New Validation Method for Establishing Correspondence Between Pairs of X-Ray Mammograms

Establishing spatial correspondence between features visible in x-ray mammograms obtained at different times has great potential to aid assessment of change in the breast indicative of malignant changes and facilitate their quantification. The literature contains numerous non-rigid registration algorithms developed for this purpose, but quantitative estimation of registration accuracy is limited. In this paper we describe a novel validation method which simulates plausible mammographic compressions of the breast using an MRI derived finite element model. By projecting the resulting known 3D displacements into 2D and simulating x-ray mammograms from these same compressed MR volumes, we can generate convincing images with known 2D displacements with which to validate a registration algorithm. We illustrate this approach by computing the accuracy for a non-rigid registration algorithm applied to mammographic test images generated from three patient MR datasets.

[1]  Nico Karssemeijer,et al.  A regional registration method to find corresponding mass lesions in temporal mammogram pairs. , 2005, Medical physics.

[2]  Robert Marti,et al.  Automatic Point Correspondence and Registration Based on Linear Structures , 2002, Int. J. Pattern Recognit. Artif. Intell..

[3]  David Gavaghan,et al.  Predicting Tumour Location by Simulating Large Deformations of the Breast Using a 3D Finite Element Model and Nonlinear Elasticity , 2004, MICCAI.

[4]  Michael Brady,et al.  A registration framework for the comparison of mammogram sequences , 2005, IEEE Transactions on Medical Imaging.

[5]  Dan Rico,et al.  A volumetric method for estimation of breast density on digitized screen-film mammograms. , 2003, Medical physics.

[6]  Dimitris N. Metaxas,et al.  A finite element model of the breast for predicting mechanical deformations during biopsy procedures , 2000, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis. MMBIA-2000 (Cat. No.PR00737).

[7]  R. Warren,et al.  Magnetic resonance imaging screening in women at genetic risk of breast cancer: imaging and analysis protocol for the UK multicentre study , 2000 .

[8]  T. Krouskop,et al.  Elastic Moduli of Breast and Prostate Tissues under Compression , 1998, Ultrasonic imaging.

[9]  Jonathan Bishop,et al.  A constrained modulus reconstruction technique for breast cancer assessment , 2001, IEEE Transactions on Medical Imaging.

[10]  D. Hawkes,et al.  Anisotropic multi-scale fluid registration: evaluation in magnetic resonance breast imaging , 2005, Physics in medicine and biology.

[11]  J. Schnabel,et al.  Factors influencing the accuracy of biomechanical breast models. , 2006, Medical physics.

[12]  R. Sinkus,et al.  High-resolution tensor MR elastography for breast tumour detection. , 2000, Physics in medicine and biology.

[13]  Michael A. Wirth,et al.  Nonrigid mammogram registration using mutual information , 2002, SPIE Medical Imaging.

[14]  A. Miller,et al.  Quantitative classification of mammographic densities and breast cancer risk: results from the Canadian National Breast Screening Study. , 1995, Journal of the National Cancer Institute.

[15]  J. Kaufhold,et al.  A calibration approach to glandular tissue composition estimation in digital mammography. , 2002, Medical physics.

[16]  Laurent D. Cohen,et al.  A new Image Registration technique with free boundary constraints: application to mammography , 2002, Comput. Vis. Image Underst..

[17]  Michael I. Miga,et al.  Modality independent elastography (MIE): a new approach to elasticity imaging , 2004, IEEE Transactions on Medical Imaging.

[18]  Nico Karssemeijer,et al.  A comparison of methods for mammogram registration , 2003, IEEE Transactions on Medical Imaging.

[19]  Nick C. Fox,et al.  Automated Hippocampal Segmentation by Regional Fluid Registration of Serial MRI: Validation and Application in Alzheimer's Disease , 2001, NeuroImage.

[20]  Hany Farid,et al.  Elastic registration in the presence of intensity variations , 2003, IEEE Transactions on Medical Imaging.

[21]  Nico Karssemeijer,et al.  Volumetric breast density estimation from full-field digital mammograms , 2006, IEEE Trans. Medical Imaging.

[22]  Derek L. G. Hill,et al.  Comparison of biomechanical breast models: a case study , 2002, SPIE Medical Imaging.

[23]  Michael Brady,et al.  Mammographic Image Analysis , 1999, Computational Imaging and Vision.

[24]  G Wang,et al.  ImageParser: a tool for finite element generation from three-dimensional medical images , 2004, Biomedical engineering online.

[25]  Berkman Sahiner,et al.  Comparison of similarity measures for the task of template matching of masses on serial mammograms. , 2005, Medical physics.

[26]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[27]  Martin J. Yaffe,et al.  Biomechanical 3-D finite element modeling of the human breast using MRI data , 2001, IEEE Transactions on Medical Imaging.

[28]  K D Paulsen,et al.  Three‐dimensional subzone‐based reconstruction algorithm for MR elastography , 2001, Magnetic resonance in medicine.

[29]  David J. Hawkes,et al.  Validation of nonrigid image registration using finite-element methods: application to breast MR images , 2003, IEEE Transactions on Medical Imaging.

[30]  Dmitry B. Goldgof,et al.  Matching point features under small nonrigid motion , 2001, Pattern Recognit..