Analysis of the value of enhanced CT combined with texture analysis in the differential diagnosis of pulmonary sclerosing pneumocytoma and atypical peripheral lung cancer: a feasibility study

Abstract

Background As a rare benign lung tumour, pulmonary sclerosing pneumocytoma (PSP) is often misdiagnosed as atypical peripheral lung cancer (APLC) on routine imaging examinations. This study explored the value of enhanced CT combined with texture analysis to differentiate between PSP and APLC. Methods Forty-eight patients with PSP and fifty patients with APLC were retrospectively enrolled. The CT image features of the two groups of lesions were analysed, and MaZda software was used to evaluate the texture of CT venous phase thin-layer images. Independent sample t-test, Mann–Whitney U tests or χ2 tests were used to compare between groups. The intra-class correlation coefficient (ICC) was used to analyse the consistency of the selected texture parameters. Spearman correlation analysis was used to evaluate the differences in texture parameters between the two groups. Based on the statistically significant CT image features and CT texture parameters, the independent influencing factors between PSP and APLC were analysed by multivariate logistic regression. Extremely randomized trees (ERT) was used as the classifier to build models, and the models were evaluated by the five-fold cross-validation method. Results Logistic regression analysis based on CT image features showed that calcification and arterial phase CT values were independent factors for distinguishing PSP from APLC. The results of logistic regression analysis based on CT texture parameters showed that WavEnHL_s-1 and Perc.01% were independent influencing factors to distinguish the two. Compared with the single-factor model (models A and B), the classification accuracy of the model based on image features combined with texture parameters was 0.84 ± 0.04, the AUC was 0.84 ± 0.03, and the sensitivity and specificity were 0.82 ± 0.13 and 0.87 ± 0.12, respectively. Conclusion Enhanced CT combined with texture analysis showed good diagnostic value for distinguishing PSP and APLC, which may contribute to clinical decision-making and prognosis evaluation.

CT‐based radiomics for differentiating peripherally located pulmonary sclerosing pneumocytoma from carcinoid

“…Similar to our results, recent studies have also demonstrated the efficacy of radiomics models in dis-tinguishing PSP from other malignant lung tumors. For instance, Luo et al 20 investigated the value of CECT combined with texture analysis in differentiating PSP from atypical peripheral lung cancer, and achieved an AUC value of 0.72 for their CT texture-based model. Similarly, Xiao et al 21 assessed the diagnostic value of radiomics-based texture analysis in differentiating PSP from solid malignant pulmonary nodules on singleand three-phase CT images.…”

“…18 Recently, several studies have highlighted the clinical value of radiomics in discriminating benign from malignant pulmonary lesions. [19][20][21][22] To the best of our knowledge, there were only two studies published to investigate the diagnostic value of radiomics in differentiating PSP from pulmonary malignancy. One focused on PSP versus solid malignant pulmonary nodules,the other focused on PSP versus atypical peripheral lung cancer.…”

“…One focused on PSP versus solid malignant pulmonary nodules,the other focused on PSP versus atypical peripheral lung cancer. 20,21 However, as of now, the utility of radiomics to differentiate PSP from PC has not been reported. Therefore, the purpose of this study is to investigate the feasibility of CT radiomics in the differentiation between PSP and PC.…”

Giant pulmonary sclerosing pneumocytoma with potentially malignant biological behavior: a case report and literature review

“…In some cases, invasive growth is distributed near the pleura or hilum, or there are malignant signs such as burrs and pleural depression, which are easily misdiagnosed as lung cancer and require careful clinical decision-making. In one report, enhanced CT combined with texture analysis was used to locate calcification, and arterial phase CT values could assist in differentiating PSP from peripheral lung cancer ( 17 ). Depending on the different tissue structures of the lesion, different degrees of enhancement may occur in the early stage after enhanced scanning ( 14 ).…”

The adding value of contrast-enhanced CT radiomics: Differentiating tuberculosis from non-tuberculous infectious lesions presenting as solid pulmonary nodules or masses

“…CECT images often reflect the blood supply to the lesion, and enhancement attenuation helped distinguish between benign and malignant pulmonary nodules ( 16 , 17 ). In terms of radiomics, CECT combined with texture analysis had a good diagnostic value for distinguishing pulmonary sclerosing pneumocytoma and atypical peripheral lung cancer, with a sensitivity and specificity of 0.82 and 0.87, respectively ( 18 ). The study of Liu et al ( 19 ) showed that texture analysis of CECT could be used to evaluate the pathological grade of lung adenocarcinoma.…”