188 IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 2, FEBRUARY 2006 Mammogram Registration: A Phantom-Based Evaluation of Compressed Breast Thickness Variation Effects Frédéric J. P. Richard, Member, IEEE, Predrag R. Bakic ´*, Student Member, IEEE, and Andrew D. A. Maidment, Student Member, IEEE Abstract—The temporal comparison of mammograms is complex; a wide variety of factors can cause changes in image appearance. Mammogram registration is proposed as a method to reduce the effects of these changes and potentially to emphasize genuine alterations in breast tissue. Evaluation of such registra- tion techniques is difficult since ground truth regarding breast deformations is not available in clinical mammograms. In this paper, we propose a systematic approach to evaluate sensitivity of registration methods to various types of changes in mammograms using synthetic breast images with known deformations. As a first step, images of the same simulated breasts with various amounts of simulated physical compression have been used to evaluate a pre- viously described nonrigid mammogram registration technique. Registration performance is measured by calculating the average displacement error over a set of evaluation points identified in mammogram pairs. Applying appropriate thickness compensation and using a preferred order of the registered images, we obtained an average displacement error of 1.6 mm for mammograms with compression differences of 1–3 cm. The proposed methodology is applicable to analysis of other sources of mammogram differences and can be extended to the registration of multimodality breast data. Index Terms—Breast compression, evaluation, finite elements, image registration, mammogram synthesis, mammography, multi- grid optimization, partial differential equations, tissue modeling. I. INTRODUCTION R ADIOLOGISTS analyze mammograms by examining temporal sequences of images. Such temporal compar- isons have value because, to a first approximation, normal breasts do not change significantly over time, except for minor variations associated with the menstrual cycle or significant changes in body weight, [1], [2]. Some pathological changes in the breast are sufficiently subtle that they may pass unnoticed for many years; thus, radiologists compare images from a number of previous years. Such changes can be further obfus- cated by different choices of X-ray technique, and variation in Manuscript received September 15, 2005; revised November 15, 2005. The Associate Editor responsible for coordinating the review of this paper and recommending its publication was N. Karssemeijer. Asterisk indicates corresponding author. F. J. P. Richard is with the Department of Mathematics and Computer Science, University Paris 5-René Descartes, 75 270 Paris, cedex 06 France. *P. R. Bakic ´ is with the Department of Radiology, University of Penn- sylvania, 3400 Spruce Street, Philadelphia, PA 19104 USA (e-mail: pre- drag.bakic@uphs.upemm.edu). A. D. A. Maidment is with the Department of Radiology, University of Penn- sylvania, Philadelphia, PA 19104 USA. Digital Object Identifier 10.1109/TMI.2005.862204 breast positioning or compression. It is our desire to develop methods which will increase the sensitivity to temporal patho- logical changes and develop means to evaluate these methods. The task of comparing mammograms is difficult because there are many factors which may cause changes in image appearance, e.g., choice of image acquisition parameters, positioning and compression of the breast, image display parameters, and changes in breast anatomy. Changes such as those resulting from acquisition conditions tend to affect images globally and can typically be corrected by image normalization methods, [3]. Differences caused by changes in breast positioning and compression are more complex and more difficult to correct because mammograms are projections through the deformed breast. Mammogram registration is being considered as a method that could suppress technical variations (e.g., mammogram positioning and compression) and maintain or potentially emphasize genuine alterations in the breast, whether normal or abnormal. This research was motivated in part by the development of systems for computer-aided diagnosis (CAD) of breast abnormalities, since some use bilateral or temporal mammo- gram comparisons to improve accuracy, [4]. As with clinical mammography, CAD systems are sensitive to various types of changes observed in mammograms. If not corrected, these normal changes generally decrease system performance by gen- erating false-positive lesions or hiding true lesions. Therefore, registering mammograms is of importance for CAD system design. More recently, both contrast-enhanced mammography [5], [6] and contrast-enhanced breast tomosynthesis [7] have been proposed. Both methods produce images of the breast in which the physiologic distribution of iodinated contrast agents is demonstrated. Two methods have been proposed [8]. Dual-en- ergy subtraction [6] has the advantage that low- and high-energy images of the breast are acquired nearly simultaneously; thus, breast motion is minimized, but lesion contrast and background suppression is poor. Temporal subtraction [5] results in images with superior lesion contrast and background suppression, but are subject to motion artifacts. Accurate registration of precontrast and postcontrast images to compensate for any breast motion is, thus, essential. Both rigid [9]–[12] and nonrigid [13]–[16] methods of mam- mogram registration have been proposed. No systematic evalu- ation of registration performance has been reported for specific 0278-0062/$20.00 © 2006 IEEE