Segmentation and reconstruction of DCT images based on lifted multicut

In this paper, a novel automatic segmentation and reconstruction method is proposed for diffraction contrast tomography (DCT) technology. The pipeline of the proposed method starts from the imaging of Al−La alloy with the LabDCT technique from Carl Zeiss AG, which produces a sequence of 2D microstructure sections. Then, a segmentation algorithm based on superpixel and lifted multicut is proposed to extract the 2D microstructure in an image section. Finally, 2D segmentations are joined together to reconstruct and visualize the 3D microstructure. As a result, a novel morphology of Al−La alloy is recovered with both dendrite and lamellar morphologies. The proposed method has the advantage of the ability to losslessly recover the internal microstructure.