Cell-competition algorithm: A new segmentation algorithm for multiple objects with irregular boundaries in ultrasound images
Ultrasound in Medicine & BiologyPublished 1 December 2005
Chung‐Ming Chen, Chung‐Ming Chen, Yi‐Hong Chou, Curtis S.K. Chen, Curtis S.K. Chen, Jie-Zhi Cheng
Citations46
SJR quartileQ1
SJR score0.66
SNIP0.96
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The proposed algorithm is shown to be superior to the region-competition algorithm for both types of images and robust to the variation of regions-of-interest and a range of thresholds required for the second-pass watershed transformation.
Abstract
Segmentation of multiple objects with irregular contours and surrounding sporadic spots is a common practice in ultrasound image analysis. A new region-based approach, called cell-competition algorithm, is proposed for simultaneous segmentation of multiple objects in a sonogram. The algorithm is composed of two essential ideas. One is simultaneous cell-based deformation of regions and the other is cell competition. The cells are generated by two-pass watershed transformations. The cell-competition algorithm has been validated with 13 synthetic images of different contrast-to-noise ratios and 71 breast sonograms. Three assessments have been carried out and the results show that the boundaries derived by the cell-competition algorithm are reasonably comparable to those delineated manually. Moreover, the cell-competition algorithm is robust to the variation of regions-of-interest and a range of thresholds required for the second-pass watershed transformation. The proposed algorithm is also shown to be superior to the region-competition algorithm for both types of images.
Keywords
Computer ScienceMedicine
IEEE Transactions on Pattern Analysis and Machine IntelligenceWatersheds in digital spaces: an efficient algorithm based on immersion simulations
5,468 Citations1991Luc Vincent, Pierre Soille
A fast and flexible algorithm for computing watersheds in digital gray-scale images is introduced, based on an immersion process analogy, which is reported to be faster than any other watershed algorithm.
TechnometricsApplied Nonparametric Statistics
5,029 Citations1991Patricia J. Wozniak, Wayne W. Daniel
IEEE Transactions on Pattern Analysis and Machine IntelligenceRegion competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation
1,907 Citations1996Song Chun Zhu, Alan Yuille
A novel statistical and variational approach to image segmentation based on a new algorithm, named region competition, derived by minimizing a generalized Bayes/minimum description length (MDL) criterion using the variational principle is presented.
IEEE Transactions on Medical ImagingA multiple active contour model for cardiac boundary detection on echocardiographic sequences
305 Citations1996Vikram Chalana, David T. Linker +2 more
The authors have developed an effective and robust algorithm to extract left-ventricular boundaries from echocardiographic sequences that is fairly insensitive to the choice of the initial curve.
Journal of Visual Communication and Image RepresentationA Fully Global Approach to Image Segmentation via Coupled Curve Evolution Equations
303 Citations2002Anthony Yezzi, Andy Tsai +1 more
A novel region-based approach to snakes designed to optimally separate the values of certain image statistics over a known number of region types is developed, endowing the algorithm with a robustness to initial contour placement above and beyond the significant improvement exhibited by other region based snakes over earlier edge based snakes.
IEEE Transactions on Medical ImagingAutomatic segmentation of echocardiographic sequences by active appearance motion models
295 Citations2002Johan G. Bosch, Susan Mitchell +5 more
A novel extension of active appearance models (AAMs) for automated border detection in echocardiographic image sequences is reported and the AAMM was significantly more accurate than an equivalent set of two-dimensional AAMs.
IEEE Transactions on Image ProcessingImage segmentation and analysis via multiscale gradient watershed hierarchies
282 Citations1999John M. Gauch
The multiscale behavior of gradient watershed regions is investigated, a mechanism for imposing a scale-based hierarchy on the watersheds associated with these minima that can be used to label watershed boundaries according to their scale.
IEEE Transactions on Medical ImagingSegmentation of prostate boundaries from ultrasound images using statistical shape model
261 Citations2003Dinggang Shen, Yiqiang Zhan +1 more
A hierarchical deformation strategy is employed, in which the model adaptively focuses on the similarity of different Gabor features at different deformation stages using a multiresolution technique, i.e., coarse features first and fine features later.
