Non-rigid registration of breast images using feature points.

We present a feature point detection algorithm which we use for non-rigid registration, illustrated for breast images (mammography, MRI). By associating the continuous intrinsic dimensionality of image structure with the output of a scale saliency algorithm, breast boundary points can be separated from internal feature points. Correspondences established for the breast boundary and internal feature points respectively are used to drive two recent non-rigid registration techniques: polyaffine transformation and coherent point drift registration. Experimental results are presented for digital breast tomosynthesis and 3D breast MRI, and in all case achieve good spatial alignments.

Classification of clusters of microcalcifications in digital breast tomosynthesis.

The detection of microcalcifications, reconstruction of clusters of microcalcifications and their subsequent classification into malignant and benign are important tasks in the early detection of breast cancer. Digital breast tomosynthesis (DBT) provides new opportunities in such tasks. By utilizing the multiple projections in DBT and using the geometry of DBT, we have developed an approach to them based on epipolar curves. It improves the sensitivity and specificity in detection; provides information for estimation of 3D positions of microcalcifications; and facilitates classification. We have generated 15 simulated datasets, each with a microcalcification cluster based on an ellipsoidal shape. We estimate the 3D positions of the microcalcifications in each of the clusters and reconstruct the clusters as ellipsoids. We classify each cluster as malignant or benign based on the parameters of the ellipsoids. The classification result is compared with the ground truth. Our results show that the deviations between the actual and estimated 3D positions of the microcalcification, and the actual and estimated parameters of the ellipsoids are sufficiently small that the classification results are 100% correct. This demonstrates the feasibility in cluster classification in 3D.

Avoiding local optima of the joint entropy prior in limited view tomography using a multiresolution scheme.

The incorporation of anatomical reference images into limited view transmission tomography has been attempted previously by using the joint entropy prior. However, this prior has been found to be sensitive to local optima. Here, we propose to increase robustness to local optima by using a multiresolution optimisation scheme. To our knowledge, this is the first work to apply multiresolution optimisation to the joint entropy prior in limited view transmission tomography. The results show a substantial mitigation of the sensitivity to local optima, as well as a robustness to missing as well as extra regions in the anatomical reference image. In addition, we demonstrate the method's robustness to misalignment between the reconstruction and the anatomical reference image.