Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Breast Contrast-Enhanced MRI (ce-MRI) requires a series of images to be acquired before, and repeatedly after, intravenous injection of a contrast agent. Breast MRI segmentation based on the differential enhancement of image intensities can assist the clinician detect suspicious regions. Image registration between the temporal data sets is necessary to compensate for patient motion, which is quite often substantial. Although segmentation and registration are usually treated as separate problems in medical image analysis, they can naturally benefit a great deal from each other. In this paper, we propose a scheme for simultaneous segmentation and registration of breast ce-MRI. It is developed within a Bayesian framework, based on a maximum a posteriori estimation method. A pharmacokinetic model and Markov Random Field model have been incorporated into the framework in order to improve the performance of our algorithm. Our method has been applied to the segmentation and registration of clinical ce-MR images. The results show the potential of our methodology to extract useful information for breast cancer detection.


Journal article


Inf Process Med Imaging

Publication Date





126 - 137


Algorithms, Artificial Intelligence, Breast, Breast Neoplasms, Contrast Media, Gadolinium DTPA, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Magnetic Resonance Imaging, Pattern Recognition, Automated, Reproducibility of Results, Sensitivity and Specificity, Subtraction Technique