Automatic Coronary Centerline Extraction Using Gradient Vector Flow Field and Fast Marching Method From CT Images

Cui, Hengfei; Xia, Yong

doi:10.1109/access.2018.2859786

Cited by 9 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MF filter can achieve relatively good results for both datasets. Oliveira's method Frangi [14] 0.8880 0.8980 GW [7] 0.9306 0.8117 MF [20] 0.9309 0.9422 Oliveira's [4] 0.9379 0.9392 mFrangi [17] 0.9381 0.9472 MFAT [2] 0.9400 0.9500 Proposed 0.9634 0.9657 is able to improve the AUC values up to 0.9379 and 0.9392, which is found to outperform each single filter. Unfortunately, it can be seen that the improvement in the segmentation accuracy is marginal.…”

Section: Retinal Imagesmentioning

confidence: 94%

“…On the other hand, unsupervised techniques [9,[11][12][13] are normally capable of revealing patterns, correlations and clusters, which can be performed without hand-labeled ground truth images. Many tubular structure enhancement techniques have been developed based on the Hessian matrix [14][15][16][17][18]. Frangi's filter [14] is the pioneer work to capture vessel structures by exploiting the eigensystem of the Hessian matrix, which calculates the second-order Gaussian derivatives for multiple values of standard deviation.…”

Section: Introductionmentioning

confidence: 99%

“…A novel enhancement filter is proposed in [15] , which utilizes the ratio of the Hessian eigenvalues in a multiscale manner. Moreover, a modified Frangi's filter (mFrangi) is developed in Cui et al [17], which multiplies the original Frangi's filter by the novel exponential term, for the purpose of tackling the problem of non-smoothness at the origin. Nevertheless, only local geometric features are explored by the Hessian matrix.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Three-Dimensional Tubular Structure Segmentation via Filter Combination

Cui

Chang

Jiang

2021

Int J Comput Intell Syst

Self Cite

View full text Add to dashboard Cite

Tubular structure enhancement plays an utmost role in medical image segmentation as a pre-processing technique. In this work, an unsupervised 3D tubular structure segmentation technique is developed, which is mainly inspired by the idea of filter combination. Three well-known vessel filters, Frangi’s filter, the modified Frangi’s filter and the Multiscale Fractional Anisotropic Tensor (MFAT) filter, separately enhance the original images. Next, the enhanced images obtained using three different filters are combined. Different categories of vessel filters have the ability of complementarity, which is the main motivation of combining these three advanced filters. The combination of them ensures a high diversity of the enhancing results. Weighted mean and median ranking methods are used to conduct the operation of filter combination. Based on the optimized weights for all the three individual filters, fuzzy C-means method is then applied to segment the tubular structures. The proposed technique is tested on the public DRIVE and STARE datasets, the public synthetic vascular models (2011 and 2013 VascuSynth Sample), and real-patient Coronary Computed Tomography Angiography (CCTA) datasets. Experimental results demonstrate that the proposed technique outperforms the state-of-the-art filter combination-based segmentation methods. Moreover, our proposed method is able to yield better tubular structure segmentation results than that of each individual filter, which exhibits the superiority of the proposed method. In conclusion, the proposed method can be further used to facilitate vessel segmentation in medical practice.

show abstract

Section: Retinal Imagesmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Three-Dimensional Tubular Structure Segmentation via Filter Combination

Cui

Chang

Jiang

2021

Int J Comput Intell Syst

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the V F defined in ( 9) cannot be used directly in (1) because of its non-smoothness at the origin. Therefore, an enhanced vesselness function V s is developed [26]:…”

Section: Methodologies a Vesselness Enhancement Diffusionmentioning

confidence: 99%

2D and 3D Vascular Structures Enhancement Via Improved Vesselness Filter and Vessel Enhancing Diffusion

2019

Self Cite

View full text Add to dashboard Cite

In medical imaging practice, vascular enhancement filtering has been widely performed before vessel segmentation and centerline detection, which provides important pathological information and holds great significance for vessel quantification. In the literature, numerous well known vesselness filtering approaches have been developed. For example, some techniques explore the Hessian matrix of the original images and construct the vessel filter based on the eigenvalues of the Hessian matrix. In this work we develop a hybrid technique for fast and accurate vascular enhancement filter, which contains two main steps: vesselness diffusion and improved vesselness filter based on the eigenvalues ratio. This novel approach is quantitatively and qualitatively tested on the public 2D retinal datasets and 3D synthetic vascular structure models. Experimental results demonstrate that the proposed filter outperforms other existing approaches for curvilinear structure enhancement from noisy images. Moreover, the novel approach is further evaluated on real patient Coronary Computed Tomography Angiography (CCTA) datasets with ground truth regions labelled by professional cardiologist. Our method is proven to produce more accurate coronary artery segmentation results. Given the accuracy and efficiency, the proposed vesselness filter can be further used in medical practice for vascular structures enhancement before vessel segmentation and quantification.INDEX TERMS Vascular structures detection, improved enhancement filter, Hessian matrix, vesselness diffusion, vessel segmentation.

show abstract

“…Another centerline extractor starting from segmented vessels was described in [15], in which the authors compute a 3D gradient vector flow field that is then used to compute a timetable of arrival times from one point to another. Combined with a branch tracing algorithm and a measure function for vesselness, the centerlines were extracted in about 16 min of processing time.…”

Section: Rule-based Centerline Extractionmentioning

confidence: 99%

Coronary Centerline Extraction from CCTA Using 3D-UNet

2021

View full text Add to dashboard Cite

The mesh-type coronary model, obtained from three-dimensional reconstruction using the sequence of images produced by computed tomography (CT), can be used to obtain useful diagnostic information, such as extracting the projection of the lumen (planar development along an artery). In this paper, we have focused on automated coronary centerline extraction from cardiac computed tomography angiography (CCTA) proposing a 3D version of U-Net architecture, trained with a novel loss function and with augmented patches. We have obtained promising results for accuracy (between 90–95%) and overlap (between 90–94%) with various network training configurations on the data from the Rotterdam Coronary Artery Centerline Extraction benchmark. We have also demonstrated the ability of the proposed network to learn despite the huge class imbalance and sparse annotation present in the training data.

show abstract

Automatic Coronary Centerline Extraction Using Gradient Vector Flow Field and Fast Marching Method From CT Images

Cited by 9 publications

References 26 publications

Unsupervised Three-Dimensional Tubular Structure Segmentation via Filter Combination

Unsupervised Three-Dimensional Tubular Structure Segmentation via Filter Combination

2D and 3D Vascular Structures Enhancement Via Improved Vesselness Filter and Vessel Enhancing Diffusion

Coronary Centerline Extraction from CCTA Using 3D-UNet

Contact Info

Product

Resources

About