Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels

Zhou, Yuqian; Yu, Hanchao

doi:10.1007/978-3-030-87193-2_6

Cited by 36 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In above methods, [21,22,30,37,59,61] consider the vessel segmentation, which relate closely to our work. 2.2.…”

Section: Related Workmentioning

confidence: 93%

Section: Related Workmentioning

confidence: 99%

“…Meanwhile, others considered task priors and employed multiple UNets (and possibly the other pre-defined networks like ResNets) to construct task-oriented giant networks [30,37,54,61]. Some studies also designed structures served as automatic data-augmentation corresponding to image priors, or in other words, generating pseudo-samples; See [30,37,61] and the references therein. With huge number of learnable parameters, they achieved incredible performance improvement, but lacked interpretability and relied on tricky training procedures with more hyper-parameters, because of the black-box nature without mathematical modeling.…”

Section: Related Workmentioning

confidence: 99%

“…They are powerful and universal solvers, disengaging people from burdens of accurate modeling with no performance trade-off. But recent studies [22,61,62] showed that the original UNet structure, or, in other words, processing images on multiple scale levels through encoder-decoder pairs, require more sophisticated structures to avoid some defects. For example, obvious overfitting phenomenon and generalizing error are discovered in the experiments in [22].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

IDmUNet: A new image decomposition induced network for sparse feature segmentation

Ren¹,

Gao²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

UNet and its variants are among the most popular methods for medical image segmentation. Despite their successes in task generality, most of them consider little mathematical modeling behind specific applications. In this paper, we focus on the sparse feature segmentation task and make a taskoriented network design, in which the target objects are sparsely distributed and the background is hard to be mathematically modeled. We start from an image decomposition model with sparsity regularization, and propose a deep unfolding network, namely IDNet, based on an iterative solver, scaled alternating direction method of multipliers (scaled-ADMM). The IDNet splits raw inputs into double feature layers. Then a new task-oriented segmentation network is constructed, dubbed as IDmUNet, based on the proposed IDNets and a mini-UNet. Because of the sparsity prior and deep unfolding method in the structure design, this IDmUNet combines the advantages of mathematical modeling and data-driven approaches. Firstly, our approach has mathematical interpretability and can achieve favorable performance with far fewer learnable parameters. Secondly, our IDmUNet is robust in a simple end-to-end training with explainable behaviors. In the experiments of retinal vessel segmentation (RVS), IDmUNet produces the state-of-the-art results with only 0.07m parameters, whereas SA-UNet, one of the latest variants of UNet, contains 0.54m and the original UNet 31.04m. Moreover, the training procedure of our network converges faster without overfitting phenomenon. This decomposition-based network construction strategy can be generalized to other problems with mathematically clear targets and complicated unclear backgrounds.

show abstract

“…In above methods, [21,22,30,37,59,61] consider the vessel segmentation, which relate closely to our work. 2.2.…”

Section: Related Workmentioning

confidence: 93%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

IDmUNet: A new image decomposition induced network for sparse feature segmentation

Ren¹,

Gao²,

Wu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…According to the ranking on the paperwithcode website 1 , some state-of-the-art (SOTA) methods with the current top performance were used for the performance compassion. The comparative methods adopted in this work including the methods without the consideration of the vascular connectivity, that is, Dual E-UNet [27], IterNet [44], SA-UNet [28], SGL [45], RV-GAN [46], SUD-GAN [47], DUNet [48] and R2U-Net [25], and methods with the consideration of vascular connectivity, that is, the method proposed by Oliveira et al [49], and the method proposed by Araújo et al [30].The comparative experimental results are listed in Table 4.…”

Section: 43mentioning

confidence: 99%

MCG&BA‐Net: Retinal vessel segmentation using multiscale context gating and breakpoint attention

Zhao

Liu

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

The accurate segmentation of blood vessels plays a crucial role in screening, diagnosis and treatment of multiple diseases. However, current automated segmentation approaches do not pay enough attention to the vascular topology errors (such as mistaking vesselbreakpoints), resulting in considerable scattered vessel-fragments in segmentation results. This article proposes a retinal vessel segmentation model using multi-scale context gating and breakpoint attention mechanism, called MCG&BA-Net. Specifically, it obtains a feature map containing contextual information of vessels through an introduced multi-scale context module, and then filters the redundant features and noises by a gated structure to highlight target features. Furthermore, a kind of breakpoint attention module is proposed, which can locate and focus on potential breakpoint areas, thereby facilitating accurate segmentation results of tree-like fine vessels. Extensive confirmatory and comparative experiments have been conducted on five public datasets, including three benchmark datasets, that is, DRIVE, CHASDB1 and SATRE, and two clinical datasets, that is, fun-dusimage1000 and RFMID. The AUC scores on the benchmark datasets are 0.9878, 0.9923 and 0.9942, respectively. Among them, the AUC score on CHADEDB1 and STARE outperforms the state-of-the-art results. In addition, experimental results on the two clinical datasets demonstrate strong generalization capability of the propose method, indicating high clinical application values.

show abstract

Logarithmic Mathematical Morphology: A New Framework Adaptive to Illumination Changes

Noyel

2019

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

A new set of mathematical morphology (MM) operators adaptive to illumination changes caused by variation of exposure time or light intensity is defined thanks to the Logarithmic Image Processing (LIP) model. This model based on the physics of acquisition is consistent with human vision. The fundamental operators, the logarithmic-dilation and the logarithmic-erosion, are defined with the LIP-addition of a structuring function. The combination of these two adjunct operators gives morphological filters, namely the logarithmic-opening and closing, useful for pattern recognition. The mathematical relation existing between "classical" dilation and erosion and their logarithmic-versions is established facilitating their implementation. Results on simulated and real images show that logarithmic-MM is more efficient on low-contrasted information than "classical" MM.

show abstract

Study Group Learning: Improving Retinal Vessel Segmentation Trained with Noisy Labels

Cited by 36 publications

References 23 publications

IDmUNet: A new image decomposition induced network for sparse feature segmentation

IDmUNet: A new image decomposition induced network for sparse feature segmentation

MCG&BA‐Net: Retinal vessel segmentation using multiscale context gating and breakpoint attention

Logarithmic Mathematical Morphology: A New Framework Adaptive to Illumination Changes

Contact Info

Product

Resources

About