Automatic Segmentation of Rotational X-Ray Images for Anatomic Intra-Procedural Surface Generation in Atrial Fibrillation Ablation Procedures

Abstract

Since the introduction of 3-D rotational X-ray imaging, protocols for 3-D rotational coronary artery imaging have become widely available in routine clinical practice. Intra-procedural cardiac imaging in a computed tomography (CT)-like fashion has been particularly compelling due to the reduction of clinical overhead and ability to characterize anatomy at the time of intervention. We previously introduced a clinically feasible approach for imaging the left atrium and pulmonary veins (LAPVs) with short contrast bolus injections and scan times of approximately 4 -10 s. The resulting data have sufficient image quality for intra-procedural use during electro-anatomic mapping (EAM) and interventional guidance in atrial fibrillation (AF) ablation procedures. In this paper, we present a novel technique to intra-procedural surface generation which integrates fully-automated segmentation of the LAPVs for guidance in AF ablation interventions. Contrast-enhanced rotational X-ray angiography (3-D RA) acquisitions in combination with filtered-back-projection-based reconstruction allows for volumetric interrogation of LAPV anatomy in near-real-time. An automatic model-based segmentation algorithm allows for fast and accurate LAPV mesh generation despite the challenges posed by image quality; relative to pre-procedural cardiac CT/MR, 3-D RA images suffer from more artifacts and reduced signal-to-noise. We validate our integrated method by comparing 1) automatic and manual segmentations of intra-procedural 3-D RA data, 2) automatic segmentations of intra-procedural 3-D RA and pre-procedural CT/MR data, and 3) intra-procedural EAM point cloud data with automatic segmentations of 3-D RA and CT/MR data. Our validation results for automatically segmented intra-procedural 3-D RA data show average segmentation errors of 1) approximately 1.3 mm compared with manual 3-D RA segmentations 2) approximately 2.3 mm compared with automatic segmentation of pre-procedural CT/MR data and 3) approximately 2.1 mm compared with registered intra-procedural EAM point clouds. The overall experiments indicate that LAPV surfaces can be automatically segmented intra-procedurally from 3-D RA data with comparable quality relative to meshes derived from pre-procedural CT/MR.

Multi-part Left Atrium Modeling and Segmentation in C-Arm CT Volumes for Atrial Fibrillation Ablation

“…There is no quantitative evaluation available in [2,3]. To the best of our knowledge, there is only one previous work [7] on the LA segmentation on C-arm CT, which was validated on large volumes only and did not segment the more challenging LA appendage. After excluding the LA appendage, we achieve an overall segmentation error of 1.50 mm for large volumes and 1.63 mm for small volumes.…”

“…Compared to the holistic approach [7], the part based approach can handle large structural variations. The MSL based detection/segmentation works well for the LA chamber.…”

“…In practice, non-model based approaches work well on CT and MRI datasets, but they are not robust on challenging Carm CT. The model based approaches exploit a prior shape of the LA (either in the form of an atlas [5,6] or a mean shape mesh [7]) to guide the segmentation. For example, Manzke et al [7] built a mean shape of the combined structure of the LA chamber and PVs from a training set.…”

“…The model based approaches exploit a prior shape of the LA (either in the form of an atlas [5,6] or a mean shape mesh [7]) to guide the segmentation. For example, Manzke et al [7] built a mean shape of the combined structure of the LA chamber and PVs from a training set. With a prior shape constraint, they could avoid the leakage around weak or missing boundaries, which plagues the non-model based approaches.…”

“…Instead of using one mean model [7], the PV structural variations are addressed using a part based model, where the whole LA is split into the chamber, appendage, and four major PVs. Each part is a much simpler anatomical structure compared to the holistic one, therefore can be detected and segmented using a model based approach.…”