Mutual consistency learning for semi-supervised medical image segmentation

Wu, Yi‐Cheng; Ge, Zongyuan; Zhang, Donghao; Xu, Minfeng; Zhang, Lei; Xia, Yong; Cai, Jianfei

doi:10.1016/j.media.2022.102530

Cited by 110 publications

(54 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments were divided into training and validation sets according to the ratio of 4:1. In addition, the latest methods that achieved excellent performance in the LASC2013 and ASC2018 datasets were selected for comparison [ 38 , 39 , 40 , 41 , 42 ]. The segmentation performance of the different models is shown in Table 2 and Figure 7 .…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Cardiac Magnetic Resonance Image Segmentation Method Based on Multi-Scale Feature Fusion and Sequence Relationship Learning

Zuo

et al. 2023

Sensors

View full text Add to dashboard Cite

Accurate segmentation of the left atrial structure using magnetic resonance images provides an important basis for the diagnosis of atrial fibrillation (AF) and its treatment using robotic surgery. In this study, an image segmentation method based on sequence relationship learning and multi-scale feature fusion is proposed for 3D to 2D sequence conversion in cardiac magnetic resonance images and the varying scales of left atrial structures within different slices. Firstly, a convolutional neural network layer with an attention module was designed to extract and fuse contextual information at different scales in the image, to strengthen the target features using the correlation between features in different regions within the image, and to improve the network’s ability to distinguish the left atrial structure. Secondly, a recurrent neural network layer oriented to two-dimensional images was designed to capture the correlation of left atrial structures in adjacent slices by simulating the continuous relationship between sequential image slices. Finally, a combined loss function was constructed to reduce the effect of positive and negative sample imbalance and improve model stability. The Dice, IoU, and Hausdorff distance values reached 90.73%, 89.37%, and 4.803 mm, respectively, based on the LASC2013 (left atrial segmentation challenge in 2013) dataset; the corresponding values reached 92.05%, 89.41% and 9.056 mm, respectively, based on the ASC2018 (atrial segmentation challenge at 2018) dataset.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Cardiac Magnetic Resonance Image Segmentation Method Based on Multi-Scale Feature Fusion and Sequence Relationship Learning

Zuo

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In this study, two public datasets and one in-house dataset are employed to validate the proposed RCPS method, which includes the LA dataset [9], pancreas-CT dataset [10] and TBI dataset [41]. We compare the segmentation performance on the public datasets of the proposed RCPS and state-of-the-art methods, including UA-MT [23], SASSNet [26], DTC [27], URPC [29] and MC-Net+ [30], which have been discussed in Sec. II-B.…”

Section: Methodsmentioning

confidence: 99%

“…Dataset and Preprocessing 1) LA Dataset: The LA dataset is the benchmark dataset for the 2018 Atrial Segmentation Challenge, which includes 100 gadolinium-enhanced labeled MR scans with an isotropic resolution of 0.625 × 0.625 × 0.625 mm. Since the annotations of the test set in LA are not available, we use the fixed data split used in previous works [23], [30], [31], where 80 samples are used for training and the rest 20 are for validation. Then, performance comparison with other models with the same validation set is reported for fair comparison.…”

Section: Methodsmentioning

confidence: 99%

“…where α and β are hyper-parameters to balance the loss, depending on the specific task. Note that, unlike previous works which only add the extra unsupervised losses [28], [30], [31], the proposed rectified pseudo supervision loss and the bidirectional voxel contrastive loss are added to the labeled data as well. Thus, the overall supervised loss sup is calculated as below:…”

Section: A Overview Of the Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation

Zhao¹,

Qi²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which require a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervised image segmentation can alleviate the problem by utilizing a large number of unlabeled images along with limited labeled images. However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches. To address the issues above, we propose a novel semi-supervised segmentation method named as Rectified Contrastive Pseudo Supervision (RCPS), which combines a rectified pseudo supervision and voxel-level contrastive learning to improve the effectiveness of semi-supervised segmentation. Particularly, we design a novel rectification strategy for the pseudo supervision method based on uncertainty estimation and consistency regularization to reduce the noise influence in pseudo labels. Furthermore, we introduce a bidirectional voxel contrastive loss to the network to ensure intra-class consistency and inter-class contrast in feature space, which increases class separability in the segmentation. The proposed RCPS segmentation method has been validated on two public datasets and an in-house clinical dataset. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art methods in semi-supervised medical image segmentation. The source code is available at https://github.com/hsiangyuzhao/RCPS.

show abstract

“…Our work is closely related to the consistency based semi-supervised learning (SSL) [46,45], where the basic idea is to leverage the unlabeled data based on the smoothness assumptions, i.e. deep models under various small perturbations or augmentations should output consistent results.…”

Section: Consistency-based Semi-supervised Learningmentioning

confidence: 99%

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Wu¹,

Wu²,

Lin³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbations to effectively regularize unlabeled 3D points. Specifically, we propose a novel DAT (Dual Adaptive Transformations) model for weakly supervised point cloud segmentation, where the dual adaptive transformations are performed via an adversarial strategy at both point-level and region-level, aiming at enforcing the local and structural smoothness constraints on 3D point clouds. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets. Extensive experiments demonstrate that our model can effectively leverage the unlabeled 3D points and achieve significant performance gains on both datasets, setting new state-of-the-art performance for weakly supervised point cloud segmentation.

show abstract

Mutual consistency learning for semi-supervised medical image segmentation

Cited by 110 publications

References 53 publications

Cardiac Magnetic Resonance Image Segmentation Method Based on Multi-Scale Feature Fusion and Sequence Relationship Learning

Cardiac Magnetic Resonance Image Segmentation Method Based on Multi-Scale Feature Fusion and Sequence Relationship Learning

RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Contact Info

Product

Resources

About