Abstract 14084: Computationally Identified Shape Differences In The Left Atrium On Pre-ablation Ct Scans Appear To Be Associated With Recurrence Of Atrial Fibrillation

Abstract

Introduction: Catheter-based ablation is an increasingly utilized management strategy for atrial fibrillation (AF); however, a major problem is AF recurrence post-ablation. There is increasing interest in the use of advanced image analysis to better understand differences in left atrial (LA) shape that may be associated with a higher recurrence risk and potential sites of recurrence. Hypothesis: Factors which lead to the post-ablation recurrence prompt LA differential remodeling. The significant shape difference regions among AF recurrence (AF+) and AF non-recurrence (AF-) patients can be identified from pre-ablation CT scans. Those regions could potentially represent future sites of recurrence and hence could be targets for ablation. Methods: This study included pre-ablation CT-scans of 51 AF+ and 51 AF- patients. Two separate atlases were created by registering Left atrial CT volumes of AF+ and AF- patients to their representative templates (T+ and T- respectively). The atlases were co-registered to a common canonical frame of reference (T-) and a non-parametric General Linear Model (GLM) based t-test with 500 permutations was used to identify the regions (Surface of interest (SOI)) that are statistically significant (p-value<0.1) between the two classes. To reduce sensitivity in the template selection, we constructed an ensemble SOI based on SOIs obtained from 10 different templates and made the frequency map of overlap SOIs. Results: The registration accuracy in the final common frame in terms of average Dice similarity coefficient was in the range of 0.85-0.94 over the 10 SOI constructions. The frequency map revealed the maximum overlap of SOIs in an area where left pulmonary veins enter the left atrium. This could potentially represent a new target for ablation. Conclusions: An ensemble atlas-based shape differentiation method revealed SOI regions that are structurally associated with recurrence and might potentially represent targets for ablation.