Multichannel Retinal Blood Vessel Segmentation Based on the Combination of Matched Filter and U‐Net Network

Ma, Yuliang; Zhu, Zhenbin; Dong, Zhekang; Shen, Tao; Sun, Mingxu; Kong, Wanzeng

doi:10.1155/2021/5561125

Cited by 15 publications

(13 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, we validate the outcome of proposed approach by presenting quantitative comparative analysis. (d)Technique in [28] (e) Technique in [29] (f) Technique in [30] (g) Technique in [31] (h) Technique in [26] (i) Proposed approach Figure .13. Blood vessel segmentation results for DRIVE dataset Above given figure 13 illustrates the comparative analysis for blood vessel segmentation.…”

Section: Comparative Analysis For Blood Vessel Segmentationmentioning

confidence: 99%

“…Blood vessel segmentation results for DRIVE dataset Above given figure 13 illustrates the comparative analysis for blood vessel segmentation. For one input image, we have compared the output of several techniques such as mentioned in [27], [28], [29], [30], [31] and [26]. The outcome is presented in the extracted vessels.…”

Section: Comparative Analysis For Blood Vessel Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Channel and Spatial Attention Aware UNet Architecture for Segmentation of Blood Vessels, Exudates and Microaneurysms in Diabetic Retinopathy

2023

Preprint

View full text Add to dashboard Cite

Diabetic retinopathy stands out as one of the highly prevalent causes of vision loss in working people worldwide. In computer vision, deep learning based strategies are seen as a viable solution for efficient diabetic retinopathy detection. We present a UNet-based deep learning architecture for diabetic retinopathy segmentation of blood vessels, exudates, and microaneurysms. Traditional methods often consider the features only from the last convolution unit and discard the remaining features, resulting in low-quality feature maps. To overcome this, we introduce a skip connection mechanism to concatenate all attributes from each layer. Additionally, we utilize an upsampling layer to aggregate the features at the final sigmoid layer. Finally, we apply channel and spatial attention mechanisms to generate the semantic feature map. We tested proposed approach on several publicly available datasets such as IDRiD, DIARETDB1, STARE, ChaseDB1, DRIVE, and HRF datasets. The comparative analysis shows that the proposed approach achieves superior performance, with an average accuracy of 98.10%, average sensitivity of 97.60%, and average specificity of 98.2% for segmentation.

show abstract

Section: Comparative Analysis For Blood Vessel Segmentationmentioning

confidence: 99%

Section: Comparative Analysis For Blood Vessel Segmentationmentioning

confidence: 99%

Channel and Spatial Attention Aware UNet Architecture for Segmentation of Blood Vessels, Exudates and Microaneurysms in Diabetic Retinopathy

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Siddique et al gave a review of U-Net and its variant techniques for image segmentation and specifically highlighted their applications in retinal fundus image segmentation ( 36 ). Yuliang et al propose a retinal blood vessel segmentation model that combines a multiscale matched filter with a U-Net that has been tested on various available public datasets ( 37 ). Shabbir et al describe different types of ML models for glaucoma detection from fundus image like multiscale, texture feature-based, Segmentation-based, CNN, Ensemble Learning approaches in detail ( 38 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Retinal Vessel Extraction via Assisted Multi-Channel Feature Map and U-Net

Bhatia

Alam

Shuaib

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Early detection of vessels from fundus images can effectively prevent the permanent retinal damages caused by retinopathies such as glaucoma, hyperextension, and diabetes. Concerning the red color of both retinal vessels and background and the vessel's morphological variations, the current vessel detection methodologies fail to segment thin vessels and discriminate them in the regions where permanent retinopathies mainly occur. This research aims to suggest a novel approach to take the benefit of both traditional template-matching methods with recent deep learning (DL) solutions. These two methods are combined in which the response of a Cauchy matched filter is used to replace the noisy red channel of the fundus images. Consequently, a U-shaped fully connected convolutional neural network (U-net) is employed to train end-to-end segmentation of pixels into vessel and background classes. Each preprocessed image is divided into several patches to provide enough training images and speed up the training per each instance. The DRIVE public database has been analyzed to test the proposed method, and metrics such as Accuracy, Precision, Sensitivity and Specificity have been measured for evaluation. The evaluation indicates that the average extraction accuracy of the proposed model is 0.9640 on the employed dataset.

show abstract

“…The focus of the work in [12] was to consider the cup and disk segmentation problem jointly instead of individually segmenting the optic disc and cup. The minimum bounding boxes of the optic disc and cup are initially detected.…”

Section: Glaucomamentioning

confidence: 99%

A Systematic Study of Deep Learning Architectures for Analysis of Glaucoma and Hypertensive Retinopathy

M¹,

Prasad²,

Kulkarni³

et al. 2022

IJAIA

View full text Add to dashboard Cite

Deep learning models are applied seamlessly across various computer vision tasks like object detection, object tracking, scene understanding and further. The application of cutting-edge deep learning (DL) models like U-Net in the classification and segmentation of medical images on different modalities has established significant results in the past few years. Ocular diseases like Diabetic Retinopathy (DR), Glaucoma, Age-Related Macular Degeneration (AMD / ARMD), Hypertensive Retina (HR), Cataract, and dry eyes can be detected at the early stages of disease onset by capturing the fundus image or the anterior image of the subject’s eye. Early detection is key to seeking early treatment and thereby preventing the disease progression, which in some cases may lead to blindness. There is a plethora of deep learning models available which have established significant results in medical image processing and specifically in ocular disease detection. A given task can be solved by using a variety of models and or a combination of them. Deep learning models can be computationally expensive and deploying them on an edge device may be a challenge. This paper provides a comprehensive report and critical evaluation of the various deep learning architectures that can be used to segment and classify ocular diseases namely Glaucoma and Hypertensive Retina on the posterior images of the eye. This review also compares the models based on complexity and edge deployability.

show abstract

Multichannel Retinal Blood Vessel Segmentation Based on the Combination of Matched Filter and U‐Net Network

Cited by 15 publications

References 44 publications

Channel and Spatial Attention Aware UNet Architecture for Segmentation of Blood Vessels, Exudates and Microaneurysms in Diabetic Retinopathy

Channel and Spatial Attention Aware UNet Architecture for Segmentation of Blood Vessels, Exudates and Microaneurysms in Diabetic Retinopathy

Retinal Vessel Extraction via Assisted Multi-Channel Feature Map and U-Net

A Systematic Study of Deep Learning Architectures for Analysis of Glaucoma and Hypertensive Retinopathy

Contact Info

Product

Resources

About