RadiologyBreast Lesions on Sonograms: Computer-aided Diagnosis with Nearly Setting-Independent Features and Artificial Neural Networks
258 Citations2003Chung‐Ming Chen, Yi‐Hong Chou +5 more
The proposed CAD algorithm could effectively and reliably differentiate benign and malignant lesions and was shown to be extendible from one set of US images to the other set and robust for both small and large sample sizes.
IEEE Transactions on Medical ImagingSegmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates
243 Citations1998Ivana Medvedec Mikić, S. Krucinski +1 more
A technique that incorporates the information on pixel velocities (optical flow) into the estimate of initial contour to enable tracking of fast-moving objects to enable segmentation and tracking of cardiac structures in ultrasound image sequences is presented.
Medical PhysicsComputerized lesion detection on breast ultrasound
236 Citations2002Karen Drukker, Maryellen L. Giger +4 more
Round robin analysis was used to assess the quality of the classification of lesion candidates into actual lesions and false-positives by a Bayesian neural network, and use of computerized analysis of breast sonograms may ultimately facilitate the use of sonography in breast cancer screening programs.
Breast Cancer Research and TreatmentAutomatic ultrasound segmentation and morphology based diagnosis of solid breast tumors
193 Citations2005Ruey‐Feng Chang, Wen-Jie Wu +2 more
The tumors are segmented using the newly developed level set method at first and then six morphologic features are used to distinguish the benign and malignant cases and six morphologic features are used to distinguish the benign and malignant cases.
IEEE Transactions on Medical ImagingEdge-guided boundary delineation in prostate ultrasound images
169 Citations2000Dev S. Pathak, David R. Haynor +1 more
It is found that consistency in prostate delineation increases when automatically detected edges are used as visual guide during outlining, while the accuracy of the detected edges was found to be at least as good as those of the human observers.
IEEE Transactions on Medical ImagingLeft ventricular volume estimation for real-time three-dimensional echocardiography
115 Citations2002Cristiana Corsi, Giuseppe Saracino +2 more
This method allows semiautomatic segmentation of heart chambers, which regularizes the shapes and improves edge fidelity, especially in the presence of gaps, as is common in ultrasound data.
Ultrasound in Medicine & BiologyStepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis
104 Citations2001Yi‐Hong Chou, Chui-Mei Tiu +4 more
The CAD system using SLR can differentiate solid breast nodules with relatively high accuracy and its high negative predictive value could potentially help inexperienced operators to avoid misdiagnoses and it could be optimized if a larger set of tumor images were supplied.
Ultrasound in Medicine & Biology3-D breast ultrasound segmentation using active contour model
100 Citations2003Dar‐Ren Chen, Ruey‐Feng Chang +3 more
This study made use of the discrete active contour model to overcome the natural properties of ultrasound (US) images, speckle, noise and tissue-related textures, to segment the breast tumors precisely and proposes an automatic initial contour-finding method.
Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis
97 Citations2002Huihua Kenny Chiang, Chui‐Mei Tiu +4 more
To assist the ultrasound diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, a SLR model withcontour features was used to classify tumors as benign or malignant.
IEEE Transactions on Medical ImagingOvarian ultrasound image analysis: follicle segmentation
95 Citations1998Anthony Krivanek, Milan Sonka
An automated method for follicle wall segmentation is reported that uses a four-step process based on watershed segmentation and a knowledge-based graph search algorithm which utilizes a priori information about follicle structure for inner and outer wall detection.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAdaptive split-and-merge segmentation based on piecewise least-square approximation
87 Citations1993Xiaolin Wu
The author proposes efficient algorithms and data structures to optimize the split-and-merge processes by piecewise least-square approximation of image intensity functions, which aims at the unification of segment finding and edge detection.
Pattern Recognition LettersSegmentation of ultrasonic images using Support Vector Machines
58 Citations2003Constantine Kotropoulos, Ioannis Pitas
It is demonstrated that trained SVMs with a radial basis function kernel segment satisfactorily (unseen) ultrasound B-mode images as well as clinical ultrasonic images.
