3D Reconstruction Based on Multi-Phase CT for Kidney Cancer Surgery

In kidney cancer surgery, it is important to reconstruct an accurate 3D model of the kidney and tumor from computed tomography (CT) data. In recent years, multi-phase CT is widely used for the diagnosis of kidney cancer due to the complementary information among phases. However, 3D reconstruction of the anatomy of kidney and renal mass using multi-phase CT data has not been well studied in the literature. In this paper, we present a multi-phase CT-based 3D reconstruction method that fuses cross-phase information seamlessly to produce an accurate 3D model of the kidney and tumor. In particular, we align multi-phase CT images based on the segmented kidney and tumor regions and aggregate the reconstructed 3D models from multiple CT phases to generate a fused model with well-defined surfaces. Experimental results show that the proposed method achieves high performance in terms of qualitative evaluations compared to the single-phase-based reconstruction method.