Lung puncture biopsy is the gold standard for the qualitative diagnosis of lung nodules. Cone Beam CT (CBCT) is commonly used for guiding punctures to locate lung nodules. However, the poor quality of CBCT images and the limited intelligence of surgical guidance systems have lowered the efficiency of puncture procedures, particularly for small and complex lesions. This study developed and validated a robust and accurate Generative AI-Powered Puncture Surgery Navigation System for lung punctures (GPS-Lung), demonstrating clinical applicability through a multicenter randomized controlled trial (Registration number: NCT06762613). The clinical results showed significant improvements in surgeon performance with the assistance of the integrated GPS-Lung system. Specifically, the system facilitated a more standardized and efficient operational process, reducing number of punctures (2.0 ± 1.2 vs. 2.5 ± 1.7, P = 0.005), shortening operative time (20.4 ± 5.6 min vs. 23.2 ± 6.3 min, P = 0.001), decreasing radiation exposure (4357.4 ± 3427.3 μGy·m 2 vs. 5570.9 ± 4846.7 μGy·m 2 , P = 0.033), and reducing pneumothorax complications (12.7% vs. 23.9%, P = 0.033). Taken together, the proposed system demonstrates promising clinical and translational value in lung nodule puncture intervention. (Clinical Trials Registration: NCT06762613). Clinical Trials Registration: NCT06762613, Registration Date: March 26, 2025. ( https://clinicaltrials.gov/study/NCT06762613?term=NCT06762613&rank=1&tab=history ).
No takes yet. Share an insight, caveat, or question.
Chen et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: