CT-Based Radiomics Nomogram for Differentiation of Anterior Mediastinal Thymic Cyst From Thymic Epithelial Tumor

Overview

Journal Front Oncol

Specialty Oncology

Date 2021 Dec 27

PMID 34956869

Citations 3

Authors

Chengzhou Zhang

Qinglin Yang

Fan Lin

Heng Ma

Haicheng Zhang

Ran Zhang

Ping Wang

Ning Mao

Affiliations

Soon will be listed here.

Abstract

Objectives: This study aimed to distinguish preoperatively anterior mediastinal thymic cysts from thymic epithelial tumors a computed tomography (CT)-based radiomics nomogram.

Methods: This study analyzed 74 samples of thymic cysts and 116 samples of thymic epithelial tumors as confirmed by pathology examination that were collected from January 2014 to December 2020. Among the patients, 151 cases (scanned at CT 1) were selected as the training cohort, and 39 cases (scanned at CT 2 and 3) served as the validation cohort. Radiomics features were extracted from pre-contrast CT images. Key features were selected by SelectKBest and least absolute shrinkage and selection operator and then used to build a radiomics signature (Rad-score). The radiomics nomogram developed herein multivariate logistic regression analysis incorporated clinical factors, conventional CT findings, and Rad-score. Its performance in distinguishing the samples of thymic cysts from those of thymic epithelial tumors was assessed discrimination, calibration curve, and decision curve analysis (DCA).

Results: The radiomics nomogram, which incorporated 16 radiomics features and 3 conventional CT findings, including lesion edge, lobulation, and CT value, performed better than Rad-score, conventional CT model, and the clinical judgment by radiologists in distinguishing thymic cysts from thymic epithelial tumors. The area under the receiver operating characteristic (ROC) curve of the nomogram was 0.980 [95% confidence interval (CI), 0.963-0.993] in the training cohort and 0.992 (95% CI, 0.969-1.000) in the validation cohort. The calibration curve and the results of DCA indicated that the nomogram has good consistency and valuable clinical utility.

Conclusion: The CT-based radiomics nomogram presented herein may serve as an effective and convenient tool for differentiating thymic cysts from thymic epithelial tumors. Thus, it may aid in clinical decision-making.

Citing Articles

The predictive value of a computed tomography-based radiomics model for the surgical separability of thymic epithelial tumors from the superior vena cava and the left innominate vein.

Li Z, Wang F, Zhang H, Zheng H, Zhou X, Wang Z Quant Imaging Med Surg. 2023; 13(9):5622-5640.

PMID: 37711814 PMC: 10498270. DOI: 10.21037/qims-22-1050.

Conventional and radiomic features to predict pathology in the preoperative assessment of anterior mediastinal masses.

Mayoral M, Pagano A, Araujo-Filho J, Zheng J, Perez-Johnston R, Tan K Lung Cancer. 2023; 178:206-212.

PMID: 36871345 PMC: 10544811. DOI: 10.1016/j.lungcan.2023.02.014.

Mediastinal thymic cysts: a narrative review.

Cooley-Rieders K, Van Haren R Mediastinum. 2022; 6:33.

PMID: 36582977 PMC: 9792833. DOI: 10.21037/med-22-25.

References

Liu J, Xu H, Qing H, Li Y, Yang X, He C . Comparison of Radiomic Models Based on Low-Dose and Standard-Dose CT for Prediction of Adenocarcinomas and Benign Lesions in Solid Pulmonary Nodules. Front Oncol. 2021; 10:634298. PMC: 7884759. DOI: 10.3389/fonc.2020.634298. View

Shen Q, Shan Y, Xu W, Hu G, Chen W, Feng Z . Risk stratification of thymic epithelial tumors by using a nomogram combined with radiomic features and TNM staging. Eur Radiol. 2020; 31(1):423-435. DOI: 10.1007/s00330-020-07100-4. View

Turna A, Sarbay I . Multimodality approach in treatment of thymic tumors. J Thorac Dis. 2021; 12(12):7626-7634. PMC: 7797860. DOI: 10.21037/jtd-20-818. View

Xiao G, Rong W, Hu Y, Shi Z, Yang Y, Ren J . MRI Radiomics Analysis for Predicting the Pathologic Classification and TNM Staging of Thymic Epithelial Tumors: A Pilot Study. AJR Am J Roentgenol. 2019; 214(2):328-340. DOI: 10.2214/AJR.19.21696. View

Tomiyama N, Muller N, Ellis S, Cleverley J, Okumura M, Miyoshi S . Invasive and noninvasive thymoma: distinctive CT features. J Comput Assist Tomogr. 2001; 25(3):388-93. DOI: 10.1097/00004728-200105000-00010. View

