Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor

Abstract

Background: Pulmonary inflammatory pseudotumor (PIPT) usually presents as solitary peripheral well-defined nodules or masses, and CT features are complex and changeable, which are often confused with peripheral lung cancer. This study is to distinguish peripheral lung cancer and PIPT using CT-radiomics features extracted from PET/CT images.Methods: In this study, the standard 18F-fluorodeoxyglucose 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 retrospectively 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, and compared by Delong test.Results: A total of 435 radiomics features were extracted, of which 23 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, 5 of 18 Shape features. area under the curve (AUC) of these features were 0.731 0.075, 0.717, 0.737, 0.748 0.038, respectively. The P values of statistical differences among ROC were 0.0499 (F11, F23), 0.0472 (F12, F13) and 0.0250 (F13, Mean4). The discrimination ability of forming new features(Parent Feature) after averaging the features extracted at different angles and distances was moderate compared to the previous features(Child features).Conclusions: Radiomics features extracted from non-contrast CT based on PET/CT images can help distinguish peripheral lung cancer and PIPT.

Narrative review of radiomics for classifying pulmonary nodules and potential impact on lung cancer screening

“…They found 14 of 330 GLCM, 1 of 49 first-order features, and 5 or 18 shape features to fit their criteria. They found that a model using shape features performed the best (64). While the studies are limited, they seem to suggest first order statistics may not have a significant role to play in differentiating benign and malignant nodules compared to features derived from shape and texture features derive from second-and higherorder statistics.…”

A subregion-based positron emission tomography/computed tomography (PET/CT) radiomics model for the classification of non-small cell lung cancer histopathological subtypes

“…[1]original_shape_VoxelVolume [2]original_shape_Sphericity [3]original_shape_Maximum2DDiameterSlice [4]original_shape_Maximum2DDiameterColumn [5]original_shape_Maximum3DDiameter [6]original_shape_Flatness [7]original_shape_MeshVolume [8]original_shape_SurfaceArea [9]original_shape_MinorAxisLength [10]original_shape_SurfaceVolumeRatio [11]original_shape_Maximum2DDiameterRow [12]original_shape_MajorAxisLength [13]original_shape_LeastAxisLength [14]original_shape_Elongation [15]original_glcm_ClusterProminence [16]original_glcm_SumSquares [17]original_glcm_DifferenceVariance [18]original_glcm_JointAverage [19]original_glcm_Contrast [20]original_glcm_ClusterShade [21]original_glcm_Idm [22]original_glcm_Idmn [23]original_glcm_Id [24]original_glcm_MCC [25]original_glcm_Autocorrelation [26]original_glcm_JointEnergy [27]original_glcm_JointEntropy [28]original_glcm_SumAverage [29]original_glcm_InverseVariance [30]original_glcm_Imc2 [31]original_glcm_ClusterTendency [32]original_glcm_DifferenceAverage [33]original_glcm_DifferenceEntropy [34]original_glcm_SumEntropy [35]original_glcm_Idn [36]original_glcm_MaximumProbability [37]original_glcm_Imc1 [38]original_glcm_Correlation [39]original_ngtdm_Contras [40]original_ngtdm_Strength…”

“…However, this method is invasive and requires random sampling of tumor fragments (7). In contrast, radiomics analysis (8,9) is considered to be a noninvasive tool for the classification of lung cancer histopathological subtypes through medical image analysis, which offers quantitative tumor heterogeneity information (10,11) by quantitatively describing shapes, gray level histograms, or textures (12,13).…”