A region and gradient based active contour model and its application in boundary tracking on anal canal ultrasound images

Xiao, Di; Ng, Wan Sing; Tsang, Charles B.; Abeyratne, Udantha R.

doi:10.1016/j.patcog.2007.03.024

Cited by 12 publications

(4 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the edge-based active contour model [34], the boundary detection terms can be constructed as follows: Figure 8 is an effect diagram of the boundary detection function based on Bayesian probability difference. Figure 8a is a CT image of a patient, the region drawn in the box is where the pulmonary nodule is located at, and the pulmonary nodule has a blurred boundary.…”

Section: Construction Of the Boundary Detection Term Based On Bayesiamentioning

confidence: 99%

Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference

et al. 2020

View full text Add to dashboard Cite

Background: Image segmentation is an important part of computer-aided diagnosis (CAD), the segmentation of small ground glass opacity (GGO) pulmonary nodules is beneficial for the early detection of lung cancer. For the segmentation of small GGO pulmonary nodules, an integrated active contour model based on Markov random field energy and Bayesian probability difference (IACM_MRFEBPD) is proposed in this paper. Methods: First, the Markov random field (MRF) is constructed on the computed tomography (CT) images, then the MRF energy is calculated. The MRF energy is used to construct the region term. It can not only enhance the contrast between pulmonary nodule and the background region, but also solve the problem of intensity inhomogeneity using local spatial correlation information between neighboring pixels in the image. Second, the Gaussian mixture model is used to establish the probability model of the image, and the model parameters are estimated by the expectation maximization (EM) algorithm. So the Bayesian posterior probability difference of each pixel can be calculated. The probability difference is used to construct the boundary detection term, which is 0 at the boundary. Therefore, the blurred boundary problem can be solved. Finally, under the framework of the level set, the integrated active contour model is constructed. Results: To verify the effectiveness of the proposed method, the public data of the lung image database consortium and image database resource initiative (LIDC-IDRI) and the clinical data of the Affiliated Jiangmen Hospital of Sun Yat-sen University are used to perform experiments, and the intersection over union (IOU) score is used to evaluate the segmentation methods. Compared with other methods, the proposed method achieves the best results with the highest average IOU of 0.7444, 0.7503, and 0.7450 for LIDC-IDRI test set, clinical test set, and all test sets, respectively. Conclusions: The experiment results show that the proposed method can segment various small GGO pulmonary nodules more accurately and robustly, which is helpful for the accurate evaluation of medical imaging.

show abstract

Section: Construction Of the Boundary Detection Term Based On Bayesiamentioning

confidence: 99%

Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference

et al. 2020

View full text Add to dashboard Cite

show abstract

“…An advantage of the ACM for image segmentation is that it partitions an image into sub-regions with closed and smooth boundaries. These ACM can be categorized into three major classes [5]: the edge-based ACM [6][7][8], the region-based ACM [9][10][11][12] and the integrated ACM [13][14][15]. The edge-based ACM utilize image gradients to identify object boundaries.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Speed Function Based Active Contour Model for Segmentation of Pulmonary Nodules

Chen

et al. 2014

Bio-Medical Materials and Engineering

View full text Add to dashboard Cite

Pulmonary nodules are potential manifestation of lung cancer. Accurate segmentation of juxta-vascular nodules and ground glass opacity (GGO) nodules is an important and active area of research in medical image processing. At present, the classical active contour models (ACM) for segmentation of pulmonary nodules may cause the problem of boundary leakage. In order to solve the problem, a new fuzzy speed function-based active model for segmentation of pulmonary nodules is proposed in this paper. The fuzzy speed function incorporated into the ACM is calculated by the degree of membership based on intensity feature and local shape index. At the boundary of pulmonary nodules, the fuzzy speed function approaches zero and the evolution of the contour curve will stop, so the accurate segmentation of pulmonary nodules can be obtained. Experimental results on juxta-vascular nodules and GGO nodules show that the proposed ACM can achieve accurate segmentation.

show abstract

“…Contour extraction is a fundamental task in digital image processing and has important applications in medical image analysis, 8,19,20 pattern recognition, 7,13 and reverse engineering. 18 Contours are the boundary curves of geometrical shapes of digital images, which can be expressed as discrete or parametric curves.…”

Section: Introductionmentioning

confidence: 99%

An Iterative Convex Hull Approach for Image Segmentation and Contour Extraction

Zhao¹,

2012

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

The contours and segments of objects in digital images have many important applications. Contour extractions of gray images can be converted into contour extractions of binary images. This paper presents a novel contour-extraction algorithm for binary images and provides a deduction theory for this algorithm. First, we discuss the method used to construct convex hulls of regions of objects. The contour of an object evolves from a convex polygon until the exact boundary is obtained. Second, the projection methods from lines to objects are studied, in which, a polygon iteration method is presented using linear projection. The result of the iteration is the contour of the object region. Lastly, addressing the problem that direct projections probably cannot¯nd correct projection points, an e®ective discrete ray-projection method is presented. Comparisons with other contour deformation algorithms show that the algorithm in the present paper is very robust with respect to the shapes of the object regions. Numerical tests show that time consumption is primarily concentrated on convex hull computation, and the implementation e±ciency of the program can satisfy the requirement of interactive operations.

show abstract

A region and gradient based active contour model and its application in boundary tracking on anal canal ultrasound images

Cited by 12 publications

References 58 publications

Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference

Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference

Fuzzy Speed Function Based Active Contour Model for Segmentation of Pulmonary Nodules

An Iterative Convex Hull Approach for Image Segmentation and Contour Extraction

Contact Info

Product

Resources

About