Automatic Liver Segmentation Based on Shape Constraints and Deformable Graph Cut in CT Images
The DOI matches its Crossref record; 48 of the 52 references it cites were found in a registry or an index.
Abstract
Liver segmentation is still a challenging task in medical image processing area due to the complexity of the liver's anatomy, low contrast with adjacent organs, and presence of pathologies. This investigation was used to develop and validate an automated method to segment livers in CT images. The proposed framework consists of three steps: 1) preprocessing; 2) initialization; and 3) segmentation. In the first step, a statistical shape model is constructed based on the principal component analysis and the input image is smoothed using curvature anisotropic diffusion filtering. In the second step, the mean shape model is moved using thresholding and Euclidean distance transformation to obtain a coarse position in a test image, and then the initial mesh is locally and iteratively deformed to the coarse boundary, which is constrained to stay close to a subspace of shapes describing the anatomical variability. Finally, in order to accurately detect the liver surface, deformable graph cut was proposed, which effectively integrates the properties and inter-relationship of the input images and initialized surface. The proposed method was evaluated on 50 CT scan images, which are publicly available in two databases Sliver07 and 3Dircadb. The experimental results showed that the proposed method was effective and accurate for detection of the liver surface.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Our proposed method competes with state-of-the-art.”
From Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields (2016) · cites this paper as [16]
In the citing paper
“Furthermore, and in contrast to prior work such as [5,15,16], our proposed method could be generalized to segment multiple organs in medical data using multiple cascaded FCNs.”
From Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields (2016) · cites this paper as [16]
Citations
Cites
Estimates of worldwide burden of cancer in 2008: GLOBOCAN 2008
Ferlay, J., Shin, H., Bray, F., Forman, D., Mathers, C., & Parkin, D. M. (2010) · International Journal of Cancer · doi:10.1002/ijc.25516 · Cited by 21,293
Marching cubes: A high resolution 3D surface construction algorithm
Lorensen, W. E., & Cline, H. E. (1987) · Proceedings of the 14th annual conference on Computer graphics and interactive techniques · doi:10.1145/37401.37422 · Cited by 10,104 · cited 2×
“The labeled binary images are converted into triangulated meshes to represent manual segmentation by using the marching cube algorithm [32].”
MethodMarching cubes: A high resolution 3D surface construction algorithm
Lorensen, W. E., & Cline, H. E. (1987) · ACM SIGGRAPH Computer Graphics · doi:10.1145/37402.37422 · Cited by 8,647
An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision
Boykov, Y., & Kolmogorov, V. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.60 · Cited by 4,577
Closed-form solution of absolute orientation using unit quaternions
Horn, B. K. P. (1987) · Journal of the Optical Society of America A · doi:10.1364/josaa.4.000629 · Cited by 4,116
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images
Boykov, Y. Y., & Jolly, M.-P. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937505 · Cited by 3,674 · cited 4×
“[5]–[7].”
BackgroundMethodInfluentialGraph Cuts and Efficient N-D Image Segmentation
Boykov, Y., & Funka-Lea, G. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-7934-5 · Cited by 1,910 · cited 4×
“[5]–[7].”
BackgroundMethodInfluentialStatistical shape models for 3D medical image segmentation: A review
Heimann, T., & Meinzer, H.-P. (2009) · Medical Image Analysis · doi:10.1016/j.media.2009.05.004 · Cited by 1,417 · cited 3×
“Many researchers have provided publicly available datasets and/or organized liver segmentation competitions to investigate those current segmentation algorithms [3].”
BackgroundMethodComparison and evaluation of methods for liver segmentation from CT datasets
Heimann, T., van Ginneken, B., Styner, M. A., Arzhaeva, Y., Aurich, V., Bauer, C., Beck, A., Becker, C., Beichel, R., Bekes, G., et al. (2009) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2009.2013851 · Cited by 1,135 · cited 1×
“…of our proposed method, we compared the segmentation results with the ground truth according to the following five volume and surface based metrics [41]: volumetric overlap error (VOE), signed relative volume difference (SRVD), average symmetric surface distance (ASD), root mean square symmetric…”
MethodOptimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach
Li, K., Wu, X., Chen, D. Z., & Sonka, M. (2006) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2006.19 · Cited by 664 · cited 3×
“• Inspired by [18], [19], [29], and [30], a new graph is constructed to achieve an accurate liver surface detection by using the proposed deformable graph cut.”
