shape of nasopharyngeal carcinoma is complex. These challenges make the segmentation of nasopharyngeal carcinoma difficult. This paper proposes a novel semi-supervised method named CAFS for automatic segmentation of nasopharyngeal carcinoma. CAFS addresses the above challenges through three mechanisms: the teacher–student cooperative segmentation mechanism, the attention mechanism, and the feedback mechanism. CAFS can use only a small amount of labeled nasopharyngeal carcinoma data to segment the cancer region accurately. The average DSC value of CAFS is 0.8723 on the nasopharyngeal carcinoma segmentation task. Moreover, CAFS has outperformed the state-of-the-art nasopharyngeal carcinoma segmentation methods in the comparison experiment. Among the compared state-of-the-art methods, CAFS achieved the highest values of DSC, Jaccard, and precision. In particular, the DSC value of CAFS is 7.42% higher than the highest DSC value in the state-of-the-art methods.

show abstract

Reciprocal Learning for Semi-supervised Segmentation

Cited by 17 publications

References 12 publications

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation

Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

CAFS: An Attention-Based Co-Segmentation Semi-Supervised Method for Nasopharyngeal Carcinoma Segmentation

Contact Info

Product

Resources

About