A radiomics model to predict the invasiveness of thymic epithelial tumors based on contrast‑enhanced computed tomography

Chen,Xiangmeng; Feng,Bao; Li,Changlin; Duan,Xiaobei; Chen,Yehang; Li,Zhi; Liu,Zhuangsheng; Zhang,Chaotong; Long,Wansheng

doi:10.3892/or.2020.7497

A radiomics model to predict the invasiveness of thymic epithelial tumors based on contrast‑enhanced computed tomography

Authors:
- Xiangmeng Chen
- Bao Feng
- Changlin Li
- Xiaobei Duan
- Yehang Chen
- Zhi Li
- Zhuangsheng Liu
- Chaotong Zhang
- Wansheng Long
View Affiliations

Affiliations: Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong 529030, P.R. China, School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin, Guangxi 541004, P.R. China, Department of Nuclear Medicine, Jiangmen Central Hospital, Jiangmen, Guangdong 529030, P.R. China
Published online on: February 11, 2020 https://doi.org/10.3892/or.2020.7497
Pages: 1256-1266
Copyright: © Chen et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

In the present study, we aimed to construct a radiomics model using contrast‑enhanced computed tomography (CT) to predict the pathological invasiveness of thymic epithelial tumors (TETs). We retrospectively reviewed the records of 179 consecutive patients (89 females) with histologically confirmed TETs from two hospitals. The 82 low‑ and 97 high‑risk TETs were assigned to training (90 tumors), internal validation (49 tumors) and external validation (40 tumors) cohorts. Radiomics features extracted from preoperative contrast‑enhanced chest CT were selected using least absolute shrinkage and selection operator logistic regression. Three prediction models were developed using multivariate logistic regression analysis. Their performance and clinical utility were assessed using receiver operating characteristic curves and the DeLong test, respectively. Eight radiomics features with non‑zero coefficients were used to develop a radiomics score, which significantly differed between low‑ and high‑risk TETs (P<0.001). The subjective finding, infiltration, was independently associated with high‑risk TETs. Prediction models based on infiltration alone, the radiomics signature alone, and both these parameters showed diagnostic accuracies of 72.2% [area under curve (AUC), 0.731; 95% confidence interval (CI): 0.627‑0.819; sensitivity, 85.7%; specificity, 60.4%], 88.9% (AUC, 0.944; 95% CI: 0.874‑0.981; sensitivity, 92.9%; specificity, 85.4%), and 90.0% (AUC, 0.953; 95% CI: 0.887‑0.987; sensitivity, 92.9%; specificity, 87.5%), respectively. Decision‑curve analysis showed that the combined model added more net benefit than the single‑parameter models. In conclusion, a radiomics signature based on contrast‑enhanced CT has the potential to differentiate between low‑ and high‑risk TETs. The model incorporating the radiomics signature and subjective finding may facilitate the individualized, preoperative prediction of the pathological invasiveness of TETs.