BackgroundMethodInterpolating Subdivision for meshes with arbitrary topology
Zorin, D., Schröder, P., & Sweldens, W. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237254 · Cited by 537
Automatic Model-Based Segmentation of the Heart in CT Images
Ecabert, O., Peters, J., Schramm, H., Lorenz, C., von Berg, J., Walker, M. J., Vembar, M., Olszewski, M. E., Subramanyan, K., Lavi, G., et al. (2008) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2008.918330 · Cited by 368 · cited 2×
“On the other hand, the amount of data produced by high resolution CT scanners, as well as the time needed to review the resulting several thousand slices, has been continuously increasing, which makes it tedious and time-consuming for radiologists and physicians [2].”
BackgroundMethodThe use of active shape models for locating structures in medical images
Cootes, T. F., Hill, A., Taylor, C. J., & Haslam, J. (2005) · Lecture Notes in Computer Science · doi:10.1007/bfb0013779 · Cited by 297 · cited 1×
“[15] introduced active shape models to image segmentation.”
MethodNew quadric metric for simplifiying meshes with appearance attributes
Hoppe, H. (1999) · IEEE Visualization · doi:10.5555/319351.319357 · Cited by 288
Laplacian-Isoparametric Grid Generation Scheme
Herrmann, L. R. (1976) · Journal of the Engineering Mechanics Division · doi:10.1061/jmcea3.0002158 · Cited by 235
A General Algorithm for Computing Distance Transforms in Linear Time
Meijster, A., Roerdink, J. B. T. M., & Hesselink, W. H. (2005) · Computational Imaging and Vision · doi:10.1007/0-306-47025-x_36 · Cited by 234 · cited 1×
“The algorithm computes Euclidean distance for d -dimensional images in linear time [36].”
MethodNew quadric metric for simplifying meshes with appearance attributes
Hoppe, H. (2003) · Proceedings Visualization '99 (Cat. No.99CB37067) · doi:10.1109/visual.1999.809869 · Cited by 229 · cited 1×
“In order to reduce the time complexity of the correspondence construction algorithm, all meshes are simplified by using the quadric error metric algorithm [33] with the same V vertices connected in T triangles.”
MethodA multilevel banded graph cuts method for fast image segmentation
Lombaert, H., Sun, Y., Grady, L., & Xu, C. (2005) · Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 · doi:10.1109/iccv.2005.13 · Cited by 220 · cited 6×
“As reported in the literature [18], [21], [22], [26], [28], [37], some sharp structures such as the lateral lobe often exist as shown in Fig.5, which makes it difficult to extract using these methods.”
BackgroundMethodInfluentialObject segmentation using graph cuts based active contours
Xu, N., Ahuja, N., & Bansal, R. (2007) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2006.11.004 · Cited by 219
Medical Image Segmentation by Combining Graph Cuts and Oriented Active Appearance Models
Chen, X., Udupa, J. K., Bagci, U., Zhuge, Y., & Yao, J. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2186306 · Cited by 207 · cited 6×
“[26] combined an oriented active appearance model with a pseudo-3D initialization strategy and shape constrained graph cuts to automatically segment livers.”
BackgroundMethodInfluentialSelf-citationLiver segmentation from computed tomography scans: A survey and a new algorithm
Campadelli, P., Casiraghi, E., & Esposito, A. (2009) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2008.07.020 · Cited by 197 · cited 1×
“A comprehensive review of different methods have been presented [3], [8].”
