Automatic Liver Segmentation of Contrast Enhanced CT Images Based on Histogram Processing

Seo, Kyung-Sik; Kim, Hyung-Bum; Park, Taesu; Kim, Pankoo; Park, Jong-An

doi:10.1007/11539087_135

Cited by 23 publications

(16 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AER was used as an established tool for validating the segmentation accuracy. Our results are in accordance with the studies of Ciecholewski [10], who tested the ACM on ultrasound images to extract the shape of the gallbladder, and studies carried out by Seo et al [31] on the automatic segmentation of the liver using computed tomography images. In both papers, the AER is used as an evaluation criterion of the performances.…”

Section: Discussionsupporting

confidence: 92%

Comparative study on the performance of textural image features for active contour segmentation

Moraru

Moldovanu

2012

Sci. China Life Sci.

View full text Add to dashboard Cite

We present a computerized method for the semi-automatic detection of contours in ultrasound images. The novelty of our study is the introduction of a fast and efficient image function relating to parametric active contour models. This new function is a combination of the gray-level information and first-order statistical features, called standard deviation parameters. In a comprehensive study, the developed algorithm and the efficiency of segmentation were first tested for synthetic images. Tests were also performed on breast and liver ultrasound images. The proposed method was compared with the watershed approach to show its efficiency. The performance of the segmentation was estimated using the area error rate. Using the standard deviation textural feature and a 5×5 kernel, our curve evolution was able to produce results close to the minimal area error rate (namely 8.88% for breast images and 10.82% for liver images). The image resolution was evaluated using the contrast-to-gradient method. The experiments showed promising segmentation results.

show abstract

Section: Discussionsupporting

confidence: 92%

Comparative study on the performance of textural image features for active contour segmentation

Moraru

Moldovanu

2012

Sci. China Life Sci.

View full text Add to dashboard Cite

show abstract

“…Although many works have been produced since the nineties, especially in CT, the variance in liver size and shape between the patients and the proximity with other organs of similar intensity make automatic liver segmentation especially difficult( [6], [7]). We have to add to this situation the inherent problems to magnetic resonance images, such as the lack of homogeneity in the radiated magnetic field and the artefacts of the coils.…”

Section: Motwationmentioning

confidence: 99%

Liver segmentation for hepatic lesions detection and characterisation

Platero

Poncela

González

et al. 2008

2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

The detection and characterisation of hepatic lesions is fundamental in clinical practice, from the diagnosis stages to the evolution of the therapeutic response. Hepatic magnetic resonance is a usual practice in the localization and quantification of lesions. Automatic segmentation of the liver is illustrated in Ti weighted images. This task is necessary for detecting the lesions. The proposed liver segmentation is based on 3D anisotropic diffusion processing without any control parameter. Combinations of edge detection techniques, histogram analysis, morphological post-processing and evolution of an active contour have been applied to the liver segmentation. The active contour evolution is based on the minimization of variances in luminance between the liver and its closest neighbourhood.

show abstract

“…More specifically, liver segmentation in 3D CT image can be grouped as prior-model-based approaches 3,4,[12][13][14][15] and image-data-driven approaches. [5][6][7][16][17][18][19] The first group, modelbased segmentation, is a global approach that matches a prior model into the target image. Popular methods for construction of prior models are statistical shape model (SSM) 3,14,20,21 and (probabilistic) atlas.…”

Section: Introductionmentioning

confidence: 99%

“…Commonly used methods include thresholding, 18 region growing, 19 deformable model-based approaches/variational energy minimization, 5,8 fast marching, 17 graph cuts, 7,9 and so on. Leakage on weak edges is one of the biggest challenges for methods in this class.…”

Section: Introductionmentioning

confidence: 99%

3D liver segmentation using multiple region appearances and graph cuts

Peng

et al. 2015

Medical Physics

View full text Add to dashboard Cite

Purpose: Efficient and accurate 3D liver segmentations from contrast-enhanced computed tomography (CT) images play an important role in therapeutic strategies for hepatic diseases. However, inhomogeneous appearances, ambiguous boundaries, and large variance in shape often make it a challenging task. The existence of liver abnormalities poses further difficulty. Despite the significant intensity difference, liver tumors should be segmented as part of the liver. This study aims to address these challenges, especially when the target livers contain subregions with distinct appearances. Methods: The authors propose a novel multiregion-appearance based approach with graph cuts to delineate the liver surface. For livers with multiple subregions, a geodesic distance based appearance selection scheme is introduced to utilize proper appearance constraint for each subregion. A special case of the proposed method, which uses only one appearance constraint to segment the liver, is also presented. The segmentation process is modeled with energy functions incorporating both boundary and region information. Rather than a simple fixed combination, an adaptive balancing weight is introduced and learned from training sets. The proposed method only calls initialization inside the liver surface. No additional constraints from user interaction are utilized. Results: The proposed method was validated on 50 3D CT images from three datasets, i.e., Medical Image Computing and Computer Assisted Intervention (MICCAI) training and testing set, and local dataset. On MICCAI testing set, the proposed method achieved a total score of 83.4 ± 3.1, outperforming nonexpert manual segmentation (average score of 75.0). When applying their method to MICCAI training set and local dataset, it yielded a mean Dice similarity coefficient (DSC) of 97.7% ± 0.5% and 97.5% ± 0.4%, respectively. These results demonstrated the accuracy of the method when applied to different computed tomography (CT) datasets. In addition, user operator variability experiments showed its good reproducibility. Conclusions: A multiregion-appearance based method is proposed and evaluated to segment liver. This approach does not require prior model construction and so eliminates the burdens associated with model construction and matching. The proposed method provides comparable results with state-of-the-art methods. Validation results suggest that it may be suitable for the clinical use. C 2015 American Association of Physicists in Medicine. [http://dx

show abstract

Automatic Liver Segmentation of Contrast Enhanced CT Images Based on Histogram Processing

Cited by 23 publications

References 3 publications

Comparative study on the performance of textural image features for active contour segmentation

Comparative study on the performance of textural image features for active contour segmentation

Liver segmentation for hepatic lesions detection and characterisation

3D liver segmentation using multiple region appearances and graph cuts

Contact Info

Product

Resources

About