A Seeded Image Segmentation Framework Unifying Graph Cuts And Random Walker Which Yields A New Algorithm

Sinop, Ali Kemal; Grady, Leo

doi:10.1109/iccv.2007.4408927

Cited by 224 publications

(205 citation statements)

References 11 publications

Supporting

Mentioning

204

Contrasting

Order By: Relevance

“…In both methods, a weighted graph is constructed. Nodes of the graph correspond to voxels in image and edges are placed between nearby voxels [22]. The edge weights are determined by the character of the image intensity.…”

Section: Introductionmentioning

confidence: 99%

Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images

Xiang

Zhang

et al. 2015

IEEE Trans. on Image Process.

136

View full text Add to dashboard Cite

Abstract-Accurate lung tumor delineation plays an important role in radiotherapy treatment planning. Since the lung tumor has poor boundary in PET images and low contrast in CT images, segmentation of tumor in PET and CT images is a challenging task. In this study, we effectively integrate the two modalities by making fully use of the superior contrast of PET images and superior spatial resolution of CT images. Random walk and graph cut method are integrated to solve the segmentation problem, in which random walk is utilized as an initialization tool to provide object seeds for graph cut segmentation on PET and CT images. The co-segmentation problem is formulated as an energy minimization problem which is solved by max-flow/min-cut method. A graph includes two sub-graphs and a special link is constructed, in which one sub-graph is for PET and another is for CT, and the special link encodes a context term which penalizes the difference of the tumor segmentation on the two modalities. To fully utilize the characteristics of PET and CT images, a novel energy representation is devised. For PET, a downhill cost and a 3D derivative cost is proposed. For CT, a shape penalty cost is integrated into the region and boundary function which helps constrain the tumor location during the segmentation. We validate our algorithm on a dataset which consists of 18 PET-CT images. The experimental results indicate the proposed method is superior to the graph cut method solely using the PET or CT is more accurate compared with the random walk method, random walk co-segmentation method, and non-improved graph-cut method.Index Terms-Image segmentation, interactive segmentation, graph cut, random walks, prior information, lung tumor, positron emission tomography (PET), computed tomography (CT).

show abstract

Section: Introductionmentioning

confidence: 99%

Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images

Xiang

Zhang

et al. 2015

IEEE Trans. on Image Process.

136

View full text Add to dashboard Cite

show abstract

“…Graph cut is however known to be sensitive to the number of seeds [11]. If all other unary capacities λ i were set to zero, and all binary capacities β ij to some positive constant, then the smallest cut that separates the source from the sink would simply separate the positive seed from its direct neighbors.…”

Section: Joint Detection and Segmentationmentioning

confidence: 99%

Segmentation Based Features for Lymph Node Detection from 3-D Chest CT

Feulner

Zhou

Hammon

et al. 2011

Machine Learning in Medical Imaging

View full text Add to dashboard Cite

Abstract. Lymph nodes routinely need to be considered in clinical practice in all kinds of oncological examinations. Automatic detection of lymph nodes from chest CT data is however challenging because of low contrast and clutter. Sliding window detectors using traditional features easily get confused by similar structures like muscles and vessels. It recently has been proposed to combine segmentation and detection to improve the detection performance. Features extracted from a segmentation that is initialized with a detection candidate can be used to train a classifier that decides whether the detection is a true or false positive. In this paper, the graph cuts method is adapted to the problem of lymph nodes segmentation. We propose a setting that requires only a single positive seed and at the same time solves the small cut problem of graph cuts. Furthermore, we propose a feature set that is extracted from the candidate segmentation. A classifier is trained on this feature set and used to reject false alarms. Cross validation on 54 CT datasets showed that the proposed system reaches a detection rate of 60.9% with only 6.1 false alarms per volume image, which is better than the current state of the art of mediastinal lymph node detection.

show abstract

“…The segmentation of a partially labeled image (with sparse labeled seeds) has been addressed in [1,12] as an optimal cut on a partially labeled graph using min-cut/max-flow or random walker. In a two-label case, it is possible to find a global optimum because the energy function is convex.…”

Section: Problem Formulationmentioning

confidence: 99%

“…The challenge here is that some new groups may be formed in G x . Instead of using a seeded segmentation as in [1,12], we conduct a pairwise subgraph grouping on G x , which is similar to [3], but with different grouping criteria. Prior to the aggregation of subgraphs in G x , we group the unlabeled nodes in S x into small subgraphs by a low-level color clustering (Mean Shift [2]).…”

Section: Aggregationmentioning

confidence: 99%

Video segmentation: Propagation, validation and aggregation of a preceding graph

Liu

Guo

Yan

et al. 2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

In this work, video segmentation is viewed as an efficient intra-frame grouping temporally reinforced by a strong inter-frame coherence. Traditional approaches simply regard pixel motions as another prior in the MRF-MAP framework. Since pixel pre-grouping is inefficiently performed on every frame, the strong correlation between inter-frame groupings is largely underutilized. We exploit the inter-frame correlation to propagate trustworthy groupings from the previous frame. A preceding graph is constructed and labeled for the previous frame. It is temporally propagated to the current frame and validated by similarity measures. All unlabeled subgraphs are spatially aggregated for the final grouping. Experimental results show that the proposed approach is highly efficient for spatio-temporal segmentation. It makes good use of temporal correlation and produces satisfactory grouping results.

show abstract

A Seeded Image Segmentation Framework Unifying Graph Cuts And Random Walker Which Yields A New Algorithm

Cited by 224 publications

References 11 publications

Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images

Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images

Segmentation Based Features for Lymph Node Detection from 3-D Chest CT

Video segmentation: Propagation, validation and aggregation of a preceding graph

Contact Info

Product

Resources

About