A protocol for evaluation of similarity measures for rigid registration
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
The accuracy and robustness of a registration method depend on a number of factors, such as imaging modality, image content and image degrading effects, the class of spatial transformation used for registration, similarity measure, optimization, and numerous implementation details. The complex interdependence of these factors makes the assessment of the influence of a particular factor on registration difficult, although it is often desirable to have some estimate of such influences prior to registration. The similarity measure used to create the cost function is one of the factors that most influences the quality of registration. Traditionally, limited information on the behavior of a similarity measure is obtained either by studying the quality of the final registration or by drawing plots of similarity measure values obtained by translating or rotating one image relative to the "gold standard." In this paper, we present a protocol for a more thorough, optimization-independent, and systematic statistical evaluation of similarity measures. This protocol estimates a similarity measure's capture range, the number, location and extent of local optima, and the accuracy and distinctiveness of the global optimum. To show that the proposed evaluation protocol is viable, we have conducted several experiments with nine similarity measures and real computed tomography and magnetic resonance (MR) images of a spine phantom, MR brain images, and MR and positron emission tomography brain images, for which "gold standard" registrations were available. We have also studied the impact of histogram bin size on the behavior of nine similarity measures. The proposed evaluation protocol is useful for selecting the best similarity measure and corresponding optimization method for a particular application, as well as for studying the influence of sampling, interpolation, histogram bin size, partial image overlap, and image degradation, such as noise, intensity inhomogeneity, and geometrical distortions on the behavior of a similarity measure.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Nonrigid registration using free-form deformations: application to breast mr images
Rueckert, D., Sonoda, L. I., Hayes, C., Hill, D. L. G., Leach, M. O., & Hawkes, D. J. (1999) · IEEE Transactions on Medical Imaging · doi:10.1109/42.796284 · Cited by 5,265 · cited 1×
“Most often, however, thin-plate splines (Bookstein, 1989) and B-splines (Rueckert et al., 1999; Unser, 1999) were used.”
Multimodality image registration by maximization of mutual information
Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., & Suetens, P. (1997) · IEEE Transactions on Medical Imaging · doi:10.1109/42.563664 · Cited by 4,547 · cited 6×
“More directly, in order to exclude the impact of optimization, similarity measures may be evaluated by drawing plots or traces, showing their behavior when one image is systematically translated from and/or rotated relative to the “gold standard” registration position [2], [29], [31]–[35].”
BackgroundMethodInfluentialValidation of medical image processing in image-guided therapy
Jannin, P., Fitzpatrick, J. M., Hawkes, D. J., Pennec, X., Shahidl, R., & Vannier, M. W. (2002) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2002.806568 · Cited by 177 · cited 1×
“Robustness is the ability of a registration method to produce similar results on all trials [14], i.”
Result“Gold standard” data for evaluation and comparison of 3D/2D registration methods
Tomaževič, D., Likar, B., & Pernuš, F. (2004) · Computer Aided Surgery · doi:10.3109/10929080500097687 · Cited by 40 · cited 1×
“Rigid ‘‘gold standard’’ registrations for this set of real images were obtained by fiducial marker registration (Tomaževič et al., 2004).”
Self-citation“Gold Standard” 2D/3D Registration of X-Ray to CT and MR Images
Tomaevič, D., Likar, B., & Pernuš, F. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-45787-9_58 · Cited by 9 · cited 1×
“• Set 2 [9][43]: MR T1 volume of interest (VOI) (238 238 22 voxels, 8 bits) containing vertebra L3 of a lumbar spine phantom and the CT image (512 512 233 voxels, 8 bits) of the L1-L5 segment (Fig.”
BackgroundSelf-citation
Cited by
Brain Functional Localization: A Survey of Image Registration Techniques
Gholipour, A., Kehtarnavaz, N., Briggs, R., Devous, M., & Gopinath, K. (2007) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2007.892508 · Cited by 274
De Silva, T., Uneri, A., Ketcha, M. D., Reaungamornrat, S., Kleinszig, G., Vogt, S., Aygun, N., Lo, S.-F., Wolinsky, J.-P., & Siewerdsen, J. H. (2016) · Physics in Medicine & Biology · doi:10.1088/0031-9155/61/8/3009 · Cited by 116
“The profiles were normalized such that a unit change in all the transform directions (i.e. both rotations and translations) cause the same mean shift in physical dimensions in the image (Škerl et al 2006).”
BackgroundGendrin, C., Markelj, P., Pawiro, S. A., Spoerk, J., Bloch, C., Weber, C., Figl, M., Bergmann, H., Birkfellner, W., Likar, B., et al. (2011) · Medical Physics · doi:10.1118/1.3553403 · Cited by 38
Self-citationSo, R. W. K., & Chung, A. C. S. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.09.004 · Cited by 36
Accurate and precise 2D–3D registration based on X-ray intensity
Aouadi, S., & Sarry, L. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.05.006 · Cited by 30
“To evaluate them separately, a recent study [32] has defined an optimization-independent protocol for systematic evaluation of SM.”
Method
Metadata
- Authors
- Skerl, D., Likar, B., & Pernus, F.
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2006-06
- Volume
- 25
- Issue
- 6
- Pages
- 779-791
- ISSN
- 0278-0062 (ISSN-L)
- OpenAlex
- W2097840056
- Cited by
- 94
- References
- 5
- FWCI
- 12.94
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.