Retinal blood vessel segmentation based on the Gaussian matched filter and U-net

Gao, Xudong; Yuan-hu, Cai; Qiu, Changyan; Cui, Yize

doi:10.1109/cisp-bmei.2017.8302199

Cited by 33 publications

(22 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen from the table that the accuracy, specificity and AUC of the proposed method are all higher than those of the other listed methods, reaching 96.83, 98.97 and 0.9830%, respectively. In terms of accuracy, the second highest comparison reaches 96.36% in [23], which is still 0.47% lower than that of the proposed method, and its other three indexes are 2.64, 0.21, 0.0058% lower than that of the proposed method, respectively; in terms of sensitivity, the highest comparison reaches 80.78% in [24], which is 0.12% higher than that of the proposed method, but its accuracy and specificity are 2.14 and 2.23% lower than that of the proposed method, respectively; in terms of specificity, the second highest comparison reaches 98.94% in [25], which is just 0.03% lower than that of the proposed method, and its accuracy and sensitivity are 1.81 and 6.56% lower than that of the proposed method, respectively; in terms of AUC, the second highest comparison reaches 0.9800 in [26], which is 0.0030 lower than that of the proposed method, and its other three indexes are 1.27, 0.3 and 1.19% lower than that of the proposed method, respectively.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Retinal vessel segmentation based on task‐driven generative adversarial network

et al. 2020

View full text Add to dashboard Cite

Retinal vessel segmentation has important application value in clinical diagnosis. If experts manually segment the retinal vessels, the workload is heavy, and the result is strong subjectively. However, some existing automatic segmentation methods have the problems of incomplete vessel segmentation and low‐segmentation accuracy. In order to solve the above problems, this study proposes a retinal vessel segmentation method based on task‐driven generative adversarial network (GAN). In the generative model, a U‐Net network is used to segment the retinal vessels. In the discriminative model, multi‐scale discriminators with different receptive fields are used to guide the generative model to generate more details. On the other hand, in view of the uncontrollable characteristics of the data generated by the traditional GAN, a task‐driven model based on perceptual loss is added to traditional GAN for feature matching, which makes the generated image more task‐specific. Experimental results show that the accuracy, sensitivity, specificity and area under the receiver operating characteristic curve of the proposed method on data set digital retinal images for vessel extraction are 96.83, 80.66, 98.97 and 0.9830%, respectively.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Retinal vessel segmentation based on task‐driven generative adversarial network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Gao et al [74] proposed a method based on Gaussian matched filter and U-net (fully convolutional neural network) for the prediction of vessel segmentation. The thin vessels were strengthened using the Gaussian matched filter while U-net was used for end-end automatic retinal vessel segmentation.…”

Section: ) Matched Filtered Methodsmentioning

confidence: 99%

Comparative Analysis of Vessel Segmentation Techniques in Retinal Images

Imran

Pei

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The blood vessels are the primary anatomical structure that can be visible in retinal images. The segmentation of retinal blood vessels has been accepted worldwide for the diagnosis of both cardiovascular (CVD) and retinal diseases. Thus, it requires an appropriate vessel segmentation method for automatic detection of retinal diseases such as diabetic retinopathy and cataract. The detection of retinal diseases using computer-aided diagnosis (CAD) can help people to avoid the risks of visual impairment and save medical resources. This survey presents a comparative analysis of various machine learning and deep learning-based methods for automated blood vessel segmentation in retinal images. This paper briefly describes fundus photography, publicly available retinal databases, pre-processing and post-processing techniques for retinal vessels segmentation. A comprehensive review of the state of the art supervised and unsupervised blood vessel segmentation methodologies are presented in this paper. The objective of this study is to establish a professional structure to familiarize an individual with up-to-date vessel segmentation techniques. Moreover, we compared these approaches to the dataset, evaluation metrics, pre-processing and post-processing steps, feature extraction, segmentation methods, and induced results.

show abstract

“…The number of training images available was only 39, but training was done using data augmentation. Gao et al [18] utilized U-net architecture along Gaussian matched filter to outperform the existing algorithms of blood vessel segmentation from fundus images. Work proposed in [47] consists of applying a customized loss function on U-net architecture for the purpose of segmentation of OD and OC.…”

Section: Related Workmentioning

confidence: 99%

Improved optic disc and cup segmentation in Glaucomatic images using deep learning architecture

Mangipudi

Pandey

Choudhary

2021

Multimed Tools Appl

View full text Add to dashboard Cite

Glaucoma is an ailment causing permanent vision loss but can be prevented through the early detection. Optic disc to cup ratio is one of the key factors for glaucoma diagnosis. But accurate segmentation of disc and cup is still a challenge. To mitigate this challenge, an effective system for optic disc and cup segmentation using deep learning architecture is presented in this paper. Modified Groundtruth is utilized to train the proposed model. It works as fused segmentation marking by multiple experts that helps in improving the performance of the system. Extensive computer simulations are conducted to test the efficiency of the proposed system. For the implementation three standard benchmark datasets such as DRISHTI-GS, DRIONS-DB and RIM-ONE v3 are used. The performance of the proposed system is validated against the state-of-the-art methods. Results indicate an average overlapping score of 96.62%, 96.15% and 98.42% respectively for optic disc segmentation and an average overlapping score of 94.41% is achieved on DRISHTI-GS which is significant for optic cup segmentation.

show abstract

Retinal blood vessel segmentation based on the Gaussian matched filter and U-net

Cited by 33 publications

References 18 publications

Retinal vessel segmentation based on task‐driven generative adversarial network

Retinal vessel segmentation based on task‐driven generative adversarial network

Comparative Analysis of Vessel Segmentation Techniques in Retinal Images

Improved optic disc and cup segmentation in Glaucomatic images using deep learning architecture

Contact Info

Product

Resources

About