A new method for evaluating lung volume: AI-3D reconstruction

Abstract

Objective: This study aims to explore the clinical application of an AI-3D reconstruction system in measuring lung volume and analyze its practical value in donor-recipient size matching in lung transplantation. Methods: The study retrospectively collected data from 75 subjects who underwent a plethysmography examination and lung CT at the First Hospital of Jilin University. General data and information related to lung function, and imaging results were collected. The correlation between actual total lung volume (aTLV), predicted total lung volume (pTLV), and artificial intelligence three-dimensional reconstruction CT lung volume (AI-3DCTVol) was analyzed for the overall, male, and female groups. The correlation coefficient and the absolute error percentage with pTLV and AI-3DCTVol were obtained. Results: In the overall, male, and female groups, there were statistical differences (p <0.05) between the pTLV formula and AI-3D reconstruction compared to the plethysmography examination value. The ICC between pTLV and aTLV for all study participants was 0.788 (95% CI: 0.515-0.893), p <0.001. Additionally, the ICC value between AI-3D reconstruction and aTLV was 0.792 (95% CI: 0.681-0.866), p <0.001. For male study participants, the ICC between pTLV and aTLV was 0.330 (95% CI: 0.032-0.617), p = 0.006. Similarly, the ICC value between AI-3D reconstruction and aTLV was 0.413 (95% CI: 0.089-0.662), p = 0.007. In the case of female research subjects, the ICC between pTLV and aTLV was 0.279 (95% CI: 0.001-0.523), p = 0.012. Further, the ICC value between AI-3D reconstruction and aTLV was 0.615 (95% CI: 0.561-0.870), p <0.001. Conclusion: The AI-3D reconstruction, as a convenient method, has significant potential for application in lung transplantation.

Keywords: AI-3D reconstruction; ICC; donor-recipient lung volume matching; lung transplantation; lung volume calculation.