Pattern Recognition LettersSegmentation of ultrasound images by using a hybrid neural network
53 Citations2002Zümray Dokur, Tamer Ölmez
A hybrid neural network is presented for the segmentation of ultrasound images and first-layer-nodes of the proposed hybrid network represent hyperspheres (HSs) in the feature space to represent the distribution of classes.
Ultrasound in Medicine & BiologyA two-dimensional extension of minimum cross entropy thresholding for the segmentation of ultrasound images
52 Citations1996Y. Zimmer, R. Tepper +1 more
A multivariate extension of MCE is presented in which the segmented variable (gray level) is replaced by a weighted combination of several image parameters, which uses a linear combination of the gray level and the local entropy.
IEEE Transactions on Medical Imaging3-D freehand echocardiography for automatic left ventricle reconstruction and analysis based on multiple acoustic windows
43 Citations2002Xujiong Ye, J. Alison Noble +1 more
A new method to reconstruct and analyze the left ventricle from multiple acoustic window three-dimensional ultrasound acquired using a transthoracic 3-D rotational probe is proposed and shows that the new method agrees better with MRI measurements than the previous approach developed based on a single acoustic window.
Ultrasonic ImagingImproved Detectability with Blocked Element Compensation
34 Citations1994Pai-chi Li, M. O’Donnell
IEEE Transactions on Medical ImagingROPES: a semiautomated segmentation method for accelerated analysis of three-dimensional echocardiographic data
31 Citations2002Ivo Wolf, Mark Hastenteufel +6 more
A semiautomated segmentation algorithm (ROPES) that is able to greatly reduce the time necessary for user interaction and its application to extract various parameters from 4-D echocardiographic data.
Ultrasound in Medicine & BiologyCell-based dual snake model: a new approach to extracting highly winding boundaries in the ultrasound images
27 Citations2002Chung‐Ming Chen, Henry Horng‐Shing Lu +1 more
A new deformable model (namely, the cell-based dual snake model) is proposed, which provides an effective mechanism allowing a distant initial contour and makes it possible to catch the winding characteristics of the desired boundary.
Ultrasonic ImagingImproved Detectability with Blocked Element Compensation
22 Citations1994P Li
Results show that low contrast detectability is determined by sidelobe energy in the point spread function if the total aperture size is not reduced, and contrast resolution can be restored using the object dependent method if the number of blocked elements is not very significant.
The XUltra project-automated analysis of ovarian ultrasound images
17 Citations2003Božidar Potočnik, Boris Cigale +1 more
Three different automatic computer-based follicle identification algorithms are proposed, one based on cellular neural networks, another based on region growing segmentation method, and a third one that processes entire image sequence with a predictor-corrector recognition scheme.
Computerized Medical Imaging and GraphicsB-spline methods for interactive segmentation and modeling of lumen and vessel surfaces in three-dimensional intravascular ultrasound
16 Citations2002Jon D. Klingensmith, D. Geoffrey Vince
B-spline-based surface fitting and manipulation methods are presented that can be integrated easily with previously developed segmentation algorithms to provide a semi-automated segmentation system for identification of luminal and vessel borders in volumetric IVUS images.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE3D segmentation of breast tumor in ultrasound images
7 Citations2003Jong In Kwak, Mal Nam Jung +2 more
A three-dimensional (3D) region-based segmentation algorithm for extracting a diagnostic tumor from ultrasound images by using a split-and-merge and seeded region growing with a distortion-based homogeneity cost yields maximum three times reduction in error rate over the Krivanek’s method.
CancerNerve-sparing radical retropubic prostatectomy for localized prostate cancer. The pros and cons
6 Citations1995Philippe E. Zimmern, Gary E. Leach
A detailed review of the literature focuses on the potency results attained by this operation, reviews the shortcomings of this approach in terms of cancer eradication and continence, and attempts to define the optimal candidate for such a procedure.
EURASIP Journal on Advances in Signal ProcessingRegion Information-Based ROI Extraction by Multi-Initial Fast Marching Algorithm
2 Citations2004Zhang Hongmei, Bian Zhengzhong +3 more
Experiments show that the proposed approach to ROI extraction based on the curve evolution could fast extract low-contrast and narrow thin ROI precisely.