Hidden Markov Measure Field Models for Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Texture-Based Simultaneous Registration and Segmentation of Breast DCE-MRI
IWDM '08 Proceedings of the 9th international workshop on Digital Mammography
MIAR '08 Proceedings of the 4th international workshop on Medical Imaging and Augmented Reality
Segmentation and classification of breast tumor using dynamic contrast-enhanced MR images
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
De-enhancing the dynamic contrast-enhanced breast MRI for robust registration
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Stabilization of Flicker-Like Effects in Image Sequences through Local Contrast Correction
SIAM Journal on Imaging Sciences
Non-rigid registration for colorectal cancer MR images
CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
Hi-index | 0.00 |
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.