View Figures

View References

1	Marom EM: Advances in thymoma imaging. J Thorac Imaging. 28:69–83. 2013. View Article : Google Scholar : PubMed/NCBI
2	Fujii Y: Published guidelines for management of thymoma. Thorac Surg Clin. 21:125–129. 2011. View Article : Google Scholar : PubMed/NCBI
3	Marx A, Ströbel P, Badve SS, Chalabreysse L, Chan JK, Chen G, de Leval L, Detterbeck F, Girard N, Huang J, et al: ITMIG consensus statement on the use of the WHO histological classification of thymoma and thymic carcinoma: Refined definitions, histological criteria, and reporting. J Thorac Oncol. 9:596–611. 2014. View Article : Google Scholar : PubMed/NCBI
4	Marx A, Chan JK, Coindre JM, Detterbeck F, Girard N, Harris NL, Jaffe ES, Kurrer MO, Marom EM, Moreira AL, et al: The 2015 World Health Organization classification of tumors of the thymus: Continuity and changes. J Thorac Oncol. 10:1383–1395. 2015. View Article : Google Scholar : PubMed/NCBI
5	Giaccone G, Wilmink H, Paul MA and van der Valk P: Systemic treatment of malignant thymoma. Am J Clin Oncol. 29:336–344. 2006. View Article : Google Scholar : PubMed/NCBI
6	Okumura M, Miyoshi S, Fujii Y, Takeuchi Y, Shiono H, Inoue M, Fukuhara K, Kadota Y, Tateyama H, Eimoto T and Matsuda H: Clinical and functional significance of WHO classification on human thymic epithelial neoplasms: A study of 146 consecutive tumors. Am J Surg Pathol. 25:103–110. 2001. View Article : Google Scholar : PubMed/NCBI
7	Falkson CB, Bezjak A, Darling G, Gregg R, Malthaner R, Maziak DE, Yu E, Smith CA, McNair S, Ung YC, et al: The management of thymoma: A systematic review and practice guideline. J Thorac Oncol. 4:911–919. 2009. View Article : Google Scholar : PubMed/NCBI
8	Jeong YJ, Lee KS, Kim J, Shim YM, Han J and Kwon OJ: Does CT of thymic epithelial tumors enable us to differentiate histologic subtypes and predict prognosis? AJR Am J Roentgenol. 183:283–289. 2004. View Article : Google Scholar : PubMed/NCBI
9	Marom EM, Milito MA, Moran CA, Liu P, Correa AM, Kim ES, Komaki R, Erasmus JJ, Hofstetter WL, Rice DC and Swisher SG: Computed tomography findings predicting invasiveness of thymoma. J Thorac Oncol. 6:1274–1281. 2011. View Article : Google Scholar : PubMed/NCBI
10	Liu GB, Qu YJ, Liao MY, Hu HJ, Yang GF and Zhou SJ: Relationship between computed tomography manifestations of thymic epithelial tumors and the WHO pathological classification. Asian Pac J Cancer Prev. 13:5581–5585. 2012. View Article : Google Scholar : PubMed/NCBI
11	Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, Zegers CM, Gillies R, Boellard R, Dekker A and Aerts HJ: Radiomics: Extracting more information from medical images using advanced feature analysis. Eur J Cancer. 48:441–446. 2012. View Article : Google Scholar : PubMed/NCBI
12	Kumar V, Gu Y, Basu S, Berglund A, Eschrich SA, Schabath MB, Forster K, Aerts HJ, Dekker A, Fenstermacher D, et al: Radiomics: The process and the challenges. Magn Reson Imaging. 30:1234–1248. 2012. View Article : Google Scholar : PubMed/NCBI
13	Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, et al: Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 5:40062014. View Article : Google Scholar : PubMed/NCBI
14	Braman NM, Etesami M, Prasanna P, Dubchuk C, Gilmore H, Tiwari P, Plecha D and Madabhushi A: Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res. 19:572017. View Article : Google Scholar : PubMed/NCBI
15	Kuo MD and Jamshidi N: Behind the numbers: Decoding molecular phenotypes with radio-genomics-Guiding principles and technical considerations. Radiology. 270:320–325. 2014. View Article : Google Scholar : PubMed/NCBI
16	Iannarelli A, Sacconi B, Tomei F, Anile M, Longo F, Bezzi M, Napoli A, Saba L, Anzidei M, D'Ovidio G, et al: Analysis of CT features and quantitative texture analysis in patients with thymic tumors: Correlation with grading and staging. Radiol Med. 123:345–350. 2018. View Article : Google Scholar : PubMed/NCBI
