Automatic segmentation of contrast-enhanced time resolved image series

Medical imaging often involves the injection of contrast agents and the subsequent analysis of tissue enhancement patterns. Many important types of tissue have characteristic enhancement patterns; for example, in MR mammography, malignancies exhibit a characteristic "wash out" temporal pattern, while in MR angiography, arteries, veins and parenchyma each have their own distinctive temporal signature. In such time resolved image series, there are substantial changes in intensities; however, this change is due primarily to the contrast agent, rather than to motion. As a result, the task of automatically segmenting contrast-enhanced images poses interesting new challenges. In this paper, we propose a new image segmentation algorithm for time resolved image series with contrast enhancement, using a model-based time series analysis of individual pixels. We take an energy minimization approach to ensure spatial coherence. The energy is minimized in an expectation-maximization fashion that alternates between segmenting the image into a number of non-overlapping regions and finding the temporal profile parameters which describe the behavior of each region. Preliminary experiments on MR angiography and MR mammography studies show the algorithm's ability to find an accurate segmentation.