Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imaging

TL;DR

This paper introduces a class-aware cartilage segmentation and geometry-constrained registration method to improve autonomous ultrasound-guided thoracic imaging by accurately mapping scanning paths to individual patients.

Contribution

It presents a novel cartilage segmentation network with geometry constraints and a dense skeleton graph-based registration for personalized US-CT path mapping in thoracic imaging.

Findings

Accurately maps intercostal US paths with 2.21mm error

Enhances internal organ visibility by precise path localization

Robustly registers CT and US data across multiple patients

Abstract

Ultrasound imaging has been widely used in clinical examinations owing to the advantages of being portable, real-time, and radiation-free. Considering the potential of extensive deployment of autonomous examination systems in hospitals, robotic US imaging has attracted increased attention. However, due to the inter-patient variations, it is still challenging to have an optimal path for each patient, particularly for thoracic applications with limited acoustic windows, e.g., intercostal liver imaging. To address this problem, a class-aware cartilage bone segmentation network with geometry-constraint post-processing is presented to capture patient-specific rib skeletons. Then, a dense skeleton graph-based non-rigid registration is presented to map the intercostal scanning path from a generic template to individual patients. By explicitly considering the high-acoustic impedance bone structures, the transferred scanning path can be precisely located in the intercostal space, enhancing the visibility of internal organs by reducing the acoustic shadow. To evaluate the proposed approach, the final path mapping performance is validated on five distinct CTs and two volunteer US data, resulting in ten pairs of CT-US combinations. Results demonstrate that the proposed graph-based registration method can robustly and precisely map the path from CT template to individual patients (Euclidean error: $2.21\pm1.11~mm$).