Computing the Differential Characteristics of Isointensity Surfaces

Thirion, Jean-Philippe; Gourdon, Alexis

doi:10.1006/cviu.1995.1015

Cited by 186 publications

(114 citation statements)

References 0 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…Based on the initial nodule region and the grown nodule region, we then extracted 18 features for each of the nodule candidates from the original image, from the nodule-, blood vessel-, and airway wall-enhanced images obtained with our selective enhancement filters [23], and from the two images for the shape index and curvedness based on the differential characteristics of the isointensity surface [26]. The 18 features extracted were:…”

Section: Feature Determinationmentioning

confidence: 99%

See 1 more Smart Citation

Computerized Detection of Lung Nodules in Thin-Section CT Images by Use of Selective Enhancement Filters and an Automated Rule-Based Classifier

Li¹,

Li²,

Doi³

2008

Academic Radiology

133

105

View full text Add to dashboard Cite

We have been developing a computer-aided diagnostic (CAD) scheme for lung nodule detection in order to assist radiologists in the detection of lung cancer in thin-section computed tomography (CT) images. Our database consisted of 117 thin-section CT scans with 153 nodules, obtained from a lung cancer screening program at a Japanese university (85 scans, 91 nodules) and from clinical work at an American university (32 scans, 62 nodules). The database included nodules of different sizes (4-28 mm, mean 10.2 mm), shapes, and patterns (solid and ground-glass opacity (GGO)). Our CAD scheme consisted of modules for lung segmentation, selective nodule enhancement, initial nodule detection, feature extraction, and classification. The selective nodule enhancement filter was a key technique for significant enhancement of nodules and suppression of normal anatomic structures such as blood vessels, which are the main sources of false positives. Use of an automated rule-based classifier for reduction of false positives was another key technique; it resulted in a minimized overtraining effect and an improved classification performance. We employed a case-based four-fold cross-validation testing method for evaluation of the performance levels of our computerized detection scheme. Our CAD scheme achieved an overall sensitivity of 86% (small: 76%, medium-sized: 94%, large: 95%; solid: 86%, mixed GGO: 89%, pure GGO: 81%) with 6.6 false positives per scan; an overall sensitivity of 81% (small: 69%, medium-sized: 91%, large: 91%; solid: 79%, mixed GGO: 88%, pure GGO: 81%) with 3.3 false positives per scan; and an overall sensitivity of 75% (small: 60%, medium-sized: 88%, large: 87%; solid: 70%, mixed GGO: 87%, pure GGO: 81%) with 1.6 false positives per scan. The experimental results indicate that our CAD scheme with its two key techniques can achieve a relatively high performance for nodules presenting large variations in size, shape, and pattern.

show abstract

Section: Feature Determinationmentioning

confidence: 99%

“…Twelve features based on voxel value: mean and standard deviation of voxel values inside the grown region, each extracted from the original CT image, from the nodule-, blood vessel-, and airway wall-enhanced images [23], and from the two images for the shape index and curvedness [26].…”

mentioning

confidence: 99%

Computerized Detection of Lung Nodules in Thin-Section CT Images by Use of Selective Enhancement Filters and an Automated Rule-Based Classifier

Li¹,

Li²,

Doi³

2008

Academic Radiology

133

105

View full text Add to dashboard Cite

show abstract

“…Ridge curves correspond to local extrema of curvature taken in the principal direction of the surface, after some algebraic manipulations they can be obtained as implicit curve (see [CFPR05]). See also [TG92] and [TG95] for other related approaches. In the example it corresponds to a bicubic surface, the input polynomial is of total degree 84, of multidegree (43, 43) with 1907 monomials.…”

Section: Planar Curves Of High Degree With Large Coefficientsmentioning

confidence: 99%

Subdivision Methods for the Topology of 2d and 3d Implicit Curves

Chen¹,

Mourrain²,

Pavone³

2008

Geometric Modeling and Algebraic Geometry

View full text Add to dashboard Cite

Abstract. In this paper, we describe a subdivision method for handling algebraic implicit curves in 2d and 3d. We use the representation of polynomials in the Bernstein basis associated with a given box, to check if the topology of the curve is determined inside this box, from its points on the border of the box. Subdivision solvers are used for computing these points on the faces of the box, and segments joining these points are deduced to get a graph isotopic to the curve. Using envelop of polynomials, we show how this method allow to handle efficiently and accurately implicit curves with large coefficients. We report on implementation aspects and experimentations on 2d curves such as ridge curves or self intersection curves of parameterized surfaces, and on silhouette curves of implicit surfaces, showing the interesting practical behavior of this approach.

show abstract

“…However, it is limited to curves/surfaces embedded in 2D or 3D spaces. There exists some literature from the visualization community, e.g., [14,36] and references therein, that develops second order derivative computation on iso-surfaces extracted from trivariate functions. Most of these approaches use discrete approximations.…”

Section: Compute the Structural Change At Transition Eventsmentioning

confidence: 99%

Theoretically Based Robust Algorithms for Tracking Intersection Curves of Two Deforming Parametric Surfaces

Chen

Riesenfeld

Cohen

et al. 2006

Geometric Modeling and Processing - GMP 2006

View full text Add to dashboard Cite

Abstract. This paper applies singularity theory of mappings of surfaces to 3-space and the generic transitions occurring in their deformations to develop algorithms for continuously and robustly tracking the intersection curves of two deforming parametric spline surfaces, when the deformation is represented as a family of generalized offset surfaces. The set of intersection curves of 2 deforming surfaces over all time is formulated as an implicit 2-manifold I in the augmented (by time domain) parametric space R 5 . Hyper-planes corresponding to some fixed time instants may touch I at some isolated transition points, which delineate transition events, i.e., the topological changes to the intersection curves. These transition points are the 0-dimensional solution to a rational system of 5 constraints in 5 variables, and can be computed efficiently and robustly with a rational constraint solver using subdivision and hyper-tangent bounding cones. The actual transition events are computed by contouring the local osculating paraboloids. Away from any transition points, the intersection curves do not change topology and evolve according to a simple evolution vector field that is constructed in the euclidean space in which the surfaces are embedded.

show abstract

Computing the Differential Characteristics of Isointensity Surfaces

Cited by 186 publications

References 0 publications

Computerized Detection of Lung Nodules in Thin-Section CT Images by Use of Selective Enhancement Filters and an Automated Rule-Based Classifier

Computerized Detection of Lung Nodules in Thin-Section CT Images by Use of Selective Enhancement Filters and an Automated Rule-Based Classifier

Subdivision Methods for the Topology of 2d and 3d Implicit Curves

Theoretically Based Robust Algorithms for Tracking Intersection Curves of Two Deforming Parametric Surfaces

Contact Info

Product

Resources

About