Artery/vein classification in fundus images using CNN and likelihood score propagation

Girard, Fantin; Cheriet, Foued

doi:10.1109/globalsip.2017.8309054

Cited by 18 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The model can take the whole image directly as input, thereby avoiding the use of overlap strategies as with DeepVessel. Compared to the original U-Net model, patches fed to our network can be of any size, which is a significant advantage when dealing with images of different [42] 86.0% ± 4% 83.8% ± 9% 125s Niemeijer et al [5] 80.0% 80.0% resolutions.…”

Section: Comparison Of Segmentation Results With the State Of The Artmentioning

confidence: 99%

“…The positive detections are defined as the arteries pixels while the negative are veins. Table 9 also reports the performance of three recent state-of-the-art methods on CT-DRIVE, and of another CNN system we recently proposed [42] which uses a pixel classification (PC) approach similar to [40,41]. Classifying arteries and veins is more accurate with the encoder-decoder model strategy and it is also significantly faster.…”

Section: Comparison Of A/v Classification Results With the State Of Tmentioning

confidence: 99%

See 1 more Smart Citation

Joint segmentation and classification of retinal arteries/veins from fundus images

Girard

Kavalec

Cheriet

2019

Artificial Intelligence in Medicine

Self Cite

View full text Add to dashboard Cite

Objective: Automatic artery/vein (A/V) segmentation from fundus images is required to track blood vessel changes occurring with many pathologies including retinopathy and cardiovascular pathologies. One of the clinical measures that quantifies vessel changes is the arterio-venous ratio (AVR) which represents the ratio between artery and vein diameters. This measure significantly depends on the accuracy of vessel segmentation and classification into arteries and veins. This paper proposes a fast, novel method for semantic A/V segmentation combining deep learning and graph propagation. Methods: A convolutional neural network (CNN) is proposed to jointly segment and classify vessels into arteries and veins. The initial CNN labeling is propagated through a graph representation of the retinal vasculature, whose nodes are defined as the vessel branches and edges are weighted by the cost of linking pairs of branches. To efficiently propagate the labels, the graph is simplified into its minimum spanning tree.Results: The method achieves an accuracy of 94.8% for vessels segmentation. The A/V classification achieves a specificity of 92.9% with a sensitivity of 93.7% on the CT-DRIVE database compared to the state-of-the-art-specificity and sensitivity, both of 91.7%. Conclusion: The results show that our method outperforms the leading previous works on a public dataset for A/V classification and is by far the fastest. Significance: The proposed global AVR calculated on the whole fundus image using our automatic A/V segmentation method can better track vessel changes associated to diabetic retinopathy than the standard local AVR calculated only around the optic disc.

show abstract

Section: Comparison Of Segmentation Results With the State Of The Artmentioning

confidence: 99%

Section: Comparison Of A/v Classification Results With the State Of Tmentioning

confidence: 99%

Joint segmentation and classification of retinal arteries/veins from fundus images

Girard

Kavalec

Cheriet

2019

Artificial Intelligence in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…A decision tree is a tree-based classifier built from the training set, where leaf nodes correspond to the classes, and internal nodes are feature condition points that divide instances with different characteristics [55]. Convolutional neural network (CNN) is used to detect pulmonary vascular diseases [56] and classify the artery fundus images to assess diabetes, hypertension or other cardiovascular pathologies [57].…”

Section: Classificationmentioning

confidence: 99%

Detection of Collaterals from Cone-Beam CT Images in Stroke

Aziz

Izhar

Asirvadam

et al. 2021

Sensors

View full text Add to dashboard Cite

Collateral vessels play an important role in the restoration of blood flow to the ischemic tissues of stroke patients, and the quality of collateral flow has major impact on reducing treatment delay and increasing the success rate of reperfusion. Due to high spatial resolution and rapid scan time, advance imaging using the cone-beam computed tomography (CBCT) is gaining more attention over the conventional angiography in acute stroke diagnosis. Detecting collateral vessels from CBCT images is a challenging task due to the presence of noises and artifacts, small-size and non-uniform structure of vessels. This paper presents a technique to objectively identify collateral vessels from non-collateral vessels. In our technique, several filters are used on the CBCT images of stroke patients to remove noises and artifacts, then multiscale top-hat transformation method is implemented on the pre-processed images to further enhance the vessels. Next, we applied three types of feature extraction methods which are gray level co-occurrence matrix (GLCM), moment invariant, and shape to explore which feature is best to classify the collateral vessels. These features are then used by the support vector machine (SVM), random forest, decision tree, and K-nearest neighbors (KNN) classifiers to classify vessels. Finally, the performance of these classifiers is evaluated in terms of accuracy, sensitivity, precision, recall, F-Measure, and area under the receiver operating characteristics curve. Our results show that all classifiers achieve promising classification accuracy above 90% and able to detect the collateral and non-collateral vessels from images.

show abstract

“…Vazquez et al [3] combined color-based clustering and blood vessel tracking to differentiate arteries from veins, and the tracking strategy based on the minimal path approach was employed to support the resulting classification by voting. Girard and Cheriet [25] trained a convolutional neural network (CNN) for the task of assigning blood vessel pixels into arteries or veins. This approach propagated the blood vessel graph by using the minimum spanning tree.…”

Section: Related Workmentioning

confidence: 99%

Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering

Zhao

Liu

Xie

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

The estimation of vascular network topology in complex networks is important in understanding the relationship between vascular changes and a wide spectrum of diseases. Automatic classification of the retinal vascular trees into arteries and veins is of direct assistance to the ophthalmologist in terms of diagnosis and treatment of eye disease. However, it is challenging due to their projective ambiguity and subtle changes in appearance, contrast and geometry in the imaging process. In this paper, we propose a novel method that is capable of making the artery/vein (A/V) distinction in retinal color fundus images based on vascular network topological properties. To this end, we adapt the concept of dominant set clustering and formalize the retinal blood vessel topology estimation and the A/V classification as a pairwise clustering problem. The graph is constructed through image segmentation, skeletonization and identification of significant nodes. The edge weight is defined as the inverse Euclidean distance between its two end points in the feature space of intensity, orientation, curvature, diameter, and entropy. The reconstructed vascular network is classified into arteries and veins based on their intensity and morphology. The proposed approach has been applied to five public databases, INSPIRE, IOSTAR, VICAVR, DRIVE and WIDE, and achieved high accuracies of 95.1%, 94.2%, 93.8%, 91.1%, and 91.0%, respectively. Furthermore, we have made manual annotations of the blood vessel topologies for INSPIRE, IOSTAR, VICAVR, and DRIVE datasets, and these annotations are released for public access so as to facilitate researchers in the community.

show abstract

Artery/vein classification in fundus images using CNN and likelihood score propagation

Cited by 18 publications

References 7 publications

Joint segmentation and classification of retinal arteries/veins from fundus images

Joint segmentation and classification of retinal arteries/veins from fundus images

Detection of Collaterals from Cone-Beam CT Images in Stroke

Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering

Contact Info

Product

Resources

About