Geometrically Proper Models in Statistical Training

Han, Qi; Merck, Derek; Levy, Joshua H.; Villarruel, Christina; Damon, James; Chaney, Edward L.; Pizer, Stephen M.

doi:10.1007/978-3-540-73273-0_62

Cited by 11 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D m-rep model M t is built from a manual segmentation of pre-operative CT scans of the target object by experts, and an m-rep is fitted into the segmentation using the binary fitting method described in [11]. An automatic segmentation tool will be highly desirable for this step.…”

Section: A Pre-built 3d Model For the Target Objectmentioning

confidence: 99%

See 1 more Smart Citation

Model Completion via Deformation Cloning Based on an Explicit Global Deformation Model

Han

Carswell

Clarke

et al. 2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

Self Cite

View full text Add to dashboard Cite

Abstract. Our main focus is the registration and visualization of a pre-built 3D model from preoperative images to the camera view of a minimally invasive surgery (MIS). Accurate estimation of soft-tissue deformations is key to the success of such a registration. This paper proposes an explicit statistical model to represent global non-rigid deformations. The deformation model built from a reference object is cloned to a target object to guide the registration of the pre-built model, which completes the deformed target object when only a part of the object is naturally visible in the camera view. The registered target model is then used to estimate deformations of its substructures. Our method requires a small number of landmarks to be reconstructed from the camera view. The registration is driven by a small set of parameters, making it suitable for real-time visualization.

show abstract

Section: A Pre-built 3d Model For the Target Objectmentioning

confidence: 99%

“…where m t,i is a medial atom in M t , and where f leg is the illegality penalty term defined by equation (12) in [11]. This component penalizes shape illegalities, such as creasing or folding.…”

Section: Model Registration Via Deformation Cloningmentioning

confidence: 99%

Model Completion via Deformation Cloning Based on an Explicit Global Deformation Model

Han

Carswell

Clarke

et al. 2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…39 The largest eigenvalue of the radial shape operator yields a legality measure at every sample point with a well defined threshold for identifying folded surfaces. 40 As we narrow down the shape space during the fitting procedure, we tend to relax Nonuniform͑͒ and rely more on the legality measure. Similar smoothness and legality functions can be mathematically derived for other shape representations specifying local orientations.…”

Section: Iid2 Legalitymentioning

confidence: 99%

“…56, but dependent both on local shape and on local orientation. Measuring the largest eigenvector of the spoke length radial shape operator at each grid position 39,40 gives an immediate indication of local self-interpenetration in the volume.…”

Section: Medial Geometrymentioning

confidence: 99%

Training models of anatomic shape variability

Merck

Tracton²,

Saboo³

et al. 2008

Med. Phys.

Self Cite

View full text Add to dashboard Cite

Learning probability distributions of the shape of anatomic structures requires fitting shape representations to human expert segmentations from training sets of medical images. The quality of statistical segmentation and registration methods is directly related to the quality of this initial shape fitting, yet the subject is largely overlooked or described in an ad hoc way. This article presents a set of general principles to guide such training. Our novel method is to jointly estimate both the best geometric model for any given image and the shape distribution for the entire population of training images by iteratively relaxing purely geometric constraints in favor of the converging shape probabilities as the fitted objects converge to their target segmentations. The geometric constraints are carefully crafted both to obtain legal, nonself-interpenetrating shapes and to impose the model-tomodel correspondences required for useful statistical analysis. The paper closes with example applications of the method to synthetic and real patient CT image sets, including same patient male pelvis and head and neck images, and cross patient kidney and brain images. Finally, we outline how this shape training serves as the basis for our approach to IGRT/ART.

show abstract

“…When σ > 1, the formula for c i is given in (7). Substituting 1 σ → σ into (5) and −φ → φ into (6), shows that the size and orientation of C are independent of which curve is given the name S [0] and which is S [1].…”

Section: Interpolation Of a Similar Curvesmentioning

confidence: 99%

Rotational flows for interpolation between sampled surfaces

Levy

Foskey

Pizer

2008

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Self Cite

View full text Add to dashboard Cite

We introduce a locally defined shape-maintaining method for interpolating between corresponding oriented samples (vertices) from a pair of surfaces. We have applied this method to interpolate synthetic data sets in two and three dimensions and to interpolate medially represented shape models of anatomical objects in three dimensions. In the plane, each oriented vertex follows a circular arc as if it was rotating to its destination. In three dimensions, each oriented vertex moves along a helical path that combines in-plane rotation with translation along the axis of rotation.We show that our planar method provides shapemaintaining interpolations when the reference and target objects are similar. Moreover, the interpolations are size maintaining when the reference and target objects are congruent. In three dimensions, similar objects are interpolated by an affine transformation. We use measurements of the fractional anisotropy of such global affine transformations to demonstrate that our method is generally more shape preserving than the alternative of interpolating vertices along linear paths irrespective of changes in orientation. In both two and three dimensions we have experimental evidence that when non-shape-preserving deformations are applied to template shapes, the interpolation tends to be visually satisfying with each intermediate object appearing to belong to the same class of objects as the end points.

show abstract

Geometrically Proper Models in Statistical Training

Cited by 11 publications

References 13 publications

Model Completion via Deformation Cloning Based on an Explicit Global Deformation Model

Model Completion via Deformation Cloning Based on an Explicit Global Deformation Model

Training models of anatomic shape variability

Rotational flows for interpolation between sampled surfaces

Contact Info

Product

Resources

About