MethodChen, X., Niemeijer, M., Zhang, L., Lee, K., Abramoff, M. D., & Sonka, M. (2012) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2012.2191302 · Cited by 196 · cited 1×
“• Inspired by [18], [19], [29], and [30], a new graph is constructed to achieve an accurate liver surface detection by using the proposed deformable graph cut.”
BackgroundSelf-citationShape Constrained Automatic Segmentation of the Liver based on a Heuristic Intensity Model
Kainmueller, D., Lange, T., & Lamecker, H. (2007) · Cited by 171
Automatic Liver Segmentation Using a Statistical Shape Model With Optimal Surface Detection
Zhang, X., Tian, J., Deng, K., Wu, Y., & Li, X. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2056369 · Cited by 156 · cited 6×
“• Inspired by [18], [19], [29], and [30], a new graph is constructed to achieve an accurate liver surface detection by using the proposed deformable graph cut.”
BackgroundMethodInfluentialSelf-citationTumor Burden Analysis on Computed Tomography by Automated Liver and Tumor Segmentation
Linguraru, M. G., Richbourg, W. J., Liu, J., Watt, J. M., Pamulapati, V., Wang, S., & Summers, R. M. (2012) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2012.2211887 · Cited by 136 · cited 1×
“[25] employed a 3D affine invariant shape parameterization method to compare features of a set of closed 3D surfaces point-to-point correspondence to detect shape ambiguities on an initial segmentation of the liver and used a shape-driven geodesic active contour method to segment the liver, followed…”
MethodVariable-conductance, level-set curvature for image denoising
Whitaker, R. T., & Xue, X. (2002) · Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205) · doi:10.1109/icip.2001.958071 · Cited by 130 · cited 1×
“The mean liver shape model is trained by using PCA, and CT images are enhanced by applying a curvature anisotropic diffusion filter [31], as shown in Fig.3.”
MethodShi, F., Chen, X., Zhao, H., Zhu, W., Xiang, D., Gao, E., Milan Sonka, A., & Chen, H. (2014) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2359980 · Cited by 128 · cited 1×
“• Inspired by [18], [19], [29], and [30], a new graph is constructed to achieve an accurate liver surface detection by using the proposed deformable graph cut.”
BackgroundSelf-citationSegmentation of the Liver using a 3D Statistical Shape Model
Lamecker, H., Lange, T., & Seebaß, M. (2004) · Cited by 112
Fully automatic liver segmentation for contrast-enhanced CT images
Ruskó, L., Bekes, G., Németh, G., & Fidrich, M. (2008) · Cited by 95
Fully Automatic Liver Segmentation through Graph-Cut Technique
Massoptier, L., & Casciaro, S. (2007) · 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2007.4353524 · Cited by 84 · cited 1×
“Massoptier and Casciaro [23] applied a graph-cut method initialized by an adaptive threshold to perform fully automatic liver segmentation in CT images.”
MethodTomoshige, S., Oost, E., Shimizu, A., Watanabe, H., & Nawano, S. (2013) · Medical Image Analysis · doi:10.1016/j.media.2013.10.003 · Cited by 83 · cited 4×
“[28] combined a level set based conditional statistical shape model and graph cuts segmentation based on the estimated shape prior to automatic liver segmentation from non-contrast abdominal CT volumes.”
BackgroundMethodInfluentialA Generic Probabilistic Active Shape Model for Organ Segmentation
Wimmer, A., Soza, G., & Hornegger, J. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04271-3_4 · Cited by 81 · cited 1×
“Table II shows the quantitative comparative results of the liver segmentation with previous methods in [17], [18], [26], [42], and [43] and the proposed liver shape initialization and segmentation based on the Sliver07 database.”
MethodFast automatic liver segmentation combining learned shape priors with observed shape deviation
Erdt, M., Steger, S., Kirschner, M., & Wesarg, S. (2010) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2010.6042650 · Cited by 73
A New Approach for Model-Based Adaptive Region Growing in Medical Image Analysis
Pohle-Fröhlich, R., & Toennies, K. D. (2001) · Lecture notes in computer science · doi:10.1007/3-540-44692-3_30 · Cited by 67 · cited 1×
“The region-growing based liver segmentation approaches [11], [13], [14] can obtain good results from contrast enhanced CT images but they are very sensitive to initial seeds.”