17	Priola AM, Priola SM, Di Franco M, Cataldi A, Durando S and Fava C: Computed tomography and thymoma: Distinctive findings in invasive and noninvasive thymoma and predictive features of recurrence. Radiol Med. 115:1–21. 2010.(In English, Italian). View Article : Google Scholar : PubMed/NCBI
18	Carter BW, Benveniste MF, Madan R, Godoy MC, Groot PM, Truong MT, Rosado-de-Christenson ML and Marom EM: IASLC/ITMIG staging system and lymph node map for thymic epithelial neoplasms. Radiographics. 37:758–776. 2017. View Article : Google Scholar : PubMed/NCBI
19	Landis JR and Koch GG: The measurement of observer agreement for categorical data. Biometrics. 33:159–174. 1977. View Article : Google Scholar : PubMed/NCBI
20	Shrout PE and Fleiss JL: Intraclass correlations: Uses in assessing rater reliability. Psychol Bull. 86:420–428. 1979. View Article : Google Scholar : PubMed/NCBI
21	Vickers AJ, Cronin AM, Elkin EB and Gonen M: Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers. BMC Med Inform Decis Mak. 8:532008. View Article : Google Scholar : PubMed/NCBI
22	Tomiyama N, Johkoh T, Mihara N, Honda O, Kozuka T, Koyama M, Hamada S, Okumura M, Ohta M, Eimoto T, et al: Using The World Health Organization classification of thymic epithelial neoplasms to describe CT findings. AJR Am J Roentgenol. 179:881–886. 2002. View Article : Google Scholar : PubMed/NCBI
23	Sadohara J, Fujimoto K, Müller NL, Kato S, Takamori S, Ohkuma K, Terasaki H and Hayabuchi N: Thymic epithelial tumors: Comparison of CT and MR imaging findings of low-risk thymomas, high-risk thymomas, and thymic carcinomas. Eur J Radiol. 60:70–79. 2006. View Article : Google Scholar : PubMed/NCBI
24	Tomiyama N, Müller NL, Ellis SJ, Cleverley JR, Okumura M, Miyoshi S, Kusumoto M, Johkoh T, Yoshida S, Mihara N, et al: Invasive and non-invasive thymoma: Distinctive CT features. J Comput Assist Tomogr. 25:388–393. 2001. View Article : Google Scholar : PubMed/NCBI
25	Choe J, Lee SM, Lim S, Choi SH, Kim N, Do KH and Seo JB: Doubling time of thymic epithelial tumours on CT: Correlation with histological subtype. Eur Radiol. 27:4030–4036. 2017. View Article : Google Scholar : PubMed/NCBI
26	Henschke CI, Lee IJ, Wu N, Farooqi A, Khan A, Yankelevitz D and Altorki NK: CT screening for lung cancer: Prevalence and incidence of mediastinal masses. Radiology. 239:586–589. 2006. View Article : Google Scholar : PubMed/NCBI
27	Detterbeck FC: Clinical value of the WHO classification system of thymoma. Ann Thorac Surg. 81:2328–2334. 2006. View Article : Google Scholar : PubMed/NCBI
28	Qu YJ, Liu GB, Shi HS, Liao MY, Yang GF and Tian ZX: Preoperative CT findings of thymoma are correlated with postoperative Masaoka clinical stage. Acad Radiol. 20:66–72. 2013. View Article : Google Scholar : PubMed/NCBI
29	Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, Sanduleanu S, Larue RTHM, Even AJG, Jochems A, et al: Radiomics: The bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 14:749–762. 2017. View Article : Google Scholar : PubMed/NCBI
30	Ma Z, Fang M, Huang Y, He L, Chen X, Liang C, Huang X, Cheng Z, Dong D, Liang C, et al: CT-based radiomics signature for differentiating Borrmann type IV gastric cancer from primary gastric lymphoma. Eur J Radiol. 91:142–147. 2017. View Article : Google Scholar : PubMed/NCBI
31	Kocak B, Ates E, Durmaz ES, Ulusan MB and Kilickesmez O: Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: A reproducibility study on renal clear cell carcinomas. Eur Radiol. 12:4765–4775. 2019. View Article : Google Scholar
32	Ma X, Wei J, Gu D, Zhu Y, Feng B, Liang M, Wang S, Zhao X and Tian J: Preoperative radiomics nomogram for microvascular invasion prediction in hepatocellular carcinoma using contrast-enhanced CT. Eur Radiol. 29:3595–3605. 2019. View Article : Google Scholar : PubMed/NCBI
33	Shen C, Liu Z, Guan M, Song J, Lian Y, Wang S, Tang Z, Dong D, Kong L, Wang M, et al: 2D and 3D CT radiomics features prognostic performance comparison in non-small cell lung cancer. Transl Oncol. 10:886–894. 2017. View Article : Google Scholar : PubMed/NCBI