Limits...
An active contour model for the segmentation of images with intensity inhomogeneities and bias field estimation.

Huang C, Zeng L - PLoS ONE (2015)

Bottom Line: The proposed model first appeared as a two-phase model and then extended to a multi-phase one.The experimental results demonstrate the advantages of our model in terms of accuracy and insensitivity to the location of the initial contours.In particular, our method has been applied to various synthetic and real images with desirable results.

View Article: PubMed Central - PubMed

Affiliation: Key Laboratory of Optoelectronic Technology and System of the Education Ministry of China, Chongqing University, Chongqing, 400044, China; Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry of China, Chongqing University, Chongqing, 400044, China.

ABSTRACT
Intensity inhomogeneity causes many difficulties in image segmentation and the understanding of magnetic resonance (MR) images. Bias correction is an important method for addressing the intensity inhomogeneity of MR images before quantitative analysis. In this paper, a modified model is developed for segmenting images with intensity inhomogeneity and estimating the bias field simultaneously. In the modified model, a clustering criterion energy function is defined by considering the difference between the measured image and estimated image in local region. By using this difference in local region, the modified method can obtain accurate segmentation results and an accurate estimation of the bias field. The energy function is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. The proposed model first appeared as a two-phase model and then extended to a multi-phase one. The experimental results demonstrate the advantages of our model in terms of accuracy and insensitivity to the location of the initial contours. In particular, our method has been applied to various synthetic and real images with desirable results.

No MeSH data available.


Related in: MedlinePlus

Comparisons of the segmentation results for a MR brain image contains tumor with intensity inhomogeneity between Li’s model and our model.(a), (d) The original image with initial contours. (b), (e) The results of Li’s model. (c), (f) The results of our model.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4383562&req=5

pone.0120399.g008: Comparisons of the segmentation results for a MR brain image contains tumor with intensity inhomogeneity between Li’s model and our model.(a), (d) The original image with initial contours. (b), (e) The results of Li’s model. (c), (f) The results of our model.

Mentions: The quality of MR images is highly dependent upon the coil used to receive the RF signal emitted from the patient [43]. Fig. 8 shows the comparison between Li’s method and our method for the segmentation results with different initial contours of an MR brain image (the size is 109×119) with a tumor from the Internet. A small black spot is located at the center of the tumor. The first row shows the segmentation results with the initial contour of Fig. 8(a), and the second row shows the results with the initial contour of Fig. 8(d). Columns 1 to 3 are the original image with red initial contours, the segmentation results of Li’s method and the results of our method, respectively. Li’s method fails to acquire the tumor and spot boundaries with the initial contour shown in Fig. 8(a). The tumor boundaries obtained by Li’s model are inaccurate when the initial contour lies inside the tumor (Fig. 8(d)). Our method can obtain the boundaries of the tumor and small spot accurately because it collects the local regional difference in the entire image domain.


An active contour model for the segmentation of images with intensity inhomogeneities and bias field estimation.

Huang C, Zeng L - PLoS ONE (2015)

Comparisons of the segmentation results for a MR brain image contains tumor with intensity inhomogeneity between Li’s model and our model.(a), (d) The original image with initial contours. (b), (e) The results of Li’s model. (c), (f) The results of our model.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4383562&req=5

pone.0120399.g008: Comparisons of the segmentation results for a MR brain image contains tumor with intensity inhomogeneity between Li’s model and our model.(a), (d) The original image with initial contours. (b), (e) The results of Li’s model. (c), (f) The results of our model.
Mentions: The quality of MR images is highly dependent upon the coil used to receive the RF signal emitted from the patient [43]. Fig. 8 shows the comparison between Li’s method and our method for the segmentation results with different initial contours of an MR brain image (the size is 109×119) with a tumor from the Internet. A small black spot is located at the center of the tumor. The first row shows the segmentation results with the initial contour of Fig. 8(a), and the second row shows the results with the initial contour of Fig. 8(d). Columns 1 to 3 are the original image with red initial contours, the segmentation results of Li’s method and the results of our method, respectively. Li’s method fails to acquire the tumor and spot boundaries with the initial contour shown in Fig. 8(a). The tumor boundaries obtained by Li’s model are inaccurate when the initial contour lies inside the tumor (Fig. 8(d)). Our method can obtain the boundaries of the tumor and small spot accurately because it collects the local regional difference in the entire image domain.

Bottom Line: The proposed model first appeared as a two-phase model and then extended to a multi-phase one.The experimental results demonstrate the advantages of our model in terms of accuracy and insensitivity to the location of the initial contours.In particular, our method has been applied to various synthetic and real images with desirable results.

View Article: PubMed Central - PubMed

Affiliation: Key Laboratory of Optoelectronic Technology and System of the Education Ministry of China, Chongqing University, Chongqing, 400044, China; Engineering Research Center of Industrial Computed Tomography Nondestructive Testing of the Education Ministry of China, Chongqing University, Chongqing, 400044, China.

ABSTRACT
Intensity inhomogeneity causes many difficulties in image segmentation and the understanding of magnetic resonance (MR) images. Bias correction is an important method for addressing the intensity inhomogeneity of MR images before quantitative analysis. In this paper, a modified model is developed for segmenting images with intensity inhomogeneity and estimating the bias field simultaneously. In the modified model, a clustering criterion energy function is defined by considering the difference between the measured image and estimated image in local region. By using this difference in local region, the modified method can obtain accurate segmentation results and an accurate estimation of the bias field. The energy function is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. The proposed model first appeared as a two-phase model and then extended to a multi-phase one. The experimental results demonstrate the advantages of our model in terms of accuracy and insensitivity to the location of the initial contours. In particular, our method has been applied to various synthetic and real images with desirable results.

No MeSH data available.


Related in: MedlinePlus