Time continuous segmentation of cardiac MR images using Active Appearance Motion Models

Abstract

In previous work, we have demonstrated that Active Appearance Models (AAMs) perform robustly for segmentation of static cardiac MR images, since they exploit prior knowledge about the cardiac shape and image appearance. However, applying 2D AAMs to full cardiac cycle segmentation would require multiple models for different phases of the cardiac cycle because traditional AAMs account only for the variations within image classes and not temporal classes. This paper presents a novel 2D+time Active Appearance Motion Model (AAMM) that represents the dynamics of the cardiac cycle in combination with shape and image appearance of the heart, ensuring a time-continuous segmentation of a complete cardiac MR sequence. In an AAMM, single-beat sequences are phase-normalized into sets of 2D images and the shape points and pixel intensities between frames are concatenated into a shape vector and intensity vector. Appearance variations over time are captured using Principal Component Analysis on both vectors in the training set. Time-continuous segmentation is achieved by minimizing the model appearance-to-target differences and adjusting the model coefficients using a gradient descent approach. In a clinical validation study, the automatically detected contours exhibited a high similarity to the manually defined independent standard. Large-scale clinical validation in patients is ongoing.