Segmentation of Biological Volume Datasets Using a Level-Set Framework

Whitaker, Ross T.; Breen, David E.; Museth, Ken; Soni, Neha

doi:10.1007/978-3-7091-6756-4_17

Cited by 16 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distance fields have been used before to expedite registration processes [13]; however, no previous work has generated these distance fields with super-resolution accuracy. Recovering material boundaries from sampled datasets, as well as generating distance fields once geometric models have been extracted, is a research topic in several fields [10], [14], [15]. We build on the work of Laidlaw et al [2], who use Bayesian probability theory to classify accurately tissues in medical volume images.…”

Section: Discussionmentioning

confidence: 99%

Super-resolution registration using tissue-classified distance fields

Marai

Laidlaw

Crisco

2006

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Abstract-We present a method for registering the position and orientation of bones across multiple computed-tomography (CT) volumes of the same subject. The method is subvoxel accurate, can operate on multiple bones within a set of volumes, and registers bones that have features commensurate in size to the voxel dimension. First, a geometric object model is extracted from a reference volume image. We use then unsupervised tissue classification to generate from each volume to be registered a super-resolution distance field-a scalar field that specifies, at each point, the signed distance from the point to a material boundary. The distance fields and the geometric bone model are finally used to register an object through the sequence of CT images. In the case of multiobject structures, we infer a motion-directed hierarchy from the distance-field information that allows us to register objects that are not within each other's capture region.We describe a validation framework and evaluate the new technique in contrast with grey-value registration. Results on human wrist data show average accuracy improvements of 74% over greyvalue registration. The method is of interest to any intrasubject, same-modality registration applications where subvoxel accuracy is desired.

show abstract

Section: Discussionmentioning

confidence: 99%

Super-resolution registration using tissue-classified distance fields

Marai

Laidlaw

Crisco

2006

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…There are many applications in the biosciences, computer vision, medical, and pattern recognition communities where guidance by human experts is required [7,20,27,48,50]. The current interactive GPU level set methods, such as [36], provide interfaces to (1) initialize / inside/outside the object, (2) dynamically adjust parameters, and in some cases (3) allow / to be edited (a union operator on new objects/regions, followed by rerunning of the algorithm); however, it is difficult to refine evolution such as to prevent contour leaking or constrain the evolution.…”

Section: Interactive Brushesmentioning

confidence: 99%

Interactive GPU active contours for segmenting inhomogeneous objects

Willcocks

Jackson

Nelson

et al. 2017

J Real-Time Image Proc

View full text Add to dashboard Cite

We present a segmentation software package primarily targeting medical and biological applications, with a high level of visual feedback and several usability enhancements over existing packages. Specifically, we provide a substantially faster GPU implementation of the local Gaussian distribution fitting energy model, which can segment inhomogeneous objects with poorly defined boundaries as often encountered in biomedical images. We also provide interactive brushes to guide the segmentation process in a semiautomated framework. The speed of our implementation allows us to visualize the active surface in real time with a built-in ray tracer, where users may halt evolution at any time step to correct implausible segmentation by painting new blocking regions or new seeds. Quantitative and qualitative validation is presented, demonstrating the practical efficacy of our interactive elements for a variety of real-world datasets.

show abstract

“…We formulate our approach to 3D reconstruction of geometric mod els from multiple non-uniform volumetric datasets within a Ievel set segmentation framework [23]. The level set models utilized within this framework are deformable implicit surfaces whose de formation is controlled by a speed function in the level set partial differential equation (PDE).…”

Section: Methods Descriptionmentioning

confidence: 99%

“…Thus, level set deforma tions alone are not sufficient, they must be combined with powerful initialization techniques in order to produce successful segmenta tions. Our level set segmentation framework consists of a set of suitable pre-processing techniques for initialization, which are then followed by the selection and tuning of different feature-extracting terms in the level set algorithm, as seen in Figure 2 [23]. Once these terms are defined the level set deformation proceeds to produce the final result.…”

Section: Level Set Segmentation Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Level set segmentation from multiple non-uniform volume datasets

Museth

Breen

Zhukov

et al.

IEEE Visualization, 2002. VIS 2002.

View full text Add to dashboard Cite

Figure 1: 3D level set model of a griffin derived from two non-uniform laser scan reconstruction volume datasets. The two input models with resolution 294 x 312 x 24 and 294x 52 x 144 show severe aliasing effects from insufficient sampling. especially in the wings. Our method merges information from both of the datasets to produce a high resolution 294x312x 144 level set model. All models throughout this paper are flat-shaded to highlight details. ABSTRACTTypically 3-D MR and CT scans have a relatively high resolution in the scanning X -Y plane, but much lower resolution in the axial Z direction. This non-uniform sampling of an object can miss small or thin structures. One way to address this problem is to scan the same object from multiple directions. In this paper we describe a method for deforming a level set model using velocity information derived from multiple volume datasets with non-uniform resolution in order to produce a single high-resolution 3D model. The method locally approximates the values of the multiple datasets by fitting a distance-weighted polynomial using moving least-squares. The proposed method has several advantageous properties: its compu tational cost is proportional to the object surface area, it is stable with respect to noise, imperfect registrations and abrupt changes in the data, it provides gain-correction, and it employs a distance-' based weighting to ensures that the contributions from each scan are properly merged into the final result. We have demonstrated the effectiveness of our approach on four multi-scan datasets, a griffin laser scan reconstruction, a CT scan of a teapot and MR scans of a mouse embryo and a zucchini.

show abstract

Segmentation of Biological Volume Datasets Using a Level-Set Framework

Cited by 16 publications

References 18 publications

Super-resolution registration using tissue-classified distance fields

Super-resolution registration using tissue-classified distance fields

Interactive GPU active contours for segmenting inhomogeneous objects

Level set segmentation from multiple non-uniform volume datasets

Contact Info

Product

Resources

About