Ultrasound fusion image error correction using subject-specific liver motion model and automatic image registration

Purpose: Ultrasound fusion imaging is an emerging tool and benefits a variety of clinical applications, such as image-guided diagnosis and treatment of hepatocellular carcinoma and unresectable liver metastases. However, respiratory liver motion-induced misalignment of multimodal images (i.e., fusion error) compromises the effectiveness and practicability of this method. The purpose of this paper is to develop a subject-specific liver motion model and automatic registration-based method to correct the fusion error. Methods: An online-built subject-specific motion model and automatic image registration method for 2D ultrasound-3D magnetic resonance (MR) images were combined to compensate for the respiratory liver motion. The key steps included: 1) Build a subject-specific liver motion model for current subject online and perform the initial registration of pre-acquired 3D MR and intra-operative ultrasound images; 2) During fusion imaging, compensate for liver motion first using the motion model, and then using an automatic registration method to further correct the respiratory fusion error. Evaluation experiments were conducted on liver phantom and five subjects. Results: In the phantom study, the fusion error (superior-inferior axis) was reduced from 13.90 +/- 2.38 mm to 4.26 +/- 0.78 mm by using the motion model only. The fusion error further decreased to 0.63 +/- 0.53 mm by using the registration method. The registration method also decreased the rotation error from 7.06 +/- 0.21 degrees to 1.18 +/- 0.66. In the clinical study, the fusion error was reduced from 12.90 +/- 9.58 nun to 6.12 +/- 2.90 mm by using the motion model alone. Moreover, the fusion error decreased to 1.96 +/- 0.33 mm by using the registration method. Conclusions: The proposed method can effectively correct the respiration-induced fusion error to improve the fusion image quality. This method can also reduce the error correction dependency on the initial registration of ultrasound and MR images. Overall, the proposed method can improve the clinical practicability of ultrasound fusion imaging.