Room: AAPM ePoster Library
This study is to distinguish peripheral lung cancer and pulmonary inflammatory pseudotumor using CT-radiomics features extracted from PET/CT images.
In this study, the standard 18 F-flurodeoxyglucose positron emission tomography/ computed tomography (18 F-FDG PET/CT) images of 21 patients with pulmonary inflammatory pseudotumor (PIPT) and 21 patients with peripheral lung cancer were restrospectively collected. The dataset was used to extract CT-radiomics features from regions of interest (ROI),using,then,statistical methods to screen CT-radiomics features,which could distinguish peripheral lung cancer and PIPT. And the ability of radiomics features distinguished peripheral lung cancer and PIPT was estimated by receiver operating characteristic (ROC) curves.
A total of 435 radiomics features were extracted, of which 20 could difference between peripheral lung cancer and PIPT. these features were seen in 16 of 330 Gray-Level Co-occurrence Matrix features, 1 of 49 Intensity Histogram features, 1 of 5 Neighbor Intensity Difference features, 2 of 18 Shape features. area under the curve (AUC) of these features were 0.7310.075, 0.717, 0.737, 0.7480.038, respectively.
Radiomics features extracted from non-contrast CT based on PET/CT images can help distinguish peripheral lung cancer and PIPT.
FDG PET, Feature Extraction, Feature Selection