ViviSection: Skeleton‐based Volume Editing

Karimov, A.Kh.; Mistelbauer, Gabriel; Schmidt, Jean M.; Mindek, Peter; Schmidt, Ehud J.; Sharipov, T. N.; Brückner, Stefan; Gröller, Eduard

doi:10.1111/cgf.12133

Cited by 4 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the skeletonization we employ the algorithm by Lee et al [LKC94]. The skeleton distance field and the influence zones are calculated using the algorithm from our previous work [KMS*13]. Between individual correction operations all data is recomputed, as all steps of the pipeline depend on the skeleton, which is a global characteristic of the corresponding editing region.…”

Section: Methodsmentioning

confidence: 99%

“…The work of Salz et al [SRW*12] includes sketches over the object and the background, which are then used in geodesic segmentation of heart and lungs. Our previous work [KMS*13] propagates user selections on the skeleton towards the object voxels and allows the following editing operations: removing or adding the selected volume, peeling or growing the surface layer at the selection, and smoothing the selected surface patch. Graph cuts are widely used in volume editing [APB07, BFL06, LRN08].…”

Section: Related Workmentioning

confidence: 99%

“…We do not perform any skeleton post‐processing, e.g., pruning, as it may destroy details of the shape, caused by segmentation defects. We adopt the concept of a skeleton distance field and influence zones, introduced in our previous work [KMS*13]. The skeleton distance field provides distances from all non‐skeleton voxels to the closest skeleton voxels.…”

Section: Guided Volume Editingmentioning

confidence: 99%

“…We denote the influence zone of a skeleton voxel q as IZ ( q ), the distance of a voxel p from the skeleton as D S ( p ), and the largest occurring distance as I max . Details can be found in our previous work [KMS*13]. The correction scenarios abstract the user from the structural information, providing a consistent editing experience throughout different objects.…”

Section: Guided Volume Editingmentioning

confidence: 99%

See 3 more Smart Citations

Guided Volume Editing based on Histogram Dissimilarity

Karimov

Mistelbauer

Auzinger

et al. 2015

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

e) e) f) f) Figure 1: We propose a novel guided volume editing approach for improving the quality of segmented medical data (Jaccard coefficient in percents). (a) Two suggestions to rectify over-estimation defects, with an initial quality of 88%, (b) after applying the suggestions, 91%, (c) after applying four more suggestions, 92%. (d) Two suggestions to fix under-estimation defects, with an initial quality of 80%, (e) after applying the suggestions, 85%, (f) after applying six more suggestions, 94%. AbstractSegmentation of volumetric data is an important part of many analysis pipelines, but frequently requires manual inspection and correction. While plenty of volume editing techniques exist, it remains cumbersome and errorprone for the user to find and select appropriate regions for editing. We propose an approach to improve volume editing by detecting potential segmentation defects while considering the underlying structure of the object of interest. Our method is based on a novel histogram dissimilarity measure between individual regions, derived from structural information extracted from the initial segmentation. Based on this information, our interactive system guides the user towards potential defects, provides integrated tools for their inspection, and automatically generates suggestions for their resolution. We demonstrate that our approach can reduce interaction effort and supports the user in a comprehensive investigation for high-quality segmentations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Guided Volume Editingmentioning

confidence: 99%

Section: Guided Volume Editingmentioning

confidence: 99%

See 2 more Smart Citations

Guided Volume Editing based on Histogram Dissimilarity

Karimov

Mistelbauer

Auzinger

et al. 2015

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…1). By analogy to interactive segmentation algorithms, dedicated editing tools can modify the segmentation result in 2-D [14][15][16] or 3-D. [17][18][19][20][21][22][23][24] We have previously given a detailed overview on segmentation editing for medical imaging. 25 Note that even though an automatic segmentation algorithm might be used in the first stage, the segmentation process itself becomes interactive from the user's point of view as soon as an intervention, such as editing in whatever form, is required.…”

mentioning

confidence: 99%

On the evaluation of segmentation editing tools

et al. 2014

View full text Add to dashboard Cite

Abstract. Efficient segmentation editing tools are important components in the segmentation process, as no automatic methods exist that always generate sufficient results. Evaluating segmentation editing algorithms is challenging, because their quality depends on the user's subjective impression. So far, no established methods for an objective, comprehensive evaluation of such tools exist and, particularly, intermediate segmentation results are not taken into account. We discuss the evaluation of editing algorithms in the context of tumor segmentation in computed tomography. We propose a rating scheme to qualitatively measure the accuracy and efficiency of editing tools in user studies. In order to objectively summarize the overall quality, we propose two scores based on the subjective rating and the quantified segmentation quality over time. Finally, a simulation-based evaluation approach is discussed, which allows a more reproducible evaluation without the need for human input. This automated evaluation complements user studies, allowing a more convincing evaluation, particularly during development, where frequent user studies are not possible. The proposed methods have been used to evaluate two dedicated editing algorithms on 131 representative tumor segmentations. We show how the comparison of editing algorithms benefits from the proposed methods. Our results also show the correlation of the suggested quality score with the qualitative ratings.

show abstract

Dynamic Distance-Based Shape Features for Gait Recognition

2014

View full text Add to dashboard Cite

We propose a novel skeleton-based approach to gait recognition using our Skeleton Variance Image. The core of our approach consists of employing the screened Poisson equation to construct a family of smooth distance functions associated with a given shape. The screened Poisson distance function approximation nicely absorbs and is relatively stable to shape boundary perturbations which allows us to define a rough shape skeleton. We demonstrate how our Skeleton Variance Image is a powerful gait cycle descriptor leading to a significant improvement over the existing state of the art gait recognition rate.

show abstract

ViviSection: Skeleton‐based Volume Editing

Cited by 4 publications

References 27 publications

Guided Volume Editing based on Histogram Dissimilarity

Guided Volume Editing based on Histogram Dissimilarity

On the evaluation of segmentation editing tools

Dynamic Distance-Based Shape Features for Gait Recognition

Contact Info

Product

Resources

About