&lt;title&gt;Grey value correlation techniques used for automatic matching of CT and MR brain and spine images&lt;/title&gt;

Elsen, Petra A. van den; Pol, Evert-Jan D.; Sumanaweera, Thilaka S.; Hemler, Paul F.; Napel, Sandy; Adler, John R.

doi:10.1117/12.185182

Cited by 52 publications

(36 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [7,9] these structures were extracted using complex dierential operators in scale-space. Similar results were later obtained using simple ramp intensity remapping in [8].…”

Section: Voxel Similarity Measuressupporting

confidence: 82%

See 1 more Smart Citation

Rigid registration of CT, MR and cryosection images using a GLCM framework

Bro-Nielsen

1997

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The majority of the available rigid registration measures are based on a 2-dimensional histogram of corresponding grey-values in the registered images. This paper shows that these features are similar to a family of texture measures based on Grey Level Cooccurrence Matrices (GLCM). Features from the GLCM literature are compared to the current range of measures using images from the visible human data set. The voxel-based rigid registration of Cryosection and CT images have not been reported before. The tests show that mutual information is the best general measure, but some GLCM features are better for specic modality combinations. This paper discusses existing and some new voxel similarity measures for image registration. Elaborate tests are used to evaluate the dierent measures and compare them. Finally, a registration algorithm based on voxel similarity measures is described and some results are presented.

show abstract

“…In [7,9] these structures were extracted using complex dierential operators in scale-space. Similar results were later obtained using simple ramp intensity remapping in [8].…”

Section: Voxel Similarity Measuressupporting

confidence: 82%

“…Van den Elsen has proposed a modied correlation approach for CT/MR registration [7,8,9], where the images are pre-processed to extract similar structures in both modalities, typically bones. In [7,9] these structures were extracted using complex dierential operators in scale-space.…”

Section: Voxel Similarity Measuresmentioning

confidence: 99%

Rigid registration of CT, MR and cryosection images using a GLCM framework

Bro-Nielsen

1997

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…An alternative approach is to derive measures from (the spatial distribution of) the respective voxel intensities of each data set, which are then employed as parameters for registration methods. (7)(8)(9)(10)(11)(12)(13)(14) Studholme et al (16) compared four such similarity measures and concluded that measures of soft tissue correlation (11) and mutual information (13,14) provided robust solutions for the registration of 3D CT and MR data sets. Freire et al (22) also demonstrated the robustness of the Geman-McClure estimator in a comprehensive study of several intensity-based measures.…”

Section: Discussionmentioning

confidence: 99%

“…An alternative approach is to calculate the transformation from one data set to another by correlating the intensity values of corresponding voxels. (7)(8)(9)(10)(11)(12) One such mathematical procedure is called mutual information and is proposed to optimize the correlation of these intensities and calculate the desired 3D transformation for image registration. (13,14) Studholme et al (15,16) demonstrated the utilization of this method in a clinical setting.…”

Section: Introductionmentioning

confidence: 99%

Clinical validation of the normalized mutual information method for registration of CT and MR images in radiotherapy of brain tumors

Veninga¹,

Huisman²,

Maazen³

et al. 2004

J. Appl. Clin. Med. Phys.

View full text Add to dashboard Cite

Image registration integrates information from different imaging modalities and has the potential to improve determination of target volume in radiotherapy planning. This paper describes the implementation and validation of a 3D fully automated registration procedure in the process of radiotherapy treatment planning of brain tumors. Fifteen patients with various brain tumors received computed tomography (CT) and magnetic resonance (MR) brain imaging before the start of radiotherapy. First, the normalized mutual information (NMI) method was used for image registration. Registration accuracy was estimated by performing statistical analysis of coordinate differences between CT and MR anatomical landmarks along the x-, y-and zaxes. Second, a visual validation protocol was developed to validate the quality of individual registration solutions, and this protocol was tested in a series of 36 CT-MR registration procedures with intentionally applied registration errors. The mean coordinate differences between CT and MR landmarks along the x-and y-axes were in general within 0.5 mm. The mean coordinate differences along the z-axis were within 1.0 mm, which is of the same magnitude as the applied slice thickness in scanning. In addition, the detection of intentionally applied registration errors by employment of a standardized visual validation protocol resulted in low false-negative and low false-positive rates. Application of the NMI method for the brain results in excellent automatic registration accuracy, and the method has been incorporated into the daily routine at our institution. A standardized validation protocol ensures the quality of individual registrations by detecting registration errors with high sensitivity and specificity. This protocol is proposed for the validation of other linear registration methods.

show abstract

“…Surface-based registrations were performed by Barillot and Lemoine [11]; Harkness [22]; Hemler et al [7] (CT-to-MR only); Pelizzari [22]; and Robb and Hanson [9], [10] (four techniques for CT-to-MR, two of which were also applied in PET-to-MR). Volume-based registrations were performed by Collignon et al [4]; Van den Elsen et al [24] (CT-to-MR only); Hill and Studholme [23]; Maintz et al [13], [14], [15]; and Woods [28] (two techniques, PET-to-MR only). Two sites which contributed registrations to the original study are not included here.…”

Section: G Retrospective Techniquesmentioning

confidence: 99%

Retrospective intermodality registration techniques: Surface-based versus volume-based

West

Fitzpatrick

Wang

et al. 1997

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract-The primary objective of this study is to perform a blinded evaluation of two groups of retrospective image registration techniques, using as a gold standard a prospective markerbased registration method, and to compare the performance of one group with the other. These techniques have already been evaluated individually [27]. In this paper, however, we find that by grouping the techniques as volume based or surface based, we can make some interesting conclusions which were not visible in the earlier study. In order to ensure blindness, all retrospective registrations were performed by participants who had no knowledge of the gold-standard results until after their results had been submitted. Image volumes of three modalities: X-ray computed tomography (CT), magnetic resonance (MR), and positron emission tomography (PET) were obtained from patients undergoing neurosurgery at Vanderbilt University Medical Center on whom bone-implanted fiducial markers were mounted. These volumes had all traces of the markers removed and were provided via the Internet to project collaborators outside Vanderbilt, who then performed retrospective registrations on the volumes, calculating transformations from CT to MR and/or from PET to MR. These investigators communicated their transformations, again via the Internet, to Vanderbilt, where the accuracy of each registration was evaluated. In this evaluation, the accuracy is measured at multiple volumes of interest (VOI's). Our results indicate that the volume-based techniques in this study tended to give substantially more accurate and reliable results than the surface-based ones for the CT-to-MR registration tasks, and slightly more accurate results for the PET-to-MR tasks. Analysis of these results revealed that the rotational component of error was more pronounced for the surface-based group. It was also apparent that all of the registration techniques we examined have the potential to produce satisfactory results much of the time, but that visual inspection is necessary to guard against large errors.Index Terms-Computed tomography, image registration, magnetic resonance, positron emission tomography, surfacebased versus volume-based.

show abstract

<title>Grey value correlation techniques used for automatic matching of CT and MR brain and spine images</title>

Cited by 52 publications

References 0 publications

Rigid registration of CT, MR and cryosection images using a GLCM framework

Rigid registration of CT, MR and cryosection images using a GLCM framework

Clinical validation of the normalized mutual information method for registration of CT and MR images in radiotherapy of brain tumors

Retrospective intermodality registration techniques: Surface-based versus volume-based

Contact Info

Product

Resources

About