Beyond Frangi: an improved multiscale vesselness filter

Jerman, Tim; Pernuš, Franjo; Likar, Boštjan; Špiclin, Žiga

doi:10.1117/12.2081147

Cited by 72 publications

(64 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…filter to enhance image contrasts. We have omitted such steps in our analysis on purpose, since these methods have several disadvantages including generation of image artifacts resembling vessel structures and different results for vessels that are not equally distributed in size [39,40]. Limitations include the relatively small number of subjects (therefore limited generalizability of the comparisons between different automated algorithms), having only one repeat measurement per eye and limited comparability of vessel density and skeleton density values because of different calculation approaches in the literature.…”

Section: Plos Onementioning

confidence: 99%

Automated thresholding algorithms outperform manual thresholding in macular optical coherence tomography angiography image analysis

et al. 2020

View full text Add to dashboard Cite

Data Availability Statement: The data proving the main findings of the study are contained within the manuscript. The Optical Coherence Tomography Angiography images of all participants cannot be made publicly available as public availability of the data might compromise participant privacy. All participants consented to scientific analysis of the data by the researchers involved but not to public data sharing (according to the consent form approved by the Ethics committee, University of Bonn). As subjects might be identifiable by the higher for the Mean algorithm compared to the manual approach with respect to the superficial retinal layer. Conclusions Automated thresholding algorithms yield a higher reproducibility of OCTA parameters and allow for a more sensitive diagnosis of macular pathology. However, different algorithms are not interchangeable nor results readily comparable. Especially the Mean algorithm should be investigated in further detail. Automated thresholding algorithms are preferable but more standardization is needed for clinical use.

show abstract

Section: Plos Onementioning

confidence: 99%

Automated thresholding algorithms outperform manual thresholding in macular optical coherence tomography angiography image analysis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Tube‐like structures can be enhanced by Hessian‐based methods, such as the Frangi filter and the Sato filter, where the eigenvalues of the Hessian matrix describe cylindrical properties. However, the response of Hessian‐based filters is low at vessels’ edges and bifurcations . The “strain energy" filter can partly overcome this problem of low responses at vessels’ bifurcations by analyzing the shape‐tuned strain energy density, where the Hessian matrix was considered as a stress tensor, and three tensor invariants from orthogonal tensor decomposition were used to formulate distinctive functions for shape discrimination, brightness contrast, and strength.…”

Section: Introductionmentioning

confidence: 99%

“…However, the response of Hessianbased filters is low at vessels' edges and bifurcations. 23 The "strain energy" filter 19 can partly overcome this problem of low responses at vessels' bifurcations by analyzing the shapetuned strain energy density, where the Hessian matrix was considered as a stress tensor, and three tensor invariants from orthogonal tensor decomposition were used to formulate distinctive functions for shape discrimination, brightness contrast, and strength. Finally, the multiscale scheme was adopted to optimally enhance vessels with different size.…”

Section: Introductionmentioning

confidence: 99%

Automatic quantitative analysis of pulmonary vascular morphology in CT images

et al. 2019

View full text Add to dashboard Cite

PurposeVascular remodeling is a significant pathological feature of various pulmonary diseases, which may be assessed by quantitative computed tomography (CT) imaging. The purpose of this study was therefore to develop and validate an automatic method for quantifying pulmonary vascular morphology in CT images.MethodsThe proposed method consists of pulmonary vessel extraction and quantification. For extracting pulmonary vessels, a graph‐cuts‐based method is proposed which considers appearance (CT intensity) and shape (vesselness from a Hessian‐based filter) features, and incorporates distance to the airways into the cost function to prevent false detection of airway walls. For quantifying the extracted pulmonary vessels, a radius histogram is generated by counting the occurrence of vessel radii, calculated from a distance transform‐based method. Subsequently, two biomarkers, slope α and intercept β, are calculated by linear regression on the radius histogram. A public data set from the VESSEL12 challenge was used to independently evaluate the vessel extraction. The quantitative analysis method was validated using images of a three‐dimensional (3D) printed vessel phantom, scanned by a clinical CT scanner and a micro‐CT scanner (to obtain a gold standard). To confirm the association between imaging biomarkers and pulmonary function, 77 scleroderma patients were investigated with the proposed method.ResultsIn the independent evaluation with the public data set, our vessel segmentation method obtained an area under the receiver operating characteristic (ROC) curve of 0.976. The median radius difference between clinical and micro‐CT scans of a 3D printed vessel phantom was 0.062 ± 0.020 mm, with interquartile range of 0.199 ± 0.050 mm. In the studied patient group, a significant correlation between diffusion capacity for carbon monoxide and the biomarkers, α (R = −0.27, P = 0.018) and β (R = 0.321, P = 0.004), was obtained.ConclusionIn conclusion, the proposed method was validated independently using a public data set resulting in an area under the ROC curve of 0.976 and using a 3D printed vessel phantom data set, showing a vessel sizing error of 0.062 mm (0.16 in‐plane pixel units). The correlation between imaging biomarkers and diffusion capacity in a clinical data set confirmed an association between lung structure and function. This quantification of pulmonary vascular morphology may be helpful in understanding the pathophysiology of pulmonary vascular diseases.

show abstract

“…Cardiovascular diseases (CVDs) are one of the leading causes of disability and death in the developed countries [1]. An effective and timely detailed analysis is necessary to cure these life threatening diseases.…”

Section: Introductionmentioning

confidence: 99%

Automatic and Effective Delineation of Coronary Arteries from CTA Data Using Two-Way Active Contour Model

Zai

Ansari

Moon

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYPrecise estimation of coronary arteries from computed tomography angiography (CTA) data is one of the challenging problems. This study focuses on automatic delineation of coronary arteries from 3D CTA data that may assess the clinicians in identifying the coronary pathologies. In this work, we present a technique that effectively segments the complete coronary arterial tree under the guidance of initial vesselness response without relying on heavily manual operations. The proposed method isolates the coronary arteries with accuracy by using localized statistical energy model in two directions provided with an automated seed which ensures an optimal segmentation of the coronaries. The detection of seed is carried out by analyzing the shape information of the coronary arteries in three successive cross-sections. To demonstrate the efficiency of the proposed algorithm, the obtained results are compared with the reference data provided by Rotterdam framework for lumen segmentation and the level-set active contour based method proposed by Lankton et al. Results reveal that the proposed method performs better in terms of leakages and accuracy in completeness of the coronary arterial tree.

show abstract

Beyond Frangi: an improved multiscale vesselness filter

Cited by 72 publications

References 15 publications

Automated thresholding algorithms outperform manual thresholding in macular optical coherence tomography angiography image analysis

Automated thresholding algorithms outperform manual thresholding in macular optical coherence tomography angiography image analysis

Automatic quantitative analysis of pulmonary vascular morphology in CT images

Automatic and Effective Delineation of Coronary Arteries from CTA Data Using Two-Way Active Contour Model

Contact Info

Product

Resources

About