Multidimensional Alignment Using the Euclidean Distance Transform

Kozińska, Dorota; Tretiak, Oleh J.; Nissanov, Jonathan; Öztürk, Cengizhan

doi:10.1006/gmip.1997.0447

Cited by 73 publications

(43 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also different shapes registration approaches were proposed in the literature for example [3,4,5,6]. These approaches suffer from various problems.…”

Section: Introductionmentioning

confidence: 99%

“…But using a simple global transformation with homogenous scales(× Ü × Ý × Þ ×) is not enough specially when gathering training shapes from different patients scans. The registration process fails when the target shape has inhomogeneous scales.Also different shapes registration approaches were proposed in the literature for example [3,4,5,6]. These approaches suffer from various problems.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A New Variational Approach for 3d Shape Registration

Munim

Farag

Farman

2007

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

Shape-based approaches became very popular in medical imaging. The key issue in these methods is the shape representation and registration. This paper introduces a new method for the ¿ shape registration problem by matching vector distance functions. The vector distance function representation is more flexible than the conventional signed distance map since it enables us to better control the shapes registration process by using more general transformations. Based on this model, a variational frame work is proposed for the global and local registration of shapes which does not need any point correspondences. A gradient descent optimization is used and efficiently can handle both the rigid and the non-rigid operations together. The registration of real 3D human teeth models demonstrates the potential of the proposed approach. INTRODUCTIONShapes registration is an important complex problem in computer vision, computer graphics and medical imaging. It has been handled in different manners in many applications like shape-based segmentation, shape recognition, and tracking. The shapes registration problem is formulated such that a transformation that moves a point from a given shape to a target one according to some dissimilarity measure [1], needs to be estimated. The dissimilarity measure can be defined according either to the curve or in the entire region enclosed by the curve.In [2], a 3D shape-segmentation approach was proposed which included a shape registration process. A shape model was built from a set of training shapes using signed distance functions (the conventional representation). A level set function evolves minimizing the shape alignment energy and the intensity gray level. But using a simple global transformation with homogenous scales(× Ü × Ý × Þ ×) is not enough specially when gathering training shapes from different patients scans. The registration process fails when the target shape has inhomogeneous scales.Also different shapes registration approaches were proposed in the literature for example [3,4,5,6]. These approaches suffer from various problems. Scale variations and This research has been supported by the National Science Foundation (NSF) Grant IIS-0513974. local deformations can not be covered in many cases. Also their dependency on the initialization represents one of the hardships.In [7], the distance function is used to implicitly represent planar shapes. The images of distance functions are globally registered using the mutual information approach. Open structures are represented by using only the distance transform without any sign which can not distinguish between points on different sides of the shape contour.Vector distance functions (VDF's) are used in [8] to evolve smooth manifolds. This representation defines a vector that connects any point in the space to the nearest point on the curve or surface. This representation can deal with shapes of different dimensions.We proposed shape representation by vector components in a different manner in our shape-based segmentation...

show abstract

“…Also different shapes registration approaches were proposed in the literature for example [3,4,5,6]. These approaches suffer from various problems.…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

A New Variational Approach for 3d Shape Registration

Munim

Farag

Farman

2007

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

show abstract

“…The objects were represented by point sets in an Euclidean space and the Euclidean distance transform was used to evaluate the residual distance of the test object as it was iteratively aligned to the reference object, and the Marquardt-Levenberg optimization algorithm was used for optimization. For two dimensions, the distance map was in the form of a twodimensional array, whose entries were two-dimensional vectors from the closest point in the object to a given pixel [13].…”

Section: Image Processing Techniques For Assessment Of Dental Traysmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…It is encountered in many fields such as remote sensing, where two-dimensional data sets must be registered, and in biomedical imaging, where two-or three-dimensional image contours and surfaces are collected routinely. We employed distance based alignment technique to register selected two-dimensional points on the casts to main axis of the trays to measure how good their fit were [13].The purpose of this study was to develop a method to help the practitioners to find the tray which best adopts the curvature of the patient automatically.The method developed here can also be used to design better tray shapes if it is applied to a greater number of casts representative of the general population. …”

