Mathematics

Algorithm

Image (mathematics)

Artificial intelligence

Image registration

Surface (topology)

Geometry

Computer science

Computer vision

Catheter navigation guided by the registration of electroanatomic map (EAM) and CT surface is widely used in atrial fibrillation (AF) ablations, however, few studies have done on the registration algorithm. Moreover, some of them are semiautomatic that physicians must be professional; some are inaccurate for catheter navigation. A both automatic and accurate registration method is needed. Therefore, in this study, we proposed a traditional iterative closest point (ICP) based approach for EAM and CT surface registration. First, using principal axes based registration, EAM/CT pairs were coarsely aligned. Then using traditional ICP, EAM/CT pairs were finely aligned. The coarse-to-fine procedure was full automatic. Using Carto-Merge, stochastic approach (SA) and our method, we aligned three patients' EAM/CT pairs and compared their results. Among the three algorithms, our method registered EAM and CT surface most accurately and most steady. The experiment validated our approach.

A valid registration algorithm for electroanatomic map and CT surface