Skeleton Graph-Based Ultrasound-CT Non-Rigid Registration

Autonomous ultrasound (US) scanning has attracted increased attention, and it has been seen as a potential solution to overcome the limitations of conventional US examinations, such as inter-operator variations. However, it is still challenging to autonomously and accurately transfer a planned scan trajectory on a generic atlas to the current setup for different patients, particularly for thorax applications with limited acoustic windows. To address this challenge, we proposed a skeleton graph-based non-rigid registration to adapt patient-specific properties using subcutaneous bone surface features rather than the skin surface. To this end, the self-organization mapping is successively used twice to unify the input point cloud and extract the key points, respectively. Afterward, the minimal spanning tree is employed to generate a tree graph to connect all extracted key points. To appropriately characterize the rib cartilage outline to match the source and target point cloud, the path extracted from the tree graph is optimized by maximally maintaining continuity throughout each rib. To validate the proposed approach, we manually extract the US cartilage point cloud from one volunteer and seven CT cartilage point clouds from different patients. The results demonstrate that the proposed graph-based registration is more effective and robust in adapting to the inter-patient variations than the ICP (distance error mean $\pm$ SD: $5.0\pm \text{1.9}\,\text{mm}$ vs $8.6\pm \text{6.7}\,\text{mm}$ on seven CTs).

I. Introduction

Medical ultrasound (US) is one of the most widely used imaging modalities in daily clinical practice. Since US imaging is real-time, non-ionizing radiation, and widely accessible, it is often used as the standard approach for internal organ examinations [1], [2] and imaging-guided intervention [3], particularly in the preliminary healthcare industry. Nevertheless, the conventional US examination is highly user-dependent, as the resulting image is sensitive to the acquisition parameters, i.e., contact force and probe orientation [4]. Besides the deep understanding of the physiological background, sonographers are required to simultaneously optimize the acquisition parameters toward high-quality images during US examinations, which often need years of systematic medical training [5].