BackgroundLiver segmentation by intensity analysis and anatomical information in multi-slice CT images
Foruzan, A. H., Zoroofi, R. A., Hori, M., & Sato, Y. (2009) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-009-0293-2 · Cited by 56 · cited 2×
“Simple pixel-based methods [9]–[12] include global thresholding, region growing, voxel classification, or edge detection.”
Methodvan Rikxoort, E. M., Arzhaeva, Y., & van Ginneken, B. (2007) · Cited by 53
Beichel, R., Bornik, A., Bauer, C., & Sorantin, E. (2012) · Medical Physics · doi:10.1118/1.3682171 · Cited by 50 · cited 1×
“[24] developed an interactive segmentation system which allowed the user to manipulate liver volume by combining a graph cuts segmentation method and a 3D virtual reality based segmentation refinement approach.”
MethodWang, G., Zhang, S., Xie, H., Metaxas, D., & Gu, L. (2014) · Medical Image Analysis · doi:10.1016/j.media.2014.10.003 · Cited by 48 · cited 1×
“Subsequently, they employed a homotopy-based method to solve the L1-norm optimization problem [20].”
MethodZhou, X., Kitagawa, T., Hara, T., Fujita, H., Zhang, X., Yokoyama, R., Kondo, H., Kanematsu, M., & Hoshi, H. (2006) · Lecture notes in computer science · doi:10.1007/11866763_105 · Cited by 46 · cited 2×
“Simple pixel-based methods [9]–[12] include global thresholding, region growing, voxel classification, or edge detection.”
MethodLinguraru, M. G., Richbourg, W. J., Watt, J. M., Pamulapati, V., & Summers, R. M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28557-8_25 · Cited by 36 · cited 1×
“Table II shows the quantitative comparative results of the liver segmentation with previous methods in [17], [18], [26], [42], and [43] and the proposed liver shape initialization and segmentation based on the Sliver07 database.”
MethodA new segmentation framework based on sparse shape composition in liver surgery planning system
Wang, G., Zhang, S., Li, F., & Gu, L. (2013) · Medical Physics · doi:10.1118/1.4802215 · Cited by 33 · cited 2×
“To tackle these problems, shape priors are desirable and advisable, since they can help to separate adjacent organs with similar intensities and preserve liver shape with non-homogeneous gray level [4].”
BackgroundMethodLiver Segmentation from CT Images Based on Region Growing Method
Chen, Y., Wang, Z., Zhao, W., & Yang, X. (2009) · International Conference on Bioinformatics and Biomedical Engineering · doi:10.1109/icbbe.2009.5163018 · Cited by 31 · cited 1×
“The region-growing based liver segmentation approaches [11], [13], [14] can obtain good results from contrast enhanced CT images but they are very sensitive to initial seeds.”
BackgroundChen, X., Udupa, J. K., Alavi, A. A., & Torigian, D. A. (2012) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.12.001 · Cited by 30 · cited 2×
“Unlike the traditional graph construction algorithms which built a regular graph for the entire image [21], [22], [26], [28], [37], our graph construction strategy enables the construction of a deformable graph according to the initial surface properties.”
BackgroundSelf-citationSkeleton Cuts—An Efficient Segmentation Method for Volume Rendering
Xiang, D., Tian, J., Yang, F., Yang, Q., Zhang, X., Li, Q., & Liu, X. (2010) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2010.239 · Cited by 26 · cited 3×
“3) Each node corresponded a voxel in the test image in Chen’s graph, which will consume huge amount of memory as resolutions of CT images increase, as pointed in [21] and [38].”
