Artificial intelligence driven 3D reconstruction for enhanced lung surgery planning

Abstract

The increasing complexity of lung surgeries necessitates the need for enhanced imaging support to improve the precision and efficiency of preoperative planning. Despite the promise of 3D reconstruction, clinical adoption remains limited due to time constraints and insufficient validation. To address this, we evaluate an artificial intelligence-driven 3D reconstruction system for pulmonary vessels and bronchi in a retrospective, multi-center multi-reader multi-case study. Using a two-stage crossover design, ten thoracic surgeons assess 140 cases with and without the system's assistance. The system significantly improves the accuracy of anatomical variant identification by 8% (p < 0.01), reducing errors by 41%. Improvements in secondary endpoints are also observed. Operation procedure selection accuracy is improved by 8%, with a 35% decrease in errors. Preoperative planning time is decreased by 25%, and user satisfaction is high at 99%. These benefits are consistent across surgeons of varying experience. In conclusion, the artificial intelligence-driven 3D reconstruction system significantly improves the identification of anatomical variants, addressing a critical need in preoperative planning for thoracic surgery.

Fig. 1. Schematic illustration of the multi-reader multi-cases (MRMC) study.

A total of 16 thoracic surgeons from three top-tier hospitals in China participated in this study. Three surgeons collected 450 patients and enrolled in the study according to inclusion and exclusion criteria. A total of 140 cases were randomly selected from eligible cohorts. Three expert surgeons from three centers established the golden standard based on collected surgical logs, videos, CT scans, and manually constructed 3D reconstructions. The other 10 surgeons were divided into two groups randomly and took part in the MRMC study in which two rounds of fully crossed pre-operative planning simulations were conducted with an interval of 4 weeks, either with or without the aid of AI-derived 3D reconstructions of pulmonary vessels.

Fig. 2. The anatomical variant identification analysis.

A Significant improvement of the overall case-wise accuracy of anatomical variant identification. (** stands for statistical significance p < 0.01. Two-sided Mann-Whitney test was used). B Similar degree of improvement of the case-wise accuracy of anatomical variant identification in each reader. C The improvement in accuracy among 35 / 39 anatomical structures. D Positive correlation existed between variant prevalence and identification accuracy. (The error bar stands for the 95% CI of the regression line). E Higher accuracy in anatomical variant identification was observed with AI-3D assistance comparing to control method across different variant prevalence. The difference tended to be larger in lower prevalence variants. (The error bar stands for the 95% CI of the regression line.) Source data are provided as a Source Data file.

Fig. 3. The operation procedure selection analysis.

A The accuracy of operation procedure selection was improved by AI-3D assistance. B The accuracy of operation procedure selection of each reader was improved by AI-3D assistance. (n = 140, the error bar stands for the 95% CI). C Binary selection between lobectomy and segmentectomy was improved by AI-3D assistance. D The heatmap demonstration of error types of resection extent determination with or without AI-3D. E Insufficient and mistaken resection were profoundly reduced with AI-3D assistance. (n = 1400, the error bar stands for the upper side of the 95% CI, the lower side is hidden to avoid overlaying numbers presented in the chart). Source data are provided as a Source Data file.

Fig. 4. The time consumption and confidence analysis.

A The overall time consumption was decreased by AI-3D assistance. B Time consumption difference between AI-3D and 2D approach among 10 readers. C The confidence of operation procedure selection was improved by AI-3D assistance. (n for anatomical variant identification are 11,903 with AI-3D and 11471 with 2D; n for operation approach selection is 1382 with or without AI-3D; the error bar stands for the 95% CI). D Positive correlation was observed between operation procedure selection and readers’ confidence level. (The error bar stands for the 95% CI of the regression line). E Positive correlation was observed between anatomical variant identification and readers’ confidence level. (The error bar stands for the 95% CI of the regression line). Source data are provided as a Source Data file.