Attention Guided Network for Retinal Image Segmentation

Zhang, Shihao; Fu, Huazhu; Yan, Yuguang; Zhang, Yubing; Wu, Qingyao; Yang, Ming–Hsuan; Tan, Mingkui; Xu, Yanwu

doi:10.1007/978-3-030-32239-7_88

Cited by 152 publications

(95 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 6 demonstrates that, compared to the baseline M-Net, 15 ACC, SE, SP, AUC, and IOU were observed to increase by 3.40%, 5.81%, 2.54%, 1.01%, and 2.95%, respectively. However, compared to the state-of-the-art algorithm AG-Net, 32 the improvements were insignificant or completely absent. ACC increased by a mere 0.05%, SE increased by 0.2%, AUC increased by 0.08%, and IOU increased by 0.22%.…”

Section: Discussionmentioning

confidence: 87%

“…The proposed method yielded better results compared to the backbone. Comparison with AG-Net, 32 which is the state-of-the art algorithm, verified that the proposed network is effective with respect to the cell contour segmentation task. A few examples of visual comparison are presented in Fig.…”

Section: C2 Cell Contour Segmentationmentioning

confidence: 81%

“…The performance of the proposed model was compared to those of the state-of-the-art algorithms, including CE-Net, 23 GC-Net, 12 AG-Net, 32 BCDU-Net, 33 and GF-Net. 34 AG-Net is utilized in retinal fundus segmentation, which incorporates a guided filtering attention mechanism based on M-Net.…”

Section: C1 Retinal Vessel Segmentationmentioning

confidence: 99%

“…The proposed method exhibited higher SP, IOU, and dice coefficient compared to CE-Net 23 and AG-Net. 32 To verify the reliability and effectiveness of the proposed method, we compared 3D CT aortic data segmentation via the proposed method and the 3D U-Net network, 37 as recorded in Table IV. The proposed method exhibited higher dice coefficient and ACC. Further, it demonstrated higher segmentation accuracy than 3D-U-JAPA-Net6, even though its dice coefficient was slightly worse.…”

Section: C3 Upper Abdominal Aortic Segmentationmentioning

confidence: 99%

See 3 more Smart Citations

ADR‐Net: Context extraction network based on M‐Net for medical image segmentation

Jiang

Gao

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose: Medical image segmentation is an essential component of medical image analysis. Accurate segmentation can assist doctors in diagnosis and relieve their fatigue. Although several image segmentation methods based on U-Net have been proposed, their performances have been observed to be suboptimal in the case of small-sized objects. To address this shortcoming, a novel network architecture is proposed in this study to enhance segmentation performance on small medical targets. Methods: In this paper, we propose a joint multi-scale context attention network architecture to simultaneously capture higher level semantic information and spatial information. In order to obtain a greater number of feature maps during decoding, the network concatenates the images of side inputs by down-sampling during the encoding phase. In the bottleneck layer of the network, dense atrous convolution (DAC) and multi-scale residual pyramid pooling (RMP) modules are exploited to better capture high-level semantic information and spatial information. To improve the segmentation performance on small targets, the attention gate (AG) block is used to effectively suppress feature activation in uncorrelated regions and highlight the target area. Results: The proposed model is first evaluated on the public dataset DRIVE, on which it performs significantly better than the basic framework in terms of sensitivity (SE), intersection-over-union (IOU), and area under the receiver operating characteristic curve (AUC). In particular, the SE and IOU are observed to increase by 7.46% and 5.97%, respectively. Further, the evaluation indices exhibit improvements compared to those of state-of-the-art methods as well, with SE and IOU increasing by 3.58% and 3.26%, respectively. Additionally, in order to demonstrate the generalizability of the proposed architecture, we evaluate our model on three other challenging datasets. The respective performances are observed to be better than those of state-of-the-art network architectures on the same datasets. Moreover, we use lung segmentation as a comparative experiment to demonstrate the transferability of the advantageous properties of the proposed approach in the context of small target segmentation to the segmentation of large targets. Finally, an ablation study is conducted to investigate the individual contributions of the AG block, the DAC block, and the RMP block to the performance of the network. Conclusions: The proposed method is evaluated on various datasets. Experimental results demonstrate that the proposed model performs better than state-of-the-art methods in medical image segmentation of small targets.

