A method to detect landmark pairs accurately between intra‐patient volumetric medical images

Purposes: An image processing procedure was developed in this study to detect large quantity of landmark pairs accurately in pairs of volumetric medical images. The detected landmark pairs can be used to evaluate of deformable image registration (DIR) methods quantitatively. Methods: Landmark detection and pair matching were implemented in a Gaussian pyramid multi‐resolution scheme. A 3D scale‐invariant feature transform (SIFT) feature detection method and a 3D Harris–Laplacian corner detection method were employed to detect feature points, i.e., landmarks. A novel feature matching algorithm, Multi‐Resolution Inverse‐Consistent Guided Matching or MRICGM, was developed to allow accurate feature pairs matching. MRICGM performs feature matching using guidance by the feature pairs detected at the lower resolution stage and the higher confidence feature pairs already detected at the same resolution stage, while enforces inverse consistency. Results: The proposed feature detection and feature pair matching algorithms were optimized to process 3D CT and MRI images. They were successfully applied between the inter‐phase abdomen 4DCT images of three patients, between the original and the re‐scanned radiation therapy simulation CT images of two head‐neck patients, and between inter‐fractional treatment MRIs of two patients. The proposed procedure was able to successfully detect and match over 6300 feature pairs on average. The automatically detected landmark pairs were manually verified and the mismatched pairs were rejected. The automatic feature matching accuracy before manual error rejection was 99.4%. Performance of MRICGM was also evaluated using seven digital phantom datasets with known ground truth of tissue deformation. On average, 11855 feature pairs were detected per digital phantom dataset with TRE = 0.77 ± 0.72 mm. Conclusion: A procedure was developed in this study to detect large number of landmark pairs accurately between two volumetric medical images. It allows a semi‐automatic way to generate the ground truth landmark datasets that allow quantitatively evaluation of DIR algorithms for radiation therapy applications.

[1]  N. Kadoya,et al.  Use of Deformable Image Registration for Radiotherapy Applications , 2014 .

[2]  Paul M. Thompson,et al.  Inverse Consistent Mapping in 3D Deformable Image Registration: Its Construction and Statistical Properties , 2005, IPMI.

[3]  Jayashree Kalpathy-Cramer,et al.  Prospective assessment of an atlas-based intervention combined with real-time software feedback in contouring lymph node levels and organs-at-risk in the head and neck: Quantitative assessment of conformance to expert delineation. , 2013, Practical radiation oncology.

[4]  Dinggang Shen,et al.  Reconstruction of 4D-CT from a Single Free-Breathing 3D-CT by Spatial-Temporal Image Registration , 2011, IPMI.

[5]  Jan Seuntjens,et al.  4D dose-position verification in radiation therapy using the RADPOS system in a deformable lung phantom. , 2010, Medical physics.

[6]  Lei Dong,et al.  Automatic segmentation of whole breast using atlas approach and deformable image registration. , 2009, International journal of radiation oncology, biology, physics.

[7]  Xiaodong Zhang,et al.  A 4D IMRT planning method using deformable image registration to improve normal tissue sparing with contemporary delivery techniques , 2011, Radiation oncology.

[8]  I. Chetty,et al.  A novel approach for establishing benchmark CBCT/CT deformable image registrations in prostate cancer radiotherapy , 2013, Physics in medicine and biology.

[9]  Xavier Geets,et al.  Adaptive radiotherapy of head and neck cancer. , 2010, Seminars in radiation oncology.

[10]  Rolf Bendl,et al.  Accuracy quantification of a deformable image registration tool applied in a clinical setting , 2014, Journal of applied clinical medical physics.

[11]  Indrin J Chetty,et al.  Analysis of deformable image registration accuracy using computational modeling. , 2010, Medical physics.

[12]  K. Brock,et al.  Demons deformable registration for CBCT-guided procedures in the head and neck: convergence and accuracy. , 2009, Medical physics.

[13]  Sasa Mutic,et al.  SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization. , 2015, Medical physics.

[14]  B. Gino Fallone,et al.  Assessment of a commercially available automatic deformable registration system , 2010, Journal of applied clinical medical physics.

[15]  G. Sharp,et al.  Vision 20/20: perspectives on automated image segmentation for radiotherapy. , 2014, Medical physics.

[16]  Ives Rey-Otero,et al.  Anatomy of the SIFT Method , 2014, Image Process. Line.

[17]  Arno Klein,et al.  Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration , 2009, NeuroImage.

[18]  Ryan L. Smith,et al.  Performance of 12 DIR algorithms in low-contrast regions for mass and density conserving deformation. , 2013, Medical physics.

[19]  Amit Sawant,et al.  An externally and internally deformable, programmable lung motion phantom. , 2015, Medical physics.

[20]  Geoffrey G. Zhang,et al.  Validation of three deformable image registration algorithms for the thorax , 2013, Journal of applied clinical medical physics.

[21]  Robert J W Louwe,et al.  Validation of Varian’s SmartAdapt® deformable image registration algorithm for clinical application , 2015, Radiation Oncology.

