Related Experiment Video
Updated: Mar 13, 2026
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
Preoperative localization of pulmonary nodules using ultra-low-dose CT based on artificial intelligence iterative
Huixiang Lan1, Xiaobin Liu1, Danlin Ou1
1Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China.
Background:
Preoperative localization of pulmonary nodules requires multiple computed tomography (CT) scans, making it an urgent problem to address how to effectively reduce radiation damage while maintaining image quality. Artificial intelligence iterative reconstruction (AIIR) can significantly improve the image quality of ultra-low-dose CT (ULDCT). This study aimed to examine the feasibility of using ULDCT-AIIR for the preoperative localization of pulmonary nodules.
Methods:
This prospective study enrolled 40 consecutive patients with pulmonary nodules who underwent preoperative hook-wire localization under low-dose CT (LDCT). Immediately following the LDCT, an additional ULDCT scan was performed. Images were reconstructed using filtered back projection (FBP) and a hybrid iterative reconstruction (HIR) for both LDCT and ULDCT scans; additionally, AIIR was applied solely to the ULDCT images. Objective parameters measured included image noise, contrast-to-noise ratio (CNR), and the distances between nodules and reference. Subjective image quality was assessed using a 5-point Likert scale, evaluating the visualization of pulmonary nodules, localization grids, needle tips, hook-wires, and complications. Quantitative and qualitative metrics were compared across the reconstruction groups using the Kruskal-Wallis test.
Results:
The volume CT dose index of ULDCT was 90% lower than that of LDCT (0.22 vs. 2.20 mGy). ULDCT-AIIR showed comparable lung parenchyma noise and CNRnodule-lung to LDCT-HIR (P>0.05), and significantly outperformed other reconstructions (P<0.01). The subjective visualization scores for nodules, localization grids, needle tips, hook-wires, and complications with ULDCT-AIIR were non-inferior to those with LDCT-HIR and significantly superior to most other reconstruction groups (P<0.01). Distance measurements demonstrated no significant differences between ULDCT-AIIR and other reconstruction methods (P>0.05).
Conclusions:
ULDCT-AIIR achieves image quality comparable to LDCT-HIR with significantly reduced radiation doses, suggesting its potential as an alternative to LDCT for preoperative pulmonary nodule localization.
