VSSC Net: Vessel Specific Skip chain Convolutional Network for blood vessel segmentation

Samuel, Pearl Mary; Veeramalai, Thanikaiselvan

doi:10.1016/j.cmpb.2020.105769

Cited by 88 publications

(25 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jothi et al [44] have described a new algorithm based on Frangi filter based on the concept that vessels in image consists of a small area to be considered and are lighter or darker than their background. Samuel et al [45] introduced CNN based method Vessel Specific Skip Chain Convolution Network for BV segmentation which is used to detect vessels in fundus as well as X-ray Coronary Angiogram images.…”

Section: Blood Vessel (Bv) Segmentationmentioning

confidence: 99%

A Survey on Automatic Diabetic Retinopathy Screening

Nage

Shitole

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Diabetes is a chronic disease caused due to the increase in the sugar level in the blood. Diabetes mainly affects heart, blood vessels, kidneys, eyes and nerves. There are mellitus type 1 and 2 diabetes, in which insulin is either not taken by the body or not created by the body. As per the statistics provided by WHO, about 422 million people worldwide are fighting with diabetes. Primary source of vision loss in the patients suffering from diabetes is diabetic retinopathy where the individual suffers from the damage and growth of abnormal blood veins in the retina. The disease is observed by ophthalmologist through identifying the presence of abnormalities starting from microaneurysms in the non-proliferative stage of DR and if these lesions' presence is ignored and not detected then it leads to the neovascularization in the proliferative stage which leads to unavoidable vision loss. DR can be cured if detected at the beginning stage. Manual method takes lots of time for detection of DR hence it is important to develop computer-based diagnostic system for DR detection using artificial intelligence (AI) and advance image processing to help ophthalmologists for spotting early symptoms of DR in less time. This paper provides a descriptive study about recent trends and technologies used for automatic spotting and grading of DR.

show abstract

Section: Blood Vessel (Bv) Segmentationmentioning

confidence: 99%

A Survey on Automatic Diabetic Retinopathy Screening

Nage

Shitole

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning approaches have gained popularity in segmenting both major arteries and full artery trees from XCA images. Samuel and Veeramalai [ 38 ] proposed a Vessel Specific Skip Chain Network by adding two vessel-specific layers to the VGG-16 network [ 39 ]. Jo et al [ 33 ] developed a two-stage CNN specifically for left anterior descending artery segmentation, where the first stage located candidate areas of interest and the second stage generated the segmentation mask.…”

Section: Introductionmentioning

confidence: 99%

Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features

et al. 2022

View full text Add to dashboard Cite

Background Automated segmentation of coronary arteries is a crucial step for computer-aided coronary artery disease (CAD) diagnosis and treatment planning. Correct delineation of the coronary artery is challenging in X-ray coronary angiography (XCA) due to the low signal-to-noise ratio and confounding background structures. Methods A novel ensemble framework for coronary artery segmentation in XCA images is proposed, which utilizes deep learning and filter-based features to construct models using the gradient boosting decision tree (GBDT) and deep forest classifiers. The proposed method was trained and tested on 130 XCA images. For each pixel of interest in the XCA images, a 37-dimensional feature vector was constructed based on (1) the statistics of multi-scale filtering responses in the morphological, spatial, and frequency domains; and (2) the feature maps obtained from trained deep neural networks. The performance of these models was compared with those of common deep neural networks on metrics including precision, sensitivity, specificity, F1 score, AUROC (the area under the receiver operating characteristic curve), and IoU (intersection over union). Results With hybrid under-sampling methods, the best performing GBDT model achieved a mean F1 score of 0.874, AUROC of 0.947, sensitivity of 0.902, and specificity of 0.992; while the best performing deep forest model obtained a mean F1 score of 0.867, AUROC of 0.95, sensitivity of 0.867, and specificity of 0.993. Compared with the evaluated deep neural networks, both models had better or comparable performance for all evaluated metrics with lower standard deviations over the test images. Conclusions The proposed feature-based ensemble method outperformed common deep convolutional neural networks in most performance metrics while yielding more consistent results. Such a method can be used to facilitate the assessment of stenosis and improve the quality of care in patients with CAD.

show abstract

“…As the case of the networks expended in the studies [27,40], the segmentation has been produced respectively in 15.3s and 96s, despite that have been both executed into recent multi-GPU architectures. with respect to the accurately and computational constraints, several segmentation methods suggest extending well-known networks such as U-net in the works [27,28,29], Alexnet [26], VGG [41] and Z-Fnet [42] [94]. However, these network extensions still unable to reach the targeted trade-off.…”

Section: Introductionmentioning

confidence: 99%

Fast and efficient retinal blood vessel segmentation method based on deep learning network

Boudegga

Elloumi

Akil

et al. 2021

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

The segmentation of the retinal vascular tree presents a major step for detecting ocular pathologies. The clinical context expects higher segmentation performance with a reduced processing time. For higher accurate segmentation, several automated methods have been based on Deep Learning (DL) networks. However, the used convolutional layers bring to a higher computational complexity and so for execution times. For such need, this work presents a new DL based method for retinal vessel tree segmentation. Our main contribution consists in suggesting a new U-form DL architecture using lightweight convolution blocks in order to preserve a higher segmentation performance while reducing the computational complexity. As a second main contribution, preprocessing and data augmentation steps are proposed with respect to the retinal image and blood vessel characteristics. The proposed method is tested on DRIVE and STARE databases, which can achieve a better trade-off between the retinal blood vessel detection rate and the detection time with average accuracy of 0.978 and 0.98 in 0.59s and 0.48s per fundus image on GPU NVIDIA GTX 980 platforms, respectively for DRIVE and STARE database fundus images.

show abstract

VSSC Net: Vessel Specific Skip chain Convolutional Network for blood vessel segmentation

Cited by 88 publications

References 47 publications

A Survey on Automatic Diabetic Retinopathy Screening

A Survey on Automatic Diabetic Retinopathy Screening

Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features

Fast and efficient retinal blood vessel segmentation method based on deep learning network

Contact Info

Product

Resources

About