Fully Automatic 2D and 3D Image Segmentation by Data-driven Regression

We developed a novel data-driven regression method for fully-automatic landmark detection and shape segmentation in 2D X-ray and 3D CT images (Figure 3). To detect landmarks, we estimate the displacements from some randomly sampled image patches to the (unknown) landmark positions, and then we integrate these predictions via a voting scheme. Our key contribution is a new data-driven regression algorithm for estimating these displacements. Different from other methods where each image patch independently predicts its displacement, we jointly estimate the displacements from all patches together in a data driven way, by considering not only the training data but also geometric constraints on the test image. The displacements estimation is formulated as a convex optimization problem that can be solved efficiently. Finally, we use the sparse shape composition model as the a priori information to regularize the landmark positions and thus generate the segmented shape contour. Comprehensive experiments conducted on 2D X-ray images and 3D CT data demonstrated the efficacy of the developed method