[22]  Max A. Viergever,et al.  Semi-automatic construction of reference standards for evaluation of image registration , 2011, Medical Image Anal..

[23]  Ye Duan,et al.  An Ensemble Approach to Image Matching Using Contextual Features , 2015, IEEE Transactions on Image Processing.

[24]  Karl J. Friston,et al.  Image registration using a symmetric prior—in three dimensions , 1999, Human brain mapping.

[25]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[26]  Wei Lu,et al.  4D-CT motion estimation using deformable image registration and 5D respiratory motion modeling. , 2008, Medical physics.

[27]  Wolfgang A Tomé,et al.  The utilization of consistency metrics for error analysis in deformable image registration , 2009, Physics in medicine and biology.

[28]  Shunshan Li,et al.  Voxel-based statistical analysis of uncertainties associated with deformable image registration. , 2013, Physics in medicine and biology.

[29]  Xavier Geets,et al.  Assessment by a deformable registration method of the volumetric and positional changes of target volumes and organs at risk in pharyngo-laryngeal tumors treated with concomitant chemo-radiation. , 2010, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[30]  R. Cormack,et al.  Automatic online adaptive radiation therapy techniques for targets with significant shape change: a feasibility study , 2006, Physics in medicine and biology.

[31]  Michael Velec,et al.  A novel technique to enable experimental validation of deformable dose accumulation. , 2012, Medical physics.

[32]  T Kron,et al.  Is it sensible to "deform" dose? 3D experimental validation of dose-warping. , 2012, Medical physics.

[33]  Maarten L P Dirkx,et al.  Does atlas-based autosegmentation of neck levels require subsequent manual contour editing to avoid risk of severe target underdosage? A dosimetric analysis. , 2011, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[34]  Tony Lindeberg,et al.  Scale Selection Properties of Generalized Scale-Space Interest Point Detectors , 2012, Journal of Mathematical Imaging and Vision.

[35]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[36]  Thomas Guerrero,et al.  A reference dataset for deformable image registration spatial accuracy evaluation using the COPDgene study archive , 2013, Physics in medicine and biology.

[37]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[38]  Joseph O. Deasy,et al.  Technical Note: DIRART – A software suite for deformable image registration and adaptive radiotherapy research , 2010 .

[39]  Gregory C Sharp,et al.  Scale invariant feature transform in adaptive radiation therapy: a tool for deformable image registration assessment and re-planning indication , 2013, Physics in medicine and biology.

[40]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[41]  Neil Kirby,et al.  Site-specific deformable imaging registration algorithm selection using patient-based simulated deformations. , 2013, Medical physics.

[42]  M van Herk,et al.  Validation of deformable registration in head and neck cancer using analysis of variance. , 2012, Medical physics.

[43]  Ludvig Paul Muren,et al.  Propagation of target and organ at risk contours in radiotherapy of prostate cancer using deformable image registration , 2010, Acta oncologica.

[44]  R. Castillo,et al.  A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets , 2009, Physics in medicine and biology.

[45]  Dietmar Georg,et al.  Adaptive radiation therapy. , 2018, Zeitschrift fur medizinische Physik.

[46]  Deshan Yang,et al.  A fast inverse consistent deformable image registration method based on symmetric optical flow computation , 2008, 2008 42nd Asilomar Conference on Signals, Systems and Computers.

[47]  Jan-Jakob Sonke,et al.  Deformable image registration for adaptive radiation therapy of head and neck cancer: accuracy and precision in the presence of tumor changes. , 2014, International journal of radiation oncology, biology, physics.

[48]  Jing Wang,et al.  High-quality four-dimensional cone-beam CT by deforming prior images. , 2013, Physics in medicine and biology.

[49]  Nikos Paragios,et al.  Deformable Medical Image Registration: A Survey , 2013, IEEE Transactions on Medical Imaging.

[50]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[51]  Eduard Schreibmann,et al.  A measure to evaluate deformable registration fields in clinical settings , 2012, Journal of applied clinical medical physics.

[52]  R Calandrino,et al.  An automatic contour propagation method to follow parotid gland deformation during head-and-neck cancer tomotherapy , 2011, Physics in medicine and biology.

[53]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[54]  D. Hill,et al.  Non-rigid image registration: theory and practice. , 2004, The British journal of radiology.

[55]  S Yartsev,et al.  Automatic landmark generation for deformable image registration evaluation for 4D CT images of lung. , 2016, Physics in medicine and biology.

[56]  Katja M Langen,et al.  A virtual phantom library for the quantification of deformable image registration uncertainties in patients with cancers of the head and neck. , 2013, Medical physics.

[57]  Ghassan Hamarneh,et al.  N-Sift: N-Dimensional Scale Invariant Feature Transform for Matching Medical Images , 2007, ISBI.

[58]  Y Chi,et al.  Comparison of planned versus actual dose delivered for external beam accelerated partial breast irradiation using cone-beam CT and deformable registration. , 2007, International journal of radiation oncology, biology, physics.

[59]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).