Can computed tomography-based radiomics potentially discriminate between anterior mediastinal cysts and type B1 and B2 thymomas?

Abstract

Background Anterior mediastinal cysts (AMC) are often misdiagnosed as thymomas and undergo surgical resection, which caused unnecessary treatment and medical resource waste. The purpose of this study is to explore potential possibility of computed tomography (CT)-based radiomics for the diagnosis of AMC and type B1 and B2 thymomas. Methods A group of 188 patients with pathologically confirmed AMC (106 cases misdiagnosed as thymomas in CT) and thymomas (82 cases) and underwent routine chest CT from January 2010 to December 2018 were retrospectively analyzed. The lesions were manually delineated using ITK-SNAP software, and radiomics features were performed using the artificial intelligence kit (AK) software. A total of 180 tumour texture features were extracted from enhanced CT and unenhanced CT, respectively. The general test, correlation analysis, and LASSO were used to features selection and then the radiomics signature (radscore) was obtained. The combined model including radscore and independent clinical factors was developed. The model performances were evaluated on discrimination, calibration curve. Results Two radscore models were constructed from the unenhanced and enhanced phases based on the selected four and three features, respectively. The AUC, sensitivity, and specificity of the enhanced radscore model were 0.928, 89.3%, and 83.8% in the training dataset and 0.899, 84.6%, and 87.5% in the test dataset (higher than the unenhanced radscore model). The combined model of enhanced CT including radiomics features and independent clinical factors yielded an AUC, sensitivity and specificity of 0.941, 82.1%, and 94.6% in the training dataset and 0.938, 92.3%, and 87.5% in the test dataset (higher than the unenhanced combined model and enhanced radscore model). Conclusions The study suggested the possibility that the combined model in enhanced CT provided a potential tool to facilitate the differential diagnosis of AMC and type B1 and B2 thymomas.

Machine-learning classifiers based on non-enhanced computed tomography radiomics to differentiate anterior mediastinal cysts from thymomas and low-risk from high-risk thymomas: A multi-center study

“…Few studies have aimed to distinguish AMCs and thymomas using CT imaging radiomics features (14,15). Yasaka et al (14) reported that solid anterior mediastinal masses could be differentiated from cysts using quantitative CT texture analyses with AUC of 0.869 in 76 patients with NECT.…”

“…However, the sample size of the study was small. Liu et al (15) reported that the combined models, including radscore and CT value, exhibited better diagnostic performance compared to radscore models for distinguishing AMCs and type B1 and B2 thymomas, with AUCs of 0.928 and 0.856 based on NECT, and 0.938 and 0.899 based on CECT in the testing group, respectively. However, in clinical practice, the subtypes of thymomas cannot be easily distinguished from each other, and this study used only one ML model.…”

“…Radiomics has the potential to detect specific disease characteristics that cannot be visualized with current medical imaging modalities by quantitatively analyzing digital images. Qualitative CT radiomics analysis and radiomics-based ML have been applied for differential diagnosis of AMCs and thymomas in several studies (14,15) and in risk prediction for thymomas (16)(17)(18)(19)(20)(21), highlighting their potential for use in clinical practice to facilitate diagnosis and guide decision-making. However, previous studies have several limitations.…”

The Studies of Prognostic Factors and the Genetic Polymorphism of Methylenetetrahydrofolate Reductase C667T in Thymic Epithelial Tumors

“…Patients with low-risk thymomas rarely experience recurrence after a complete resection ( 7 ), but nevertheless, thymomas are considered as malignant tumors ( 8 ). TC is further divided into several subtypes, including squamous cell carcinoma, basaloid carcinoma, mucoepidermoid carcinoma, lymphoepithelioma-like carcinoma, and clear cell carcinoma ( 9 ).…”

“…Although surgical resection is usually accepted as a primary therapeutic strategy in a curative setting, adjuvant chemotherapy and/or radiotherapy is used in some patients who are at a high risk of recurrence to prolong survival ( 8 , 10 ).…”