Automatic 2-D/3-D Vessel Enhancement in Multiple Modality Images Using a Weighted Symmetry Filter

Zhao, Yitian; Zheng, Yalin; Liu, Yonghuai; Zhao, Yifan; Luo, Lingling; Yang, Siyuan; Tong, Na; Wang, Yongtian; Jiang, Leng

doi:10.1109/tmi.2017.2756073

Cited by 100 publications

(83 citation statements)

References 43 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To justify the performance improvement compared with the state-of-the-art algorithms, we finally compare our method with other methods proposed by Azzopardi [49], Zhao [15], Roychowdhury [80], Zhao [16], Xie [67], Fu [17], Zhou [51] and Ronneberger [22]. For the DRIVE dataset, the results are from the original papers.…”

Section: F Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…The earlier traditional method [47] used support vector machines. Zhao et al [15] [16] proposed infinite perimeter active contour model with hybrid region information and a weighted symmetry filter to detect vessels. Some other methods used a variety of filters to enhance the blood vessels [51] proposed to learn more discriminative features by improving dense CRF.…”

Section: B Vessel Detectionmentioning

confidence: 99%

“…Zhao et al [14] further proposed a vessel segmentation model based on saliency guided infinite perimeter active contour. A more detailed review of traditional vessel detection methods can be found in [15] [16]. A common limitation of these traditional vessel detection algorithms is that they often require some manually determined parameters tuned based on local data set, which makes the algorithms less scalable.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Dense Dilated Network With Probability Regularized Walk for Vessel Detection

Mou

Chen

Cheng

et al. 2020

IEEE Trans. Med. Imaging

Self Cite

119

View full text Add to dashboard Cite

The detection of retinal vessel is of great importance in the diagnosis and treatment of many ocular diseases. Many methods have been proposed for vessel detection. However, most of the algorithms neglect the connectivity of the vessels, which plays an important role in the diagnosis. In this paper, we propose a novel method for retinal vessel detection. The proposed method includes a dense dilated network to get an initial detection of the vessels and a probability regularized walk algorithm to address the fracture issue in the initial detection. The dense dilated network integrates newly proposed dense dilated feature extraction blocks into an encoder-decoder structure to extract and accumulate features at different scales. A multiscale Dice loss function is adopted to train the network. To improve the connectivity of the segmented vessels, we also introduce a probability regularized walk algorithm to connect the broken vessels. The proposed method has been applied on three public data sets: DRIVE, STARE and CHASE DB1. The results show that the proposed method outperforms the state-ofthe-art methods in accuracy, sensitivity, specificity and also area under receiver operating characteristic curve.

show abstract

Section: F Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: B Vessel Detectionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Dense Dilated Network With Probability Regularized Walk for Vessel Detection

Mou

Chen

Cheng

et al. 2020

IEEE Trans. Med. Imaging

Self Cite

119

View full text Add to dashboard Cite

show abstract

“…To further validate the effectiveness and robustness of our method, we perform an experiment on the HRF dataset [66], [67] comprising 45 high-resolution images divided into healthy, diabetic retinopathy and glaucomatous sets. Every set comprises 15 fundus images, each of size 3504 × 2336 pixels.…”

Section: F Evaluation On High-resolution Fundus Images (Hrf)mentioning

confidence: 99%

Deep Retinal Image Segmentation With Regularization Under Geometric Priors

Cherukuri

Bala

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Vessel segmentation of retinal images is a key diagnostic capability in ophthalmology. This problem faces several challenges including low contrast, variable vessel size and thickness, and presence of interfering pathology such as micro-aneurysms and hemorrhages. Early approaches addressing this problem employed hand-crafted filters to capture vessel structures, accompanied by morphological post-processing. More recently, deep learning techniques have been employed with significantly enhanced segmentation accuracy. We propose a novel domain enriched deep network that consists of two components: 1) a representation network that learns geometric features specific to retinal images, and 2) a custom designed computationally efficient residual task network that utilizes the features obtained from the representation layer to perform pixel-level segmentation. The representation and task networks are jointly learned for any given training set. To obtain physically meaningful and practically effective representation filters, we propose two new constraints that are inspired by expected prior structure on these filters: 1) orientation constraint that promotes geometric diversity of curvilinear features, and 2) a data adaptive noise regularizer that penalizes false positives. Multi-scale extensions are developed to enable accurate detection of thin vessels. Experiments performed on three challenging benchmark databases under a variety of training scenarios show that the proposed prior guided deep network outperforms state of the art alternatives as measured by common evaluation metrics, while being more economical in network size and inference time.

show abstract

“…Retinal fundus photographs have been widely used by clinicians to diagnose and monitor many ocular diseases including glaucoma, pathological myopia, age-related macular degeneration, and diabetic retinopathy. Since manual assessment of the images is tedious, expensive and subjective, computer aided diagnosis methods [1] have been developed to analyse the images automatically for optic disc segmentation [2]- [5], Manuscript optic cup segmentation or cup to disc ratio assessment [6]- [9], retinal vessel detection [10], [11], glaucoma detection [12], [13], diabetic retinopathy detection [14], [15], age-related macular degeneration detection [16]- [19], and pathological myopia detection [20]. Image quality is an essential factor for proper development and validation of the algorithms [21].…”

Section: Introductionmentioning

confidence: 99%