2023 World Conference on Lung Cancer (Posters)-P1.16. Artificial Intelligence-Assisted Quantitative CT parameters in Predicting the Degree of Risk of Solitary Pulmonary Nodules

P1.16. Artificial Intelligence-Assisted Quantitative CT parameters in Predicting the Degree of Risk of Solitary Pulmonary Nodules - PDF(Slides)

Back to course

Pdf Summary

This research study aimed to investigate the value of computed tomography (CT) parameters in predicting the degree of risk of solitary pulmonary nodules (SPN) in patients with lung adenocarcinoma. Lung adenocarcinoma is the most common type of non-small cell lung cancer (NSCLC), and accurately determining the invasiveness of SPN is crucial in developing effective treatment strategies. The study included patients with clinical stage 0 to IB NSCLC who underwent radical surgical resection at a hospital in China. Preoperative CT scans were performed, and CT parameters such as CT values (maximum, minimum, and mean) and CT findings (pure ground glass opacity, part-solid, and solid) were evaluated. The histological subtypes were also considered. The results showed that the CT value mean and CT findings were independently correlated with high-risk SPN in multivariate analysis. A receiver operating characteristic curve was used to identify low- or high-risk SPNs, and the area under the curve was calculated to be 0.811. The study concluded that CT analysis of SPN can be used to discriminate the risk of SPN and may be helpful in determining the appropriate extent of surgical resection. The research was funded by several organizations, including the National Natural Science Foundation of China and the Shanghai Talent Development Fund. Figures 2, 3, 4, and 5 display representative CT scans and box plots illustrating the CT parameters and CT findings.

Asset Subtitle

Long Jiang

Meta Tag

Speaker Long Jiang

Topic Screening & Early Detection: Nodule Management

Keywords

computed tomography

solitary pulmonary nodules

lung adenocarcinoma

CT values

CT findings

high-risk SPN

multivariate analysis

surgical resection

histological subtypes

CT analysis