Introduction: Radiomics methods are used to analyze various medical images, including computed tomography (CT), magnetic resonance, and positron emission tomography to provide information regarding the diagnosis, patient outcome, tumor phenotype, and the gene-protein signatures of various diseases. In low-risk group, complete surgical resection is typically sufficient, whereas in high-risk thymoma, adjuvant therapy is usually required. Therefore, it is important to distinguish between both. This study evaluated the CT radiomics features of thymomas to discriminate between low- and high-risk thymoma groups. Materials and methods: In total, 83 patients with thymoma were included in this study between 2004 and 2019. We used the Radcloud platform (Huiying Medical Technology Co., Ltd.) to manage the imaging and clinical data and perform the radiomics statistical analysis. The training and validation datasets were separated by a random method with a ratio of 2:8 and 502 random seeds. The histopathological diagnosis was noted from the pathology report. Results: Four machine-learning radiomics features were identified to differentiate a low-risk thymoma group from a high-risk thymoma group. The radiomics feature names were Energy, Zone Entropy, Long Run Low Gray Level Emphasis, and Large Dependence Low Gray Level Emphasis. Conclusions: The results demonstrated that a machine-learning model and a multilayer perceptron classifier analysis can be used on CT images to predict low- and high-risk thymomas. This combination could be a useful preoperative method to determine the surgical approach for thymoma.

Objectives: The objective of this paper is to assess the results of surgical treatment retrospectively in a consecutive series of 85 patients with pe

Background Although tumor size is included in the definition of T descriptor in the tumor-node-metastasis (TNM) classification of many solid tumors, it is not considered for thymomas. This study aimed to assess the relationship of tumor diameters (the largest tumor diameter [LTD] and the mean tumor diameter [MTD]) with survival in thymoma patients undergoing surgical resection in a single center. Methods The study included 127 thymoma patients (age, 49.2 ± 15.2 years; 65 males), who were evaluated based on pathological tumor sizes according to the LTD and MTD ([largest diameter + shortest diameter] / 2) and divided into three subgroups for each parameter as: patients with an LTD of ≤5 cm, 5.1 to 10 cm, and >10 cm and patients with an MTD of ≤5, 5.1 to 10, and >10 cm. Results In thymoma patients, survival significantly differed according to the presence of myasthenia gravis (p = 0.018), resection status (R0 or R1; p = 0.001), T status (p = 0.015), and the Masaoka–Koga stage (p = 0.003). In the LTD subgroups, the overall survival of those with R0 resection was lower in those with an LTD of 5.1 to 10 cm than in those with an LTD of ≤5 cm (p = 0.051) and significantly lower in those with an MTD of 5.1 to 10 cm than in those with an MTD of ≤5 cm (p = 0.027). In the MTD subgroups, survival decreased as the tumor size increased. Conclusion Both smaller tumor size and complete resection are associated with better survival in thymoma patients. Therefore, the largest or the mean tumor size might be considered as a criterion in the TNM staging for thymoma. It was presented as a poster at the 20th World Lung Cancer Conference in Barcelona-Spain. Received: 30 April 2020 Accepted: 24 June 2020 Publication Date: 08 September 2020 (online) Georg Thieme Verlag KG Stuttgart · New York