Soft-tissue sound-speed-aware ultrasound-CT registration method for computer-assisted orthopedic surgery

Ultrasound (US) has been introduced to computer-assisted orthopedic surgery for bone registration owing to its advantages of nonionizing radiation, low cost, and noninvasiveness. However, the registration accuracy is limited by US image distortion caused by variations in the acoustic properties of soft tissues. This paper proposes a soft-tissue sound-speed-aware registration method to overcome the above challenge. First, the feature enhancement strategy of multi-channel overlay is proposed for U²-net to improve bone segmentation performance. Secondly, the sound speed of soft tissue is estimated by simulating the bone surface distance map for the update of US-derived points. Finally, an iterative registration strategy is adopted to optimize the registration result. A phantom experiment was conducted using different registration methods for the femur and tibia/fibula. The fiducial registration error (femur, 0.98 ± 0.08 mm (mean ± SD); tibia/fibula, 1.29 ± 0.19 mm) and the target registration error (less than 2.11 mm) showed the high accuracy of the proposed method. The experimental results suggest that the proposed method can be integrated into navigation systems that provide surgeons with accurate 3D navigation information.

First, multi-channel input data including the original image, phase symmetric image, and depth weighted map are fused for U²-net model training in the automatic bone segmentation of US images. When US-derived points are obtained, the sound speed of soft tissue is estimated by simulating the bone surface distance map for the update of the locations of US-derived points. An iterative registration strategy based on the cost function of corresponding point distances is adopted to optimize the registration result. Finally, a gold-standard transformation based on artificial fiducials is constructed for method evaluation.