Weight Preserving Image Registration for Monitoring Disease Progression in Lung CT

Gorbunova, Vladlena; Lo, Pechin; Ashraf, Haseem; Dirksen, Asger; Nielsen, Mads; Bruijne, Marleen de

doi:10.1007/978-3-540-85990-1_104

Cited by 37 publications

(26 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper we used a multi-resolution image registration framework similar to the framework developed in [9]. First, lung regions were extracted from the CT images and the background value was set to 0 HU.…”

Section: Intensity-based Registration Via Bsplinesmentioning

confidence: 99%

Lung CT registration combining intensity, curves and surfaces

Gorbunova

Durrleman

et al. 2010

2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

Self Cite

View full text Add to dashboard Cite

In this paper we propose a registration method that combines intensity information with geometrical information in the form of curves and surfaces derived from lung CT images. Vessel tree centerlines and lung surfaces were extracted from segmented structures. First, a current-based registration was applied to align the pulmonary vessel tree and the lung surfaces. Subsequently, the resulting deformation field was used to constrain an intensity-based registration method. We applied the combined registration on a set of image pairs, extracted at the end exhale and the end inhale phases of 4D-CT scans. The proposed combined registration was compared to intensity-based registration, using a set of manually selected landmarks. The proposed registration decreases the mean and the standard deviation of the target registration errors for all 5 cases to on average 1.47±1.05 mm, compared to the intensity-based registration without constraint 1.74 ± 1.31 mm.Index Terms-Image registration, BSplines, currents, lung CT. INTRODUCTIONThe ultimate goal of any registration algorithm is to establish dense point-to-point correspondence between two images. Generally, registration of lung CT images is a difficult problem due to the possible large variation between the scans. Scans of the same patient taken at maximum inspiration, can have more than 0.5 liter difference in lung volume. The registration of end exhale and end inhale phases of 4D-CT lung images is an even more difficult problem due to the large and non-uniform deformations during the breathing cycle [1].Image registration methods can be divided into two groups of methods: intensity-based and feature-based. A feature-based method establishes deformations based on lowdimensional features, derived from the original images, while * This work is financially supported by the Danish Council for Strategic Research under the Programme Commission for Nanoscience and Technology, Biotechnology and IT (NABIIT), the Netherlands Organization for Scientific Research (NWO), and AstraZeneca, Lund, Sweden. Authors would like to thank Jon Sporring, Copenhagen University, Department of Computer Science, eScience Center, for fruitful discussions.intensity-based method considers intensity information over complete image. The state-of-the art registration methods for lung CT images are mainly intensity-based approaches [2] because the feature-based methods generally produce less accurate results [3].Recently, Li et al. [4] developed an image registration algorithm where the intensity-based registration was improved with the subsequent bio-mechanical simulation of lung inflation. Results showed an improvement in both accuracy of registration and physical plausibility of the deformation field for the combined approach. We previously developed a feature-based algorithm for registering lung CT images and compared it to intensity-based registration [5]. The overall accuracy of the feature-based algorithm was slightly worse than that of the intensity-based algorithm, but in 35 % of landmarks t...

show abstract

Section: Intensity-based Registration Via Bsplinesmentioning

confidence: 99%

Lung CT registration combining intensity, curves and surfaces

Gorbunova

Durrleman

et al. 2010

2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, these metrics do not consider the local image structure, which may influence the robustness of non-rigid registration 3 . Several methods have integrated features of the local structure into the similarity metric 3,4,5 to improve the registration performance. Alternatively, the so-called MIND 6 , DRAMMS 7 and ROHE 8 techniques determine structural properties of image patches and apply a simple (dis)similarity metric (e.g.…”

Section: Introductionmentioning

confidence: 99%

Image registration based on the structure tensor of the local phase

Vliet

Stoker

et al. 2015

SPIE Proceedings

View full text Add to dashboard Cite

Image registration of medical images in the presence of large intra-image signal fluctuations is a challenging task. Our paper addresses this problem by introducing a new concept based on the structure tensor of the local phase. The local phase is calculated from the monogenic signal representation of the images. The local phase image is hardly affected by unwanted signal fluctuations due to a space-variant background and a space-variant contrast. The boundary structure tensor combines the responses of edges and corners/junctions in one tensor, which has several advantages, compared to other structure tensors. We reorient the structure tensor during the registration by means of the finite-strain technique. The structure tensor is only calculated once during a preprocessing step. The results demonstrate that the proposed method effectively deals with large signal fluctuations. It performs significantly better than competing techniques.

show abstract

“…To date, a number of papers have proposed techniques for non-rigid lung motion estimation [17,55,105,108,136,198]. Previously proposed techniques most often have employed elastic registration with specific modifications [25,76,105,108,125,148,167], such as incorporation of mass conservation [51,198], or employing respiratory lung motion hysteresis [II]. A useful classification scheme for the intensity and geometric lung registration techniques is based on the two common quantitative measures similarity and smoothness [98,108,146,148,167,180,202].…”

Section: Deformable Lung Registration Methodsmentioning

confidence: 99%

“…In order to take into account changes in the voxel intensity with inflation, some authors have used the sum of squared tissue volume difference (SSTVO) as the similarity criterion [197,198]. An alternative approach has been to apply the principle of mass conservation; this has now been adopted by a number of researchers [18,51,52,116,[118][119][120][121]198].…”

Section: Deformable Lung Registration Methodsmentioning

confidence: 99%

See 1 more Smart Citation

3-D lung deformation and function from respiratory-gated 4-D x-ray CT images : application to radiation treatment planning.

Negahdar

View full text Add to dashboard Cite

show abstract

Weight Preserving Image Registration for Monitoring Disease Progression in Lung CT

Cited by 37 publications

References 11 publications

Lung CT registration combining intensity, curves and surfaces

Lung CT registration combining intensity, curves and surfaces

Image registration based on the structure tensor of the local phase

3-D lung deformation and function from respiratory-gated 4-D x-ray CT images : application to radiation treatment planning.

Contact Info

Product

Resources

About