show abstract

Section: Discussionmentioning

confidence: 87%

Section: C2 Cell Contour Segmentationmentioning

confidence: 81%

Section: C1 Retinal Vessel Segmentationmentioning

confidence: 99%

Section: C3 Upper Abdominal Aortic Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

ADR‐Net: Context extraction network based on M‐Net for medical image segmentation

Jiang

Gao

et al. 2020

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Recently, attention block is widely applied to emphasize targets and reduce the effect of noise. In [25], Zhang et al introduced an attention guided network (AG-Net) to achieve the retinal blood map. Li et al [26] designed a mini-UNets architecture performed based on the output of classical U-Net that further achieve the obscured detail of vessel.…”

Section: Related Workmentioning

confidence: 99%

Retinal vessel segmentation with constrained-based nonnegative matrix factorization and 3D modified Attention U-Net

Yao

Zhu

2020

Preprint

View full text Add to dashboard Cite

Due to the complex morphology and characteristic of retinal vessels, it remains challenging for most of the existing algorithms to accurately detect them. This paper proposes a supervised retinal vessels extraction scheme using constrained-based Nonnegative Matrix Factorization (NMF) and 3D modified Attention U-Net architecture. The proposed method detects the retinal vessels by three major steps. First, we perform Gaussian filter and Gamma correction on the Green channel of retinal images to suppress background noise and adjust the contrast of images. Then, the study develops a new within-class and between-class constrained NMF algorithms to extract neighborhood feature information of every pixel and reduce feature data dimension. By using these constraints, the method can effectively gather similar features within-class and discriminate features between-class to improve feature description ability for each pixel. Next, this study formulates segmentation task as a classification problem and solves it with a more contributing 3D modified Attention U-Net as a two-labels classifier for reducing computational cost. This proposed network contains an up-sampling to raise image resolution before encoding and revert image to its original size with a down-sampling after three max-pooling layers. Besides, the Attention Gate (AG) set in these layers contributes to more accurate segmentation by maintaining details while suppressing noises. Finally, the experimental results on two publicly available datasets STARE and DRIVE demonstrate better performance than most existing methods.

show abstract

Variance‐aware attention U‐Net for multi‐organ segmentation

Lin

Yang

et al. 2021

Medical Physics

View full text Add to dashboard Cite

With the continuous development of deep learning based medical image segmentation technology, it is expected to attain more robust and accurate performance for more challenging tasks, such as multi-organs, small/irregular areas, and ambiguous boundary issues. Methods: We propose a variance-aware attention U-Net to solve the problem of multi-organ segmentation. Specifically, a simple yet effective variancebased uncertainty mechanism is devised to evaluate the discrimination of each voxel via its prediction probability. The proposed variance uncertainty is further embedded into an attention architecture, which not only aggregates multi-level deep features in a global-level but also enforces the network to pay extra attention to voxels with uncertain predictions during training. Results: Extensive experiments on challenging abdominal multi-organ CT dataset show that our proposed method consistently outperforms cutting-edge attention networks with respect to the evaluation metrics of Dice index (DSC), 95% Hausdorff distance (95HD) and average symmetric surface distance (ASSD). Conclusions:The proposed network provides an accurate and robust solution for multi-organ segmentation and has the potential to be used for improving other segmentation applications.

show abstract

Attention Guided Network for Retinal Image Segmentation

Cited by 152 publications

References 17 publications

ADR‐Net: Context extraction network based on M‐Net for medical image segmentation

ADR‐Net: Context extraction network based on M‐Net for medical image segmentation

Retinal vessel segmentation with constrained-based nonnegative matrix factorization and 3D modified Attention U-Net

Variance‐aware attention U‐Net for multi‐organ segmentation

Contact Info

Product

Resources

About