A probabilistic approach for the simultaneous mammogram registration and abnormality detection

Authors:
Mohamed Hachama;Agnès Desolneux;Frédéric Richard
Affiliations:
MAP5, University Paris 5, Paris, France;MAP5, University Paris 5, Paris, France;MAP5, University Paris 5, Paris, France
Venue:
IWDM'06 Proceedings of the 8th international conference on Digital Mammography
Year:
2006

Citing 4
Cited 2

Outlier Modeling in Image Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
A new image registration technique with free boundary constraints: application to mammography

Computer Vision and Image Understanding - Special issue on nonrigid image registration
A New Approach For The Registration of Images With Inconsistent Differences

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
A comparative study of markovian and variational image-matching techniques in application to mammograms

Pattern Recognition Letters - Special issue: Artificial neural networks in pattern recognition

Comparison of Multiple View Strategies to Reduce False Positives in Breast Imaging

IWDM '08 Proceedings of the 9th international workshop on Digital Mammography
Template registration with missing parts: application to the segmentation of m. tuberculosis infected lungs

ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new method for simultaneously registering mammograms and detecting abnormalities. We assume that pixels can be divided into two classes: normal tissue and abnormalities (lesions). We define the registration constraints as a mixture of two distributions which describe statistically image gray-level variations for both pixel classes. The two distributions are weighted at each pixel by the probability of abnormality presence. Using the Maximum A Posteriori, we estimate the registration transformation and the probability map of abnormality presence at the same time. We illustrate the properties of our technique with some experiments and compare it with some classical methods.