A gradient feature weighted Minimax algorithm for registration of multiple portal images to 3DCT volumes in prostate radiotherapy.

PURPOSE To develop an accurate, fast, and robust algorithm for registering portal and computed tomographic (CT) images for radiotherapy using a combination of sparse and dense field data that complement each other. METHODS AND MATERIALS Gradient Feature Weighted Minimax (GFW Minimax) method was developed to register multiple portal images to three-dimensional CT images. Its performance was compared with that of three others: Minimax, Mutual Information, and Gilhuijs' method. Phantom and prostate cancer patient images were used. Effects of registration errors on tumor control probability (TCP) and normal tissue complication probability (NTCP) were investigated as a relative measure. RESULTS Registration of four portals to CTs resulted in 30% lower error when compared with registration with two portals. Computation time increased by nearly 50%. GFW Minimax performed the best, followed by Gilhuijs' method, the Minimax method, and Mutual Information. CONCLUSIONS Using four portals instead of two lowered the registration error. Reduced fields of view images with full feature sets gave similar results in shorter times as full fields of view images. In clinical situations where soft tissue targets are of importance, GFW Minimax algorithm was significantly more accurate and robust. With registration errors lower than 1 mm, margins may be scaled down to 4 mm without adversely affecting TCP and NTCP.

[1]  J. Leong,et al.  Implementation of random positioning error in computerised radiation treatment planning systems as a result of fractionation. , 1987, Physics in medicine and biology.

[2]  M Goitein,et al.  Implementation of a model for estimating tumor control probability for an inhomogeneously irradiated tumor. , 1993, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[3]  Zhe Chen,et al.  A Novel Approach for the Registration of 2D Portal and 3D CT Images for Treatment Setup Verification in Radiotherapy , 1998, MICCAI.

[4]  Max A. Viergever,et al.  Image registration by maximization of combined mutual information and gradient information , 2000, IEEE Transactions on Medical Imaging.

[5]  D. R. Fish,et al.  A patient-to-computed-tomography image registration method based on digitally reconstructed radiographs. , 1994, Medical physics.

[6]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[7]  G T Chen,et al.  A comparison of four patient immobilization devices in the treatment of prostate cancer patients with three dimensional conformal radiotherapy. , 1996, International journal of radiation oncology, biology, physics.

[8]  Nicholas Ayache,et al.  Rigid registration of 3-D ultrasound with MR images: a new approach combining intensity and gradient information , 2001, IEEE Transactions on Medical Imaging.

[9]  J H Hendry,et al.  A realistic closed-form radiobiological model of clinical tumor-control data incorporating intertumor heterogeneity. , 1998, International journal of radiation oncology, biology, physics.

[10]  J Knisely,et al.  A minimax entropy registration framework for patient setup verification in radiotherapy. , 1999, Computer aided surgery : official journal of the International Society for Computer Aided Surgery.

[11]  A Boxwala,et al.  Core-based portal image registration for automatic radiotherapy treatment verification. , 1995, International journal of radiation oncology, biology, physics.

[12]  Sayan Mukherjee,et al.  Support Vector Method for Multivariate Density Estimation , 1999, NIPS.

[13]  A. Izenman.  Review Papers: Recent Developments in Nonparametric Density Estimation , 1991 .

[14]  J C Stroom,et al.  Internal organ motion in prostate cancer patients treated in prone and supine treatment position. , 1999, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[15]  A. Izenman.  Recent Developments in Nonparametric Density Estimation , 1991 .

[16]  M van Herk,et al.  Automatic on-line inspection of patient setup in radiation therapy using digital portal images. , 1993, Medical physics.

[17]  J. Lyman.  Complication Probability as Assessed from Dose-Volume Histograms , 1985 .

[18]  Guido Gerig,et al.  Motion Measurements in Low-Contrast X-ray Imagery , 1998, MICCAI.

[19]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[20]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  James S. Duncan,et al.  Support Vector Machine Density Estimator as a Generalized Parzen Windows Estimator for Mutual Information based Image Registration , 2003, MICCAI.

[22]  Joos V Lebesque,et al.  Inclusion of geometric uncertainties in treatment plan evaluation. , 2002, International journal of radiation oncology, biology, physics.

[23]  K W Leszczynski,et al.  An image registration scheme applied to verification of radiation therapy. , 1998, The British journal of radiology.

[24]  J. Adler,et al.  CyberKnife Radiotherapy for Localized Prostate Cancer: Rationale and Technical Feasibility , 2003, Technology in cancer research & treatment.

[25]  M van Herk,et al.  Quantification of organ motion during conformal radiotherapy of the prostate by three dimensional image registration. , 1995, International journal of radiation oncology, biology, physics.

[26]  L. Beckett,et al.  Survival and cell cycle kinetics of human prostate cancer cell lines after single- and multifraction exposures to ionizing radiation. , 2004, International journal of radiation oncology, biology, physics.

[27]  G T Chen,et al.  Correlation of projection radiographs in radiation therapy using open curve segments and points. , 1992, Medical physics.

[28]  C. Ling,et al.  Analysis of biopsy outcome after three-dimensional conformal radiation therapy of prostate cancer using dose-distribution variables and tumor control probability models. , 2000, International journal of radiation oncology, biology, physics.

[29]  A. Hanlon,et al.  The relationship of increasing radiotherapy dose to reduced distant metastases and mortality in men with prostate cancer , 2004, Cancer.

[30]  D. Dearnaley,et al.  Comparison of radiation side-effects of conformal and conventional radiotherapy in prostate cancer: a randomised trial , 1999, The Lancet.

[31]  G Hilt,et al.  Preprocessing of control portal images for patient setup verification during the treatments in external radiotherapy. , 1999, Medical physics.

[32]  B G Fallone,et al.  A grey-level image alignment algorithm for registration of portal images and digitally reconstructed radiographs. , 1996, Medical physics.

[33]  M van Herk,et al.  Automatic three-dimensional inspection of patient setup in radiation therapy using portal images, simulator images, and computed tomography data. , 1996, Medical physics.

[34]  Serge Miguet,et al.  Patient setup error measurement using 3D intensity-based image registration techniques. , 2003, International journal of radiation oncology, biology, physics.

[35]  A L Boyer,et al.  An image correlation procedure for digitally reconstructed radiographs and electronic portal images. , 1995, International journal of radiation oncology, biology, physics.

[36]  Zhe Chen,et al.  Entropy-based dual-portal-to-3-DCT registration incorporating pixel correlation , 2003, IEEE Transactions on Medical Imaging.

[37]  Cristian Lorenz,et al.  2D/3D registration of pre-operative CT images and intra-operative X-ray projections for image guided surgery , 1997 .

[38]  Frans Vos,et al.  An evaluation of ridge extraction methods for portal imaging , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[39]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.