Non-rigid mammogram registration using demons algorithm: preliminary results

Authors:
Yujun Guo;Wei-Hung Cheng;Cheng-Chang Lu
Affiliations:
Kent State University, Kent, OH;Kent State University, Kent, OH;Kent State University, Kent, OH
Venue:
SIP '07 Proceedings of the Ninth IASTED International Conference on Signal and Image Processing
Year:
2007

Citing 3
Cited 1

Principal Warps: Thin-Plate Splines and the Decomposition of Deformations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Scattered Data Interpolation with Multilevel B-Splines

IEEE Transactions on Visualization and Computer Graphics
Establishing the correspondence between control points in pairs of mammographic images

IEEE Transactions on Image Processing

Detection of masses based on asymmetric regions of digital bilateral mammograms using spatial description with variogram and cross-variogram functions

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

X-ray mammography is the main tool used for the detection and diagnosis of breast malignancies. Mammogram registration plays an important role in breast cancer detection. The inhomogeneous, anisotropic nature of the soft-tissue within the breast, its inherent non-rigid body behavior, temporal changes of the breast tissue, and various imaging conditions, make breast image registration a challenging task. In this paper, we present a novel non-rigid mammogram registration approach using demons algorithm. The algorithm is fully automatic, intensity-based, and is implemented in a multi-resolution framework. An extension is also applied to accelerate the convergence. Mammogram data sets from MIAS database are used in our study. Preliminary results are presented. The performance of the algorithm was evaluated both visually and quantitatively, and the method yields promising results.