Evaluation of image registration spatial accuracy using a Bayesian hierarchical model. (English) Zbl 1419.62397
Summary: To evaluate the utility of automated deformable image registration (DIR) algorithms, it is necessary to evaluate both the registration accuracy of the DIR algorithm itself, as well as the registration accuracy of the human readers from whom the “gold standard” is obtained. We propose a Bayesian hierarchical model to evaluate the spatial accuracy of human readers and automatic DIR methods based on multiple image registration data generated by human readers and automatic DIR methods. To fully account for the locations of landmarks in all images, we treat the true locations of landmarks as latent variables and impose a hierarchical structure on the magnitude of registration errors observed across image pairs. DIR registration errors are modeled using Gaussian processes with reference prior densities on prior parameters that determine the associated covariance matrices. We develop a Gibbs sampling algorithm to efficiently fit our models to high-dimensional data, and apply the proposed method to analyze an image dataset obtained from a 4D thoracic CT study.
MSC:
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62F15 | Bayesian inference |
| 62M30 | Inference from spatial processes |
| 92C55 | Biomedical imaging and signal processing |
References:
| [1] | Al‐Mayah, A., Moseley, J., and Brock, K. K. (2008). Contact surface and material nonlinearity modeling of human lungs. Physics in Medicine and Biology53, 305-317. |
| [2] | Berger, J. O., De Oliveira, V., and Sanso, B. (2001). Objective Bayesian analysis of spatially correlated data. Journal of the American Statistical Association96, 1361-1374. · Zbl 1051.62095 |
| [3] | Boldea, V., Sharp, G. C., Jiang, S. B., and Sarrut, D. (2008). 4D‐CT lung motion estimation with deformable registration: quantification of motion nonlinearity and hysteresis. Medical Physics35, 1008-1018. |
| [4] | Castillo, R., Castillo, E., Guerra, R., Johnson, V. E., McPhail, T., Garg, A. K., and Guerrero, T. (2009). A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets. Physics in Medicine and Biology54, 1849-1870. |
| [5] | Castillo, E., Castillo, R., Martinez, J., Shenoy, M., and Guerrero, T. (2010). Four‐dimensional deformable image registration using trajectory modelling. Physics in Medicine and Biology55, 305-327. |
| [6] | Gu, X., Pan, H., Liang, Y., Castillo, R., Yang, D., Choi, D., Castillo, E., Majumdar, A., GuerreroT., and Jiang, S. B. (2010). Implementation and evaluation of various demons deformable image registration algorithms on a GPU. Physics in Medicine and Biology55, 207-219. |
| [7] | Guerrero, T., Zhang, G., Huang, T. C., and Lin, K. P. (2004). Intrathoracic tumour motion estimation from CT imaging using the 3D optical flow method. Physics in Medicine and Biology49, 4147-4161. |
| [8] | Hof, H., Herfarth, K. K., Munter, M., Essig, M., Wannenmacher, M., and Debus, J. (2003). The use of the multislice CT for the determination of respiratory lung tumor movement in stereotactic single‐dose irradiation. Strahlentherapie und Onkologie179, 542-7. |
| [9] | HornB. K. P. and SchunckB. G. (1981). Determining optical flow. Artificial Intelligence17, 185-203. · Zbl 1497.68488 |
| [10] | Johnson, V. E. (2007). Bayesian model assessment using pivotal quantities. Bayesian Analysis2, 719-734. · Zbl 1331.62147 |
| [11] | Kabus, S., Klinder, T., Murphy, K., van Ginneken, B., Lorenz, C., and Pluim, J. (2009). Evaluation of 4D‐CT lung registration. Medical Image Computing and Computer‐Assisted Intervention12, 747-754. |
| [12] | Kaus, M. R., Brock, K. K., Pekar, V., Dawson, L. A., Nichol, A. M., and Jaffray, D. A. (2007). Assessment of a model‐based deformable image registration approach for radiation therapy planning. International Journal of Radiation Oncology Biology Physics68, 572-580. |
| [13] | Keall, P. (2004). Four‐dimensional computed tomography imaging and treatment planning. Seminars in Radiation Oncology14, 81-90. |
| [14] | Li, P., Malsch, U., and Bendl, R. (2008). Combination of intensity‐based image registration with 3D simulation in radiation therapy. Physics in Medicine and Biology53, 4621-4637. |
| [15] | Padhani, A. R. and Ollivier, L. (2001). The RECIST (Response Evaluation Criteria in Solid Tumors) criteria: Implications for diagnostic radiologists. British Journal of Radiology74, 983-6. |
| [16] | Paulo, R. (2005). Default priors for Gaussian process. The Annals of Statistics33, 556-582. · Zbl 1069.62030 |
| [17] | Sarrut, D. (2006). Deformable registration for image‐guided radiation therapy. Zeitschrift für Medizinische Physik16, 285-297. |
| [18] | Schaefer, S., McPhailT., and WarrenJ. (2006). Image Deformation Using Moving Least Squares. ACM SIGGRAPH 2006 Papers. Boston, MA: ACM Press. |
| [19] | Sherman, J. and Morrison, W. J. (1950). Adjustment of an inverse matrix corresponding to a change in one element of a given matrix. Annals of Mathematical Statistics21, 124-127. · Zbl 0037.00901 |
| [20] | Schnabel, J. A., Tanner, C., Castellano Smith, A. D., Degenhard, A., Leach, M. O., Hose, R., Hill, D. L. G., and Hawkes, D. J. (2003). Validation of non‐rigid image registration using finite element methods: Application to breast MR images. IEEE Transactions on Medical Imaging22, 238-247. |
| [21] | Vandemeulebroucke, J., Sarrut, D., and Clarysse, P. (2007). The POPI‐Model, a point validated pixel‐based breathing thorax model. International Conference on the Use of Computers in Radiation Therapy (ICCR), Toronto, Canada. |
| [22] | Wolthaus, J. W. H., Sonke, J. J., van HerkM., and DamenM. F. (2008). Reconstruction of a time‐averaged midposition CT scan for radiotherapy planning of lung cancer patients using deformable registration. Medical Physics35, 3998-4011. |
| [23] | Wu, Z., Rietzel, E., Boldea, V., SarrutD., and SharpG. C. (2008). Evaluation of deformable registration of patient lung 4D CT with subanatomical region segmentations. Medical Physics35, 775-781. |
| [24] | Xu, L., Johnson, T. D., Nichols, T. E., and Nee, D. E. (2009). Modeling inter‐subject variability in fMRI activation location: a Bayesian hierarchical spatial model. Biometrics65, 1041-1051. · Zbl 1181.62099 |
| [25] | Yuan, Y. and Johnson, V. E. (2012). Goodness‐of‐fit diagnostics for Bayesian hierarchical models. Biometrics68, 156-164. · Zbl 1241.62026 |
| [26] | Zhang, X., Johnson, T. D., Little, R. J. A., and Cao, Y. (2008). Quantitative magnetic resonance imaging via the EM algorithm with stochastic variation. Annals of Applied Statistics2, 736-755. · Zbl 1400.62301 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
