LVC-Net: Medical Image Segmentation with Noisy Label Based on Local Visual Cues

Shu, Yucheng; Wu, Xiao; Li, Weisheng

doi:10.1007/978-3-030-32226-7_62

Cited by 24 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast, much less attention has been given to noisy label learning in medical imaging 16,50 . Most existing studies concentrate on designing new loss weighting strategies 51,52 or new loss functions 53 . Since various issues with the datasets may exist in reality, the effectiveness of these methods is compromised 22,26 .…”

Section: Discussionmentioning

confidence: 99%

Annotation-efficient deep learning for automatic medical image segmentation

et al. 2021

View full text Add to dashboard Cite

Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, we introduce Annotation-effIcient Deep lEarning (AIDE), an open-source framework to handle imperfect training datasets. Methodological analyses and empirical evaluations are conducted, and we demonstrate that AIDE surpasses conventional fully-supervised models by presenting better performance on open datasets possessing scarce or noisy annotations. We further test AIDE in a real-life case study for breast tumor segmentation. Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated by fully-supervised counterparts or provided by independent radiologists. The 10-fold enhanced efficiency in utilizing expert labels has the potential to promote a wide range of biomedical applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Annotation-efficient deep learning for automatic medical image segmentation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…To analyze and address various kinds of label errors, an important thing is to construct large scale datasets with real noises, which in itself is a challenging task. Currently, most studies still use public datasets with simulated label perturbations [284], [298], [301] or private datasets [25], [300]. Building up public benchmarks with real noises is crucial to make further breakthroughs, especially for clinical usage.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

“…A meta-learning was adopted to assign higher importance to pixels. Shu et al [300] proposed to enhance supervision of noisy labels by capturing local visual saliency features, which are less affected by supervised signals from inaccurate labels. For noisy-labeled medical image segmentation, Zhang et al [301] integrated confidence learning [302], which can identify the label errors through estimating the joint distribution between the noisy annotations and the true (latent) annotations, into the teacher-student framework to identify the corrupted labels at pixel-level.…”

Section: Inaccurately-supervised Segmentationmentioning

confidence: 99%

Medical Image Segmentation With Limited Supervision: A Review of Deep Network Models

Wang

2021

IEEE Access

View full text Add to dashboard Cite

Despite the remarkable performance of deep learning methods on various tasks, most cutting-edge models rely heavily on large-scale annotated training examples, which are often unavailable for clinical and health care tasks. The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling. Therefore, the strong capability of learning and generalizing from limited supervision, including a limited amount of annotations, sparse annotations, and inaccurate annotations, is crucial for the successful application of deep learning models in medical image segmentation. However, due to its intrinsic difficulty, segmentation with limited supervision is challenging and specific model design and/or learning strategies are needed. In this paper, we provide a systematic and up-to-date review of the solutions above, with summaries and comments about the methodologies. We also highlight several problems in this field, discussed future directions observing further investigations.

show abstract

“…Previous studies show that the DNNs trained by noisy labeled datasets can cause performance degradation. That is because the huge memory capacity and strong learning ability of DNNs can remember the noisy labels and easily overfit to them [17,18,14]. Hence, it is important to develop DNNs with strong robustness to noisy labels.…”

Section: Introductionmentioning

confidence: 99%

“…Zhu et al [18] proposed the automatic quality evaluation module and overfitting control module to update the network parameters. Shu et al [14] presented a LVC-Net losses function by combining noisy labels with image local visual cues to generate better semantic segmentation. Le et al [10] utilized a small set of clean training samples to assign weights to training samples.…”

Section: Introductionmentioning

confidence: 99%

Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation

Xue

Deng

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The superior performance of CNN on medical image analysis heavily depends on the annotation quality, such as the number of labeled image, the source of image, and the expert experience. The annotation requires great expertise and labour. To deal with the high inter-rater variability, the study of imperfect label has great significance in medical image segmentation tasks. In this paper, we present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation. Our model consists of three independent network, which can effectively learn useful information from the peer networks. The framework includes two stages. In the first stage, we select the clean annotated samples via a model committee setting, the networks are trained by minimizing a segmentation loss using the selected clean samples. In the second stage, we design a joint optimization framework with label correction to gradually correct the wrong annotation and improve the network performance. We conduct experiments on the public chest Xray image datasets collected by Shenzhen Hospital. The results show that our methods could achieve a significant improvement on the accuracy in segmentation tasks compared to the previous methods.

show abstract

LVC-Net: Medical Image Segmentation with Noisy Label Based on Local Visual Cues

Cited by 24 publications

References 12 publications

Annotation-efficient deep learning for automatic medical image segmentation

Annotation-efficient deep learning for automatic medical image segmentation

Medical Image Segmentation With Limited Supervision: A Review of Deep Network Models

Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation

Contact Info

Product

Resources

About