Reproducible Evaluation of Registration Algorithms for Movement Correction in Dynamic Contrast Enhancing Magnetic Resonance Imaging for Breast Cancer Diagnosis
Accurate methods for computer aided diagnosis of breast cancer increase accuracy of detection and provide support to physicians in detecting challenging cases. In dynamic contrast enhancing magnetic resonance imaging (DCE-MRI), motion artifacts can appear as a result of patient displacements. Non-linear deformation algorithms for breast image registration provide with a solution to the correspondence problem in contrast with affine models. In this study we evaluate 3 popular non-linear registration algorithms: MIRTK, Demons, SyN Ants, and compare to the affine baseline. We propose automatic measures for reproducible evaluation on the DCE-MRI breast-diagnosis TCIA-database, based on edge detection and clustering algorithms, and provide a rank of the methods according to these measures.
KeywordsMedical image processing Reproducibility DCE-MRI Registration Diffeomorphism Optical flow Non-affine registration
This work has received funding from the European Unions Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No. 656886.
- 3.Bloch, Nicolas, B., Jain, Ashali, Jaffe, C.C.: Data from breast-diagnosis. The Cancer Imaging Archive (2015)Google Scholar
- 6.Ebrahimi, M., Martel, A.L.: A general PDE-framework for registration of contrast enhanced images. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5761, pp. 811–819. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04268-3_100CrossRefGoogle Scholar
- 14.Othman, Z., Haron, H., Kadir, M.R.A., Rafiq, M.: Comparison of Canny and Sobel edge detection in MRI images. Comput. Sci. Biomech. Tissue Eng. Group Inf. Syst. 133–136 (2009)Google Scholar