Roden A, Fang W, Shen Y, Carter B, White D, Jenkins S . Distribution of Mediastinal Lesions Across Multi-Institutional, International, Radiology Databases. J Thorac Oncol. 2019; 15(4):568-579. DOI: 10.1016/j.jtho.2019.12.108. View

Kamata S, Ishida I, Suzuki Y, Oura H . Single-center evaluation of prognostic factors for thymoma treated by surgery: a retrospective study. J Cardiothorac Surg. 2021; 16(1):8. PMC: 7791864. DOI: 10.1186/s13019-020-01386-7. View

Araki T, Sholl L, Gerbaudo V, Hatabu H, Nishino M . Intrathymic cyst: clinical and radiological features in surgically resected cases. Clin Radiol. 2014; 69(7):732-8. PMC: 4068340. DOI: 10.1016/j.crad.2014.03.002. View

Yoon S, Choi S, Kang C, Goo J . Incidental Anterior Mediastinal Nodular Lesions on Chest CT in Asymptomatic Subjects. J Thorac Oncol. 2017; 13(3):359-366. DOI: 10.1016/j.jtho.2017.11.124. View

10.

Khorfan R, Bharat A, Odell D . Management and Long-Term Outcomes of Advanced Stage Thymoma in the United States. Ann Thorac Surg. 2020; 111(1):223-230. PMC: 8452232. DOI: 10.1016/j.athoracsur.2020.05.088. View

11.

Choi Y, McAdams H, Jeon S, Hong E, Kim Y, Im J . Idiopathic multilocular thymic cyst: CT features with clinical and histopathologic correlation. AJR Am J Roentgenol. 2001; 177(4):881-5. DOI: 10.2214/ajr.177.4.1770881. View

12.

Priola A, Priola S, Gned D, Giraudo M, Fornari A, Veltri A . Comparison of CT and chemical-shift MRI for differentiating thymoma from non-thymomatous conditions in myasthenia gravis: value of qualitative and quantitative assessment. Clin Radiol. 2016; 71(3):e157-69. DOI: 10.1016/j.crad.2015.12.009. View

13.

Tomiyama N, Honda O, Tsubamoto M, Inoue A, Sumikawa H, Kuriyama K . Anterior mediastinal tumors: diagnostic accuracy of CT and MRI. Eur J Radiol. 2007; 69(2):280-8. DOI: 10.1016/j.ejrad.2007.10.002. View

14.

Wang X, Chen K, Li X, Li Y, Yang F, Li J . Clinical features, diagnosis and thoracoscopic surgical treatment of thymic cysts. J Thorac Dis. 2018; 9(12):5203-5211. PMC: 5756969. DOI: 10.21037/jtd.2017.10.148. View

15.

Jeong Y, Lee K, Kim J, Shim Y, Han J, Kwon O . Does CT of thymic epithelial tumors enable us to differentiate histologic subtypes and predict prognosis?. AJR Am J Roentgenol. 2004; 183(2):283-9. DOI: 10.2214/ajr.183.2.1830283. View

16.

Jeung M, Gasser B, Gangi A, Bogorin A, Charneau D, Wihlm J . Imaging of cystic masses of the mediastinum. Radiographics. 2002; 22 Spec No:S79-93. DOI: 10.1148/radiographics.22.suppl_1.g02oc09s79. View

17.

Kumar V, Gu Y, Basu S, Berglund A, Eschrich S, Schabath M . Radiomics: the process and the challenges. Magn Reson Imaging. 2012; 30(9):1234-48. PMC: 3563280. DOI: 10.1016/j.mri.2012.06.010. View

18.

Zhonggao J, YiJiao W, Yongfeng W, Zhitao P, Jun W, Diansheng L . Multislice computed tomography performance in differential diagnosis of high-density thymic cyst and thymoma in lesions less than 3 cm. Thorac Cancer. 2018; 9(10):1300-1304. PMC: 6166092. DOI: 10.1111/1759-7714.12840. View

19.

Liu J, Yin P, Wang S, Liu T, Sun C, Hong N . CT-Based Radiomics Signatures for Predicting the Risk Categorization of Thymic Epithelial Tumors. Front Oncol. 2021; 11:628534. PMC: 7953900. DOI: 10.3389/fonc.2021.628534. View

20.

Hu J, Zhao Y, Li M, Liu Y, Wang F, Weng Q . Machine-learning-based computed tomography radiomic analysis for histologic subtype classification of thymic epithelial tumours. Eur J Radiol. 2020; 126:108929. DOI: 10.1016/j.ejrad.2020.108929. View