BackgroundMethodSelf-citationThe Probabilistic Active Shape Model: From Model Construction to Flexible Medical Image Segmentation
Kirschner, M. (2013) · Technischen Universität Darmstadt · doi:10.2312/8306 · Cited by 23
Regional appearance modeling based on the clustering of intensity profiles
Chung, F., & Delingette, H. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2013.01.011 · Cited by 22 · cited 1×
“Table III shows the quantitative comparative results of the liver segmentation with previous methods in [44]–[46] and the proposed liver shape initialization and segmentation based on the 3Dircadb database.”
MethodImplementing the Automatic Generation of 3D Statistical Shape Models with ITK
Heimann, T., Oğuz, İ., Ivo Wolf, A., Styner, M. A., & Meinzer, H. (2006) · The Insight Journal · doi:10.54294/q3fj21 · Cited by 22 · cited 1×
“The minimum description length (MDL) algorithm [34] is then used to establish vertex correspondence between the reference meshes.”
MethodLiver segmentation based on SKFCM and improved GrowCut for CT images
Song, H., Zhang, Q., & Wang, S. (2014) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2014.6999179 · Cited by 9 · cited 1×
“[27] roughly segmented the liver based on a kernel fuzzy C-means algorithm with spatial information and the refined segmentation was performed based on the GrowCut algorithm.”
Method
Research works printed but not linked: 1
- ferlay, 2013, GLOBOCAN 2012 v1.0, Cancer Incidence Mortality and Prevalence Worldwide IARC CancerBase
Cited by
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes
Li, X., Chen, H., Qi, X., Dou, Q., Fu, C.-W., & Heng, P.-A. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2845918 · Cited by 2,473
“[54] used the SLIVER07 dataset in the training, respectively.”
MethodChrist, P. F., Elshaer, M. E. A., Ettlinger, F., Tatavarty, S., Bickel, M., Bilic, P., Rempfler, M., Armbruster, M., Hofmann, F., D’Anastasi, M., et al. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_48 · Cited by 625
“In comparison to state-of-the-art, such as [5,15,16,2], we presented a framework, which is capable of a combined segmentation of the liver and its lesion.”
BackgroundResult3D deeply supervised network for automated segmentation of volumetric medical images
Dou, Q., Yu, L., Chen, H., Jin, Y., Yang, X., Qin, J., & Heng, P.-A. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.05.001 · Cited by 613
Seo, H., Huang, C., Bassenne, M., Xiao, R., & Xing, L. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2948320 · Cited by 431
“Many algorithms for automatic segmentation of livers and liver tumors have been studied, such as atlasbased models [3], graphical models [4], [5], and deformable models [6], [7].”
BackgroundAbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?
Ma, J., Zhang, Y., Gu, S., Zhu, C., Ge, C., Zhang, Y., An, X., Wang, C., Wang, Q., Liu, X., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3100536 · Cited by 426
“delineate the structure of interest [29], [30], [31].”
Background
Metadata
- Authors
- Li, G., Chen, X., Shi, F., Zhu, W., Tian, J., & Xiang, D.
- Affiliations
- Chinese Academy of Sciences (CN)
- Soochow University (CN)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2015-12
- Volume
- 24
- Issue
- 12
- Pages
- 5315-5329
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2138047924
- Cited by
- 185
- References
- 52
- Citations by year
- 2026: 5 · 2025: 6 · 2024: 10 · 2023: 10 · 2022: 26 · 2021: 29 · 2020: 17 · 2019: 28 · 2018: 24 · 2017: 17 · 2016: 10 · 2015: 2
- FWCI
- 15.30
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (81371629, 61401293, 61401294, 81401472, 81401451)
- Natural Science Foundation of the Jiangsu Higher Education of China (14KJB510032)
- National Basic Research Program of China (973 Program) (2014CB748600)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
- Physical Sciences › Engineering › Biomedical Engineering › Anatomy and Medical Technology
- Keywords
- liver segmentation, CT images, statistical shape models, shape constraints, principal component analysis, Euclidean distance transformation, anatomical variation
- MeSH terms
- Algorithms, Humans, Image Processing, Computer-Assisted, Liver, Liver Neoplasms, Tomography, X-Ray Computed, Principal Component Analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.