Robot-Assisted CT-Guided Biopsy with an Artificial Intelligence-Based Needle-Path Generator: An Experimental Evaluation Using a Phantom Model

Abstract

Purpose: To investigate the feasibility of a robotic system with artificial intelligence-based lesion detection and path planning for computed tomography (CT)-guided biopsy compared with the conventional freehand technique.

Materials and methods: Eight nodules within an abdominal phantom, incorporating the simulated vertebrae and ribs, were designated as targets. A robotic system was used for lesion detection, trajectory generation, and needle holder positioning. Four interventional radiologists with more than 5 years of experience and 4 with 5 years of experience or less performed 96 robot-assisted insertions encompassing both in-plane and out-of-plane trajectories. Additionally, 32 CT fluoroscopy single-rotation scan-guided freehand needle insertions were performed along the in-plane trajectories. The 3-dimensional (3D), lateral, depth deviations, and insertion time were quantified using post-needle insertion CT scans. Statistical analysis was performed using the unpaired t-test or 1-way analysis of variance, with a significance level of P < .05.

Results: The system detected all target lesions and generated appropriate needle paths. Robot-assisted insertions exhibited significantly smaller 3D and depth deviations than freehand insertions (3.8 mm ± 1.3 vs 4.7 mm ± 1.6, P = .001, and 1.8 mm ± 1.2 vs 2.6 mm ± 1.8, P = .005, respectively). No significant difference was observed in lateral deviations (3.0 mm ± 1.5 vs 3.5 mm ± 1.5, P = .118). Robotic assistance significantly reduced insertion time compared with freehand insertion (17.3 s ± 7.8 vs 78.6 s ± 38.1, P < .001). The same trends were observed between the 2 groups of radiologists.

Conclusions: The robotic system has the potential to shorten puncture time while maintaining sufficient accuracy in CT-guided procedures.