An efficient locally affine framework for the smooth registration of anatomical structures

Commowick, Olivier; Arsigny, Vincent; Isambert, A.; Costa, J. M. N. da; Dhermain, Frédéric; Bidault, François; Bondiau, Pierre‐Yves; Ayache, Nicholas; Malandain, Grégoire

doi:10.1016/j.media.2008.01.002

Cited by 60 publications

(54 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Polyaffine transformations were introduced in Arsigny et al (2005) to fuse locally rigid and affine transformations into a diffeomorphism, and revisited in Arsigny et al (2009) to obtain faster numerical algorithms. An efficient registration algorithm using approximations of polyaffine transformations was presented in Commowick et al (2008). In Martín-Fernández et al (2009) an extension to articulated structures was presented, which considers weights (defining the influence of each region) fixed at landmark positions along a manually defined skeleton.…”

Section: Methodological Frameworkmentioning

confidence: 99%

“…In practice, this results in computations of these logarithms via matrix logarithms. The practical relevance of this theoretical reformulation of the problem was exploited in Commowick et al (2008). In a first step, block-matching was used to estimate each affine transformation for a predefined region.…”

Section: Projection Of Stationary Velocity Fields Onto the Linear Spamentioning

confidence: 99%

See 1 more Smart Citation

Capturing the multiscale anatomical shape variability with polyaffine transformation trees

Seiler¹,

Pennec²

2012

Medical Image Analysis

View full text Add to dashboard Cite

Section: Methodological Frameworkmentioning

confidence: 99%

Section: Projection Of Stationary Velocity Fields Onto the Linear Spamentioning

confidence: 99%

Capturing the multiscale anatomical shape variability with polyaffine transformation trees

Seiler¹,

Pennec²

2012

Medical Image Analysis

View full text Add to dashboard Cite

“…Registration using locally affine transformations is an attractive registration alternative for applications where a single global affine transformation cannot provide enough accuracy, while a nonrigid registration would incorrectly affect the local topology due to the large shape variability of the heart anatomy [23]- [26]. An affine transformation is also challenged to provide a good initialization of substructures of the heart for a nonrigid registration with high degrees of freedom (DOFs).…”

Section: A Larm: Locally Affine Registration Methodsmentioning

confidence: 99%

A Registration-Based Propagation Framework for Automatic Whole Heart Segmentation of Cardiac MRI

Zhuang

Rhode

Razavi

et al. 2010

IEEE Trans. Med. Imaging

189

View full text Add to dashboard Cite

Abstract-Magnetic resonance (MR) imaging has become a routine modality for the determination of patient cardiac morphology. The extraction of this information can be important for the development of new clinical applications as well as the planning and guidance of cardiac interventional procedures. To avoid inter-and intra-observer variability of manual delineation, it is highly desirable to develop an automatic technique for whole heart segmentation of cardiac magnetic resonance images. However, automating this process is complicated by the limited quality of acquired images and large shape variation of the heart between subjects. In this paper, we propose a fully automatic whole heart segmentation framework based on two new image registration algorithms: the locally affine registration method (LARM) and the free-form deformations with adaptive control point status (ACPS FFDs). LARM provides the correspondence of anatomical substructures such as the four chambers and great vessels of the heart, while the registration using ACPS FFDs refines the local details using a constrained optimization scheme. We validated our proposed segmentation framework on 37 cardiac MR volumes on the end-diastolic phase, displaying a wide diversity of morphology and pathology, and achieved a mean accuracy of 2.14 0.63 mm (rms surface distance) and a maximal error of 4.31 mm.Index Terms-Atlas, cardiac magnetic resonance imaging (MRI), dynamic resampling and distance weighting interpolation (DRAW), free-form deformations, image registration, inverse transformation, locally affine registration, locally affine registration method (LARM), whole heart segmentation.

show abstract

“…In t r from one coor mation matrice es, so that lines nsional compu tient registratio e image with th registration of cquisitions, wit key aspects on d [2] . In particul urgical instrum ng them (see Fi [8,9] and smart are potentially u intelligence ha for different p mage fusion be ent rigid regist uation works ha d because of th stration algorit CT to MRI) [16] natomy placed o d. In general, u of applications s been reporte tion in space an ra-operative ra ue is represente n the early futu ugmented reality the first case, th rdinates system s for 3D to 3D s are mapped to ted tomograph on the goal is to he correspondi f virtual pre-op th real intra-op which effectiv ar, the registra ments) allows igure 1) [3][4][5][6][7] , s mechatronics d useful in terms ave been devel positioning of t etween the sour tration is used ave been perfo he not-rigid nat thms produce g . Their applica on the surgical using intra-ope s that do not req d by Hawkes e nd also in time, adiological sca ed by the low a ure at least for system at work J he distance bet m to another.…”

Section: Introductionmentioning

confidence: 99%

Analytic description of the image to patient torso registration problem in image guided interventions

Ferrari

Moglia

Ferrari

2015

JBEI

View full text Add to dashboard Cite

Objective: The accurate registration of virtual pre-operative information of the human body anatomy, obtained as images with imaging devices, with real intra-operative information is one of the key aspects on which effective Image Guided Surgery (IGS) is based. The registration of pre-operative images on the real patient, during abdominal and thoracic interventions, is influenced by many parameters, which in many cases are influenced each other, thus making it often difficult to define the problem and consequently to solve it for each specific kind of intervention. The objective of this paper is to obtain an analytic description of the 3D image to patient registration problem, which can be more intuitive than the traditional textual descriptions. Methods:The problem is formalized and various parameters affecting the registration are macro-classified in function of their nature.Results: The problem is analytically described discussing for each macro-category of parameters potential solutions to avoid or to reduce their contribution to the registration error. Conclusions:The availability of an analytic description of the image to patient torso registration problem can be beneficial for teaching IGS, to describe existing registration strategies, and to search new ones for each kind of surgery using a systematic approach.

show abstract

An efficient locally affine framework for the smooth registration of anatomical structures

Cited by 60 publications

References 39 publications

Capturing the multiscale anatomical shape variability with polyaffine transformation trees

Capturing the multiscale anatomical shape variability with polyaffine transformation trees

A Registration-Based Propagation Framework for Automatic Whole Heart Segmentation of Cardiac MRI

Analytic description of the image to patient torso registration problem in image guided interventions

Contact Info

Product

Resources

About