Precise target definition is a keystone of the promising cardiac radioablation (CR) technique for the treatment of ventricular tachycardia (VT). This step of treatment planning relies on multimodal data integration (cardiac CT scans, electro-anatomical mapping (EAM), PET…), as many anatomic and functional information must be exploited to locate the arrhythmogenic substrate.

The objective of this work was to propose a workflow for multimodal data integration to improve the robustness of CR target definition, and to compare this workflow with a baseline slice-by-slice delineation method with no EAM data integration.

A target definition workflow was developed to generate a 3D mesh on which were fused all descriptors of interest extracted from multimodal images of a given patient. The left ventricle and myocardium were automatically segmented from cardiac Computed Tomography (cCT) image using a deep learning approach. The 3D mesh of the left ventricle was then built using the marching cubes algorithm. Myocardium thickness was computed on each point of the cCT mesh using distance mapping. EAM data was exported from the CARTO system. The EAM mesh was automatically registered to the cCT mesh. Multimodal information was projected on the cCT LV mesh. A tool was integrated to delineate the target by geodesic path picking on its surface. The resulting target was finally propagated to the whole width of the myocardium in order to generate the clinical target volume which can be exported and directly exploited by treatment planning systems (TPS). Four cardiologists delineated targets for 3 patients using this method and using a standard TPS with no EAM integration.

Cardiologists using this workflow reported being more confident about their target definition. The three-dimensional representation especially was considered helpful to identify the optimal target zone. The targets delineated using the proposed method also showed less spatial variability between experts.

The developed workflow enables to fuse multimodal information to improve the robustness of target definition in CR of VT. Preliminary experiments show very positive feedback from clinicians and a decrease of delineation variability.