Retinal vessel delineation using a brain-inspired wavelet transform and random forest

Zhang, Jiong; Yuan, Chen; Bekkers, Erik J.; Wang, Meili; Dashtbozorg, Behdad; Romeny, Bart M. ter Haar

doi:10.1016/j.patcog.2017.04.008

Cited by 107 publications

(43 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their AUC values are 0.9682 and 0.9789 for DRIVE and STARE datasets, respectively. Multiple scales and orientation features from the wavelet transform along with random forest classifier has improved performance metrics and achieves better AUC values [36].…”

Section: Quantitative Analysismentioning

confidence: 99%

“…Although unsupervised methods do not need prior knowledge about the segmentation and are fast to run [30,31], it takes time to interpret the results correctly. Supervised methods require a lot of features and expertise to accurately segment the blood vessels [32][33][34][35][36][37]. Supervised learning algorithms based on deep convolutional neural networks (CNN) show utmost robustness and efficiency in segmenting the blood vessels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation

Samuel

Veeramalai

2019

Symmetry

View full text Add to dashboard Cite

Retinal blood vessel segmentation influences a lot of blood vessel-related disorders such as diabetic retinopathy, hypertension, cardiovascular and cerebrovascular disorders, etc. It is found that vessel segmentation using a convolutional neural network (CNN) showed increased accuracy in feature extraction and vessel segmentation compared to the classical segmentation algorithms. CNN does not need any artificial handcrafted features to train the network. In the proposed deep neural network (DNN), a better pre-processing technique and multilevel/multiscale deep supervision (DS) layers are being incorporated for proper segmentation of retinal blood vessels. From the first four layers of the VGG-16 model, multilevel/multiscale deep supervision layers are formed by convolving vessel-specific Gaussian convolutions with two different scale initializations. These layers output the activation maps that are capable to learn vessel-specific features at multiple scales, levels, and depth. Furthermore, the receptive field of these maps is increased to obtain the symmetric feature maps that provide the refined blood vessel probability map. This map is completely free from the optic disc, boundaries, and non-vessel background. The segmented results are tested on Digital Retinal Images for Vessel Extraction (DRIVE), STructured Analysis of the Retina (STARE), High-Resolution Fundus (HRF), and real-world retinal datasets to evaluate its performance. This proposed model achieves better sensitivity values of 0.8282, 0.8979 and 0.8655 in DRIVE, STARE and HRF datasets with acceptable specificity and accuracy performance metrics.

show abstract

Section: Quantitative Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation

Samuel

Veeramalai

2019

Symmetry

View full text Add to dashboard Cite

show abstract

“…Orlando et al proposed a fully connected conditional random field model, using a structured output support vector machine to learn model parameters, and performed retinal vessel segmentation [ 15 ]. Zhang et al extracted the features by vessel filtering and wavelet transform strategy, applied the random forest training strategy learn the classifier’s parameters, and performed retinal vessel segmentation [ 16 ]. For the traditional machine learning methods, feature selection has great influence on segmentation accuracy, and the independent features with high vessel recognition rate is the critical step.…”

Section: Introductionmentioning

confidence: 99%

Dense U-net Based on Patch-Based Learning for Retinal Vessel Segmentation

Wang

Zhao

Ren

et al. 2019

Entropy

168

113

View full text Add to dashboard Cite

Various retinal vessel segmentation methods based on convolutional neural networks were proposed recently, and Dense U-net as a new semantic segmentation network was successfully applied to scene segmentation. Retinal vessel is tiny, and the features of retinal vessel can be learned effectively by the patch-based learning strategy. In this study, we proposed a new retinal vessel segmentation framework based on Dense U-net and the patch-based learning strategy. In the process of training, training patches were obtained by random extraction strategy, Dense U-net was adopted as a training network, and random transformation was used as a data augmentation strategy. In the process of testing, test images were divided into image patches, test patches were predicted by training model, and the segmentation result can be reconstructed by overlapping-patches sequential reconstruction strategy. This proposed method was applied to public datasets DRIVE and STARE, and retinal vessel segmentation was performed. Sensitivity (Se), specificity (Sp), accuracy (Acc), and area under each curve (AUC) were adopted as evaluation metrics to verify the effectiveness of proposed method. Compared with state-of-the-art methods including the unsupervised, supervised, and convolutional neural network (CNN) methods, the result demonstrated that our approach is competitive in these evaluation metrics. This method can obtain a better segmentation result than specialists, and has clinical application value.

show abstract

“…In general, the corneal nerve fiber segmentation can be considered as a problem within the scope of curvilinear structure enhancement and segmentation tasks [22][23][24]. For instance, extensive conventional approaches have been applied to segment elongated medical imaging structures in three categories: classifier based, tracking based and filter based.…”

Section: Introductionmentioning

confidence: 99%

Automatic corneal nerve fiber segmentation and geometric biomarker quantification

et al. 2020

Self Cite

View full text Add to dashboard Cite

Geometric and topological features of corneal nerve fibers in confocal microscopy images are important indicators for the diagnosis of common diseases such as diabetic neuropathy. Quantitative analysis of these important biomarkers requires an accurate segmentation of the nerve fiber network. Currently, most of the analysis are performed based on manual annotations of the nerve fiber segments, while a fully automatic corneal nerve fiber extraction and analysis framework is still needed. In this paper, we establish a fully convolutional network method to precisely enhance and segment corneal nerve fibers in microscopy images. Based on the segmentation results, automatic tortuosity measurement and branching detection modules are established to extract valuable geometric and topological biomarkers. The proposed segmentation method is validated on a dataset with 142 images. The experimental results show that our deep learning-based framework outperforms state-of-the-art segmentation approaches. The biomarker extraction methods are validated on two different datasets, demonstrating high effectiveness and reliability of the proposed methods.

show abstract

Retinal vessel delineation using a brain-inspired wavelet transform and random forest

Cited by 107 publications

References 46 publications

Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation

Multilevel and Multiscale Deep Neural Network for Retinal Blood Vessel Segmentation

Dense U-net Based on Patch-Based Learning for Retinal Vessel Segmentation

Automatic corneal nerve fiber segmentation and geometric biomarker quantification

Contact Info

Product

Resources

About