Dual Encoding U-Net for Retinal Vessel Segmentation

Bo, Wang; Qiu, Shuang; He, Huiguang

doi:10.1007/978-3-030-32239-7_10

Cited by 147 publications

(68 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 compares the performance of different methods for retinal vessel segmentation on the DRIVE dataset. Compared with references [ 21 , 40 , 42 – 44 ], the sensitivity index is low, since many background pixels are still classified as vascular pixels by this method in this paper, but the specificity, accuracy, and F -measure indicators are all optimal. Compared with the method in the study by Samuel and Veeramalai [ 21 ], the specificity of this paper's method was improved by 0.84%.…”

Section: Methodsmentioning

confidence: 85%

“…The segmentation results of the BFCN method are compared with the images of the segmentation results of the methods in the studies by Zhuang [ 43 ] and Wang et al [ 44 ]. The method in the studies by Zhuang [ 43 ] and Wang et al [ 44 ] will generate lots of artifacts, which will cause serious interference to the clinical diagnosis, while the method in this paper generates fewer artifacts. In summary, the method in this paper can effectively and accurately segment retinal blood vessel images.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Efficient BFCN for Automatic Retinal Vessel Segmentation

Jiang

Wang

Gao

et al. 2020

Journal of Ophthalmology

View full text Add to dashboard Cite

Retinal vessel segmentation has high value for the research on the diagnosis of diabetic retinopathy, hypertension, and cardiovascular and cerebrovascular diseases. Most methods based on deep convolutional neural networks (DCNN) do not have large receptive fields or rich spatial information and cannot capture global context information of the larger areas. Therefore, it is difficult to identify the lesion area, and the segmentation efficiency is poor. This paper presents a butterfly fully convolutional neural network (BFCN). First, in view of the low contrast between blood vessels and the background in retinal blood vessel images, this paper uses automatic color enhancement (ACE) technology to increase the contrast between blood vessels and the background. Second, using the multiscale information extraction (MSIE) module in the backbone network can capture the global contextual information in a larger area to reduce the loss of feature information. At the same time, using the transfer layer (T_Layer) can not only alleviate gradient vanishing problem and repair the information loss in the downsampling process but also obtain rich spatial information. Finally, for the first time in the paper, the segmentation image is postprocessed, and the Laplacian sharpening method is used to improve the accuracy of vessel segmentation. The method mentioned in this paper has been verified by the DRIVE, STARE, and CHASE datasets, with the accuracy of 0.9627, 0.9735, and 0.9688, respectively.

show abstract

Section: Methodsmentioning

confidence: 85%

Section: Methodsmentioning

confidence: 99%

Efficient BFCN for Automatic Retinal Vessel Segmentation

Jiang

Wang

Gao

et al. 2020

Journal of Ophthalmology

View full text Add to dashboard Cite

show abstract

“…Yan et al [38] train the U-Net simultaneously with a joint-loss including a pixel-wise and a segment-level loss. DEU-Net [39] introduces a feature fusion module to combine a spatial path with a large kernel to preserve the spatial information and a context path with a multiscale convolution block to capture more semantic information. DeepVessel [40] applies a multi-scale and multi-level Convolutional Neural Network (CNN) with a side-output layer to learn a rich hierarchical representation and model the long-range interactions between pixels by a Conditional Random Field.…”

Section: B Retinal Vessel Segmentationmentioning

confidence: 99%

“…We compare our network with several state-of-the-art models including VesselNet [55], U-Net [5], DU-Net [39], Lad-derNet [53], Bo Liu et al [54]. CE-Net [37].…”

Section: ) Experiments Performancementioning

confidence: 99%

“…Content may change prior to final publication. [38] 2018 0.9542 0.9752 0.7653 0.9818 CE-Net [37] 2019 0.9545 0.9779 0.8309 -LadderNet [53] 2019 0.9561 0.9793 0.7856 0.9810 DU-Net [39] 2019 0.9567 0.9772 0.7940 0.9816 Bo Liu et al [54] 2019 0.9559 0.9779 0.8072 0.9780 VesselNet [55] 2019 0.9578 0.9821 0.8038 0.9802 Ours -0.9604 0.9846 0.7614 0.9837 in ACC and AUC increased by 0.121 and 0.0009 respectively compared to the second highest scores of VesselNet [55]. SPE is also the first place and increases by 0.0032 compared to the previous highest scores of Liskowski et al [26].…”

Section: ) Experiments Performancementioning

confidence: 99%

See 1 more Smart Citation

Deep Guidance Network for Biomedical Image Segmentation

et al. 2020

View full text Add to dashboard Cite

Segmentation of 2D images is a fundamental problem for biomedical image analysis. The most widely used architecture for biomedical image segmentation is U-Net. U-Net introduces skipconnections to restore the spatial information loss caused by down-sampling operations. However, for some tasks such as the retinal vessel segmentation, the loss information of structure can not be fully recovered since the vessels is merely a curve line that can not be detected after several convolutions. In this paper, we introduce a deep guidance network to segment the biomedical image. Our proposed network consists of a guided image filter module to restore the structure information through the guidance image. Our method enables end to end training and fast inference (43ms for one image). We conduct extensive experiments for the task of vessel segmentation and optic disc and cup segmentation. The experiments on four publicly available datasets: ORIGA, REFUGE, DRIVE, and CHASEDB1 verify the effectiveness of our method.

show abstract

Robustness of deep learning methods for ocular fundus segmentation: Evaluation of blur sensitivity

Petrović

Gojić

Dragan

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

This article analyzes the sensitivity of deep learning methods for ocular fundus segmentation. We use an empirical methodology based on non-adversarial perturbed datasets. The research is motivated by mass screening and self-administered tests in which AI methods are needed and may be given images with focus issues. These substandard pictures are simulated using blurring algorithms of varying designs and kernel sizes which are subjected to a test of inter-network and inter-dataset sensitivity using Gaussian noise as a control. We test for simulated defocusing, motion blur, and Gaussian noise. The DRIVE, CHASE, and STARE datasets were used to generate 441 synthetic datasets for testing. Analysis of the resultant n = 37,888 sample has identified anomalies illuminating failure modes of state-of-the-art ocular segmentation models. Data analysis led us to conclude that accuracy is a poor measure of sensitivity to input change and that even moderate levels of blur have dramatic effects on said sensitivity. We further concluded that architectures show larger variations in sensitivity to blur which do not match either their reported or measured performance on unblurred test datasets. Our analysis has attributed at least a part of the problem to overfitting non-essential input dataset features and resolution sensitivity.

show abstract

Dual Encoding U-Net for Retinal Vessel Segmentation

Cited by 147 publications

References 10 publications

Efficient BFCN for Automatic Retinal Vessel Segmentation

Efficient BFCN for Automatic Retinal Vessel Segmentation

Deep Guidance Network for Biomedical Image Segmentation

Robustness of deep learning methods for ocular fundus segmentation: Evaluation of blur sensitivity

Contact Info

Product

Resources

About