mentioning

confidence: 99%

See 1 more Smart Citation

Image processing techniques for assessment of dental trays

Yergin

Ozturk

Şermet³

2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Abstract-A tray selected for the dental patient must adapt to the curvature of the teeth and allow the impression material to be in appropriate thickness everywhere.Generally, the impression trays are selected by the practitioner via testing them in the mouth. The present study was conducted to develop an automated technique for the selection of an appropriate tray for the patient. This technique was used for the alignment of six brands of perforated metal trays with 170 lower arch cast models collected from patients having Angle Class 1 type occlusion with minor malocclusions. The cast models and trays were scanned into a computer and critical points of casts and skeleton of the tray bases were collected. After alignment of casts and trays using a distance based alignment routine, the trays which most adopted the curvature of the casts were evaluated using the residual distance of alignment. The alignment was repeated for selected subsets of the points and minimum point set that is necessary for identification of the correct tray was identified. This method can be used in a routine setting eliminating trial and error or to design better trays to fit the needs of a given population. Keywords -Dentistry, tray, cast, distance based alignment I. INTRODUCTIONA dental cast is widely used in dentistry for working on dental prostheses. Due to the problems involved in working within the mouth, the tooth shape and position, which provide fundamental diagnostic information in dentistry, are generally measured in dental casts [1]. An accurate working cast is essential for making a crown or a fixed partial denture fit the abutment precisely [2].Accuracy of the impression is the most important factor for a successful prosthetic appliance. The thickness of the space between the tray and the preparation is one of the important factors related with the dimensional stability of the impression material. In the literature, the sufficient space for the impression material between the tray and the mucosa and teeth is recommended not to be less than two millimeters.The variable thickness of the impression material in each stock tray may result in dimensional changes and inaccuracies in the cast [3][4][5][6][7][8]. It is known that custom trays affect the prognosis of the prosthesis, however it is also known that standard trays are widely used [9]. The time and cost required to construct custom-made impression trays have channelled the manufacturers to provide quick and lessexpensive alternatives. Stock trays are useful for some procedures but their flexibility and construction vary [8]. Even tough the custom perforated trays demonstrate satisfactory results, a wide range of measurements indicate that the use of this type of tray does not guarantee predictable results [10].The ultimate effect of an expansion on the accuracy of the impression depends upon the general contour of the impression tray and the adhesion of material to the tray [11]. There are no scientific data and records about the principles used to produce the dentulous s...

show abstract

Accuracy and applications of group MEG studies using cortical source locations estimated from participants' scalp surfaces

Holliday¹,

Barnes²,

Hillebrand³

et al. 2003

Human Brain Mapping

View full text Add to dashboard Cite

We contend that powerful group studies can be conducted using magnetoencephalography (MEG), which can provide useful insights into the approximate distribution of the neural activity detected with MEG without requiring magnetic resonance imaging (MRI) for each participant. Instead, a participant's MRI is approximated with one chosen as a best match on the basis of the scalp surface from a database of available MRIs. Because large inter-individual variability in sulcal and gyral patterns is an inherent source of blurring in studies using grouped functional activity, the additional error introduced by this approximation procedure has little effect on the group results, and offers a sufficiently close approximation to that of the participants to yield a good indication of the true distribution of the grouped neural activity. T1-weighted MRIs of 28 adults were acquired in a variety of MR systems. An artificial functional image was prepared for each person in which eight 5 x 5 x 5 mm regions of brain activation were simulated. Spatial normalisation was applied to each image using transformations calculated using SPM99 with (1) the participant's actual MRI, and (2) the best matched MRI substituted from those of the other 27 participants. The distribution of distances between the locations of points using real and substituted MRIs had a modal value of 6 mm with 90% of cases falling below 12.5 mm. The effects of this approach on real grouped SAM source imaging of MEG data in a verbal fluency task are also shown. The distribution of MEG activity in the estimated average response is very similar to that produced when using the real MRIs.

show abstract

Multidimensional Alignment Using the Euclidean Distance Transform

Cited by 73 publications

References 17 publications

A New Variational Approach for 3d Shape Registration

A New Variational Approach for 3d Shape Registration

Image processing techniques for assessment of dental trays

Accuracy and applications of group MEG studies using cortical source locations estimated from participants' scalp surfaces

Contact Info

Product

Resources

About