Clinical Value Of ¹⁸F-FDG PET/CT Imaging Omics In Distinguishing Benign And Malignant Pulmonary Nodules

Objective:Exploring the clinical application value of ¹⁸F-FDG PET/CT in differentiating benign and malignant pulmonary nodules using a model established through imaging omics.Methods:Retrospective collection and analysis of 100 patients from January2021 to August 2022,all of whom underwent ¹⁸F-FDG PET/CT examination at Jiangxi Provincial People’s Hospital before treatment and had pathological confirmation.Among them,24 cases were benign and 76 cases were malignant.Randomly divide patients into a training group and a validation group in a 7:3 ratio.Firstly,manually delineate the Region of Interest（ROI）in PET images and CT images using ITK-SNAP software,and extract imaging omics features using AK（GE Healthcare Analysis Kit）software.Then,the Spearman correlation analysis method is used to eliminate redundancy,eliminate features with correlation coefficients higher than 0.7,and use the Least absolute shrinkage and selection operator（LASSO）method to reduce dimensionality to obtain the most meaningful features based on¹⁸F-FDG PET/CT images for modeling.Draw a receiver operating characteristic（ROC）curve to evaluate the diagnostic effectiveness of the model,and draw a decision curve to evaluate the diagnostic benefit of patients.Results:756 imaging omics features were extracted from ¹⁸F-FDG PET images and CT images of the same machine,and 10 features were ultimately selected to construct an ¹⁸F-FDG PET/CT imaging omics model for distinguishing benign and malignant pulmonary nodules.In the training group,the area under curve（AUC）of the model was 0.95（95%CI 0.910-1.000）,with a cutoff value of 0.137,sensitivity of90.6%,specificity of 100.0%,and diagnostic accuracy of 95.2%.In the validation group,under the same cutoff values,the AUC of the model was 0.72（95%CI0.558-0.900）,the sensitivity was 73.9%,the specificity was 85.7%,and the diagnostic accuracy was 79.5%.The decision curve shows that patients can benefit from this model.Conclusion:The ¹⁸F-FDG PET/CT imaging omics model has good clinical application value in distinguishing benign and malignant pulmonary nodules.