Level Set Evolution without Re-Initialization: A New Variational Formulation

Li, Chunming; Xu, Chenyang; Gui, Changfeng; Fox, M.D.

doi:10.1109/cvpr.2005.213

Cited by 609 publications

(139 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We utilize the level set introduced by Chunming et al [19], to segment the target organ in the chosen axial slice. This approach is more efficient than the traditional level-set methods [20] since it does not require re-initialization of the level set function at every iteration.…”

Section: A Initializationmentioning

confidence: 99%

“…The first data set consists the liver organ, with slice thickness of 2 mm set consists of 28 slices for the liver o thickness of 5 mm, whereas the third data slices for the spleen organ, with slice thic Since we are re-using an existing levelcontour approach [19], of course th segmentation is limited by the choice of the set approach.…”

Section: Experimental Resulmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Initialization of Contour for Level Set Algorithms Guided by Integration of Multiple Views to Segment Abdominal CT Scans

Jawarneh

Rajeswari

Ramachandram

et al. 2010

2010 Second International Conference on Computational Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

Abstract-This paper presents a new automatic initialization procedure for a level-set based segmentation algorithm that works on all slices for a given CT dataset. Level set segmentation algorithms provide promising results, are robust to dataset variations and do not require prior training. As such, they can be reliably used for segmentation of major organs in abdominal CT scans. However, level set algorithms still require user intervention to plot the initial contour for each slice in a given dataset, which is a time consuming process. Therefore, we propose here, a technique of using multiple views to automatically initialize and propagate the contour through each slice in the CT dataset. The technique requires a user to only initialize a single point within the organ of interest in order to initiate the automated segmentation process. We report the segmentation results for liver and spleen organs within the abdominal region using three different datasets. We conclude that this technique can be used to reduce the processing time for any level set algorithm suitable to abdominal CT scans. We typically achieve time efficiency up to 203.03% for complete segmentation of three organs as compared to manually initializing the level set contour for each slice.

show abstract

Section: A Initializationmentioning

confidence: 99%

Section: Experimental Resulmentioning

confidence: 99%

Automatic Initialization of Contour for Level Set Algorithms Guided by Integration of Multiple Views to Segment Abdominal CT Scans

Jawarneh

Rajeswari

Ramachandram

et al. 2010

2010 Second International Conference on Computational Intelligence, Modelling and Simulation

View full text Add to dashboard Cite

show abstract

“…On the contrary, according to Gomes and Faugeras [8], an accurate approximation of derivatives of φ by finite differences is only guaranteed, if φ is not too steep. Also Chan and Vese [5] as well as Li et al [11] state that it is necessary to prevent φ from getting too steep or flat. As a consequence we want to make some effort to explain why φ cannot get too steep or flat in the case of diffusion regularisation.…”

Section: Practical Considerationsmentioning

confidence: 99%

“…Similar to [11] we focus on explicit regularisation strategies. However, we focus on regularisers of the form…”

Section: Regularisation Strategies Based On Diffusionmentioning

confidence: 99%

Diffusion-based Regularisation Strategies for Variational Level Set Segmentation

Baust

Zikic

Navab

2010

Procedings of the British Machine Vision Conference 2010

View full text Add to dashboard Cite

Variational level set methods are formulated as energy minimisation problems, which are often solved by gradient-based optimisation methods, such as gradient descent. Unfortunately, the gradient obtained by applying the calculus of variations is not suitable, because it is only an element of the function space L 2 making it prone to lead into wrong local minima. Consequently, some regularisation strategy -be it the restriction to signed distance functions or the choice of smooth function spaces -is necessary. In this paper we propose diffusion-based regularisation strategies and compare them to the recently proposed ones of Charpiat et al. and Sundaramoorthi et al. From this comparison we derive two general regularisation paradigms at the level of update equations and show that the diffusion-based paradigm enjoys both theoretical and practical advantages, such as an improved convergence rate, while being of the same computational complexity as the other paradigm.

show abstract

“…The existing tracking methods can be broadly divided into two categories, namely the front capturing and the front tracking. Specifically, the front capturing methods include the continuous transport method, VOF method [5][6], level-set method [7][8], and phase field method. Meanwhile, the front tracking methods include the moving grid method, MAC method, wave height function method, and particle method.…”

Section: Introductionmentioning

confidence: 99%

Study on Sloshing of Liquid Tank in Large LNG-FSRU Based on CLSVOF Method

Wang¹,

Qin²,

Ge³

et al. 2016

IJHT

View full text Add to dashboard Cite

In the light of the advantages and disadvantages of the level-set method and VOF method, a new coupling method of the liquid interface tracing named CLSVOF (Coupled Level-Set and Volume-of-Fluid method) has been proposed in recent years. By means of this method, this paper realizes the conservation of physical quantities in the calculation process compared with the level-set method, and overcomes the difficulty of accurately calculating the interface normal and curvature in comparison with the VOF method. Specifically, the above method is utilized in this paper to numerically simulate the sloshing of a liquid tank and its results are compared with the experimental results. It is found that the results agree with each other, which verifies the validity and accuracy of the CLSVOF method. Afterwards, this paper takes the liquid cargo tank of a large LNG-FSRU (Liquefied Natural Gas-Floating Storage Regasification Unit) as its research object to conduct a threedimensional numerical simulation of rolling motion and study the influence of the excitation centre on the sloshing of the liquid tank. It turns out that the position of the excitation centre affects the movement of the free surface and the pressure distribution of the tank. Meanwhile, research on the position of the excitation centre provides the theoretical foundation for designing the marine structure of the octagonal tank.

show abstract

Level Set Evolution without Re-Initialization: A New Variational Formulation

Abstract: Abstract

Cited by 609 publications

References 20 publications

Automatic Initialization of Contour for Level Set Algorithms Guided by Integration of Multiple Views to Segment Abdominal CT Scans

Automatic Initialization of Contour for Level Set Algorithms Guided by Integration of Multiple Views to Segment Abdominal CT Scans

Diffusion-based Regularisation Strategies for Variational Level Set Segmentation

Study on Sloshing of Liquid Tank in Large LNG-FSRU Based on CLSVOF Method

Contact Info

Product

Resources

About