A regional registration technique for automated interval change analysis of breast lesions on mammograms

Abstract

Analysis of interval change is a useful technique for detection of abnormalities in mammographic interpretation. Interval change analysis is routinely used by radiologists and its importance is well-established in clinical practice. As a first step to develop a computerized method for interval change analysis on mammograms, we are developing an automated regional registration technique to identify corresponding lesions on temporal pairs of mammograms. In this technique, the breast is first segmented from the background on the current and previous mammograms. The breast edges are then aligned using a global alignment procedure based on the mutual information between the breast regions in the two images. Using the nipple location and the breast centroid estimated independently on both mammograms, a polar coordinate system is defined for each image. The polar coordinate of the centroid of a lesion detected on the most recent mammogram is used to obtain an initial estimate of its location on the previous mammogram and to define a fan-shaped search region. A search for a matching structure to the lesion is then performed in the fan-shaped region on the previous mammogram to obtain a final estimate of its location. In this study, a quantitative evaluation of registration accuracy has been performed with a data set of 74 temporal pairs of mammograms and ground-truth correspondence information provided by an experienced radiologist. The most recent mammogram of each temporal pair exhibited a biopsy-proven mass. We have investigated the usefulness of correlation and mutual information as search criteria for determining corresponding regions on mammograms for the biopsy-proven masses. In 85% of the cases (63/74 temporal pairs) the region on the previous mammogram that corresponded to the mass on the current mammogram was correctly identified. The region centroid identified by the registration technique had an average distance of 2.8+/-1.9 mm from the centroid of the radiologist-identified region. These results indicate that our new registration technique may be useful for establishing correspondence between structures on current and previous mammograms. Once such a correspondence is established an interval change analysis could be performed to aid in both detection as well as classification of abnormal breast densities.

Breast image registration techniques: a survey

“…Then, TPS-registration is used to match the mammograms. In contrast to the previous studies, where the whole breast area was registered, there are also regional breast registration techniques reported [40,115].…”

“…In the normal clinical routine radiologists inspect individual mammograms for characteristic signs of potential cancer, aided by comparing bilateral mammograms for suspicious bilateral asymmetry or temporal mammograms for developing abnormalities. The identification of the abnormalities by radiologists may serve as references for registration [29,115]. Visual inspection is also the most obvious method for evaluation of the registration accuracy [72,104,107,136,137,139].…”

“…The distances can be calculated, for example, between the centroids of ROIs [29,108,115,127], breast contours [44], or other landmarks, as a measure of registration error. Tanner et al [133] quantified the displacement errors of their FEM model for MR volume registration by calculating the mean and standard deviation of the Euclidean distance error at 12 corresponding landmarks.…”

“…Figure 1 shows the anatomy of the breast. In practice, the extraction of the anatomical features, both at the surface [40,70,100,115,150] and internal [25,74,81,113,131,137,139], helps to locate corresponding control points in both images that can be used for registration. Still other features, like texton (a basic texture element) [56,93] and texture map [119], can also be found in the literature.…”

Incorporation of fuzzy spatial relation in temporal mammogram registration

“…Rigid or affine deformations between temporal mammograms was often assumed and used in many attempts [8,9]. However, these methods were limited by the fact that the map between mammograms of the same breast is usually not smooth and not even well defined.…”