A hybrid method for 2-D/3-D registration between 3-D volumes and 2-D angiography for trans-catheter aortic valve implantation (TAVI)

Minimally invasive trans-catheter aortic valve implantation (TAVI) procedure can be greatly facilitated using smart visualization and guidance technology involving the 3-D model of the aorta. In this paper, a hybrid method is proposed for contrast-based registration between the 3-D model and angiography of the aorta during TAVI procedures. By integrating the information of aorta segmentation and aortic landmark detection into intensity-based registration, the proposed method combines the merits of intensity-based registration and feature/landmark-based registration. In addition, the challenging task of explicit feature/landmark extraction on 2-D images is avoided. Experiments on 9 real clinical data achieved an average registration error of 2.14±0.49 pixels, demonstrating the efficacy of the proposed method.