Rationale and Objectives
To investigate the diagnostic value of radiomics features and dual-source dual-energy
CT (DECT) based material decomposition in differentiating low-risk thymomas, high-risk
thymomas, and thymic carcinomas.
Materials and Methods
This retrospective study included 32 patients (16 males, mean age 66 ± 14 years) with
pathologically confirmed thymic masses who underwent contrast-enhanced DECT between
10/2014 and 01/2023. Two experienced readers evaluated all patients regarding conventional
radiomics features, as well as DECT-based features, including attenuation (HU), iodine
density (mg/mL), and fat fraction (%). Data comparisons were performed using analysis
of variance and chi-square statistic tests. Receiver operating characteristic curve
analysis and Cox-regression tests were used to discriminate between low-risk/high-risk
thymomas and thymic carcinomas.
Results
Of the 32 thymic tumors, 12 (38%) were low-risk thymomas, 11 (34%) were high-risk
thymomas, and 9 (28%) were thymic carcinomas. Values differed significantly between
low-risk thymoma, high-risk thymoma, and thymic carcinoma regarding DECT-based features
(p ≤ 0.023) and 30 radiomics features (p ≤ 0.037). The area under the curve to differentiate between low-risk/high-risk thymomas
and thymic cancer was 0.998 (95% CI, 0.915–1.000; p < 0.001) for the combination of DECT imaging parameters and radiomics features, yielding
a sensitivity of 100% and specificity of 96%. During a follow-up of 60 months (IQR,
35–60 months), the multiparametric approach including radiomics features, DECT parameters,
and clinical parameters showed an excellent prognostic power to predict all-cause
mortality (c-index = 0.978 [95% CI, 0.958–0.998], p = 0.003).
Conclusion
A multiparametric approach including conventional radiomics features and DECT-based
features facilitates accurate, non-invasive discrimination between low-risk/high-risk
thymomas and thymic carcinomas.
Abbreviations:
AUC (Area under the curve), CI (Confidence interval), DECT (Dual-energy computed tomography), DICOM (Digital Imaging and Communications in Medicine), GLCM (Gray-Level Co-Occurrence Matrix), GLDM (Gray-Level Dependence Matrix), GLRLM (Grey-Level Run Length Matrix), GLSZM (Gray-Level Size Zone Matrix), HR (Hazard ratio), HU (Hounsfield unit), NGTDM (Neighboring Gray Tone Difference Matrix), NID (Normalized iodine density), ROC (Receiver operating characteristic), ROI (Region of interest), VOI (Volume of interest)Key Words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Academic RadiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Residual cervical thymus: a normal CT finding that may be present throughout patients’ lives.AJNR Am J Neuroradiol. 2015; 36: 1525-1528https://doi.org/10.3174/ajnr.A4304
- Advancement in diagnostic imaging of thymic tumors.Cancers (Basel). 2021; 13: 3599https://doi.org/10.3390/cancers13143599
- Computed tomography and magnetic resonance imaging of mediastinal tumors.J Magn Reson Imaging. 2010; 32: 1325-1339https://doi.org/10.1002/JMRI.22377
- Age-related changes in CT attenuation of the thymus in children.Pediatr Radiol. 2000; 30: 566-569https://doi.org/10.1007/s002470000245
- Epidemiology of thymoma and associated malignancies.J Thorac Oncol. 2010; 5: S260-S265https://doi.org/10.1097/JTO.0b013e3181f1f62d
- Computed tomography (CT)-derived radiomic features differentiate prevascular mediastinum masses as thymic neoplasms versus lymphomas.Radiol Med. 2020; 125: 951-960https://doi.org/10.1007/s11547-020-01188-w
- Age-related thymic activity in adults following chemotherapy-induced lymphopenia.Eur J Clin Invest. 2005; 35: 380-387https://doi.org/10.1111/j.1365-2362.2005.01499.x
- Evaluation of thymic changes after median sternotomy in children.Iran J Med Sci. 2014; 39 (Accessed November 21, 2022): 289-292
- Comparison between CT and MRI in the diagnostic accuracy of thymic masses.J Cancer. 2019; 10: 3208-3213https://doi.org/10.7150/jca.30240
- Update in diagnostic imaging of the thymus and anterior mediastinal masses.Gland Surg. 2019; 8: S188-S207https://doi.org/10.21037/gs.2019.05.06
- Surgical, radiation, and systemic treatments of patients with thymic epithelial tumours: a clinical practice guideline.J Thorac Oncol. 2022; 18: 299-312https://doi.org/10.1016/j.jtho.2022.08.007
- Radiomics: images are more than pictures, they are data.Radiology. 2016; 278: 563-577https://doi.org/10.1148/radiol.2015151169
- The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges.Theranostics. 2019; 9: 1303-1322https://doi.org/10.7150/thno.30309
- Radiomics improves cancer screening and early detection.Cancer Epidemiol Biomarkers Prev. 2020; 29: 2556-2567https://doi.org/10.1158/1055-9965.EPI-20-0075
- CT radiomics in thoracic oncology: technique and clinical applications.Nucl Med Mol Imaging. 2018; 52: 91-98https://doi.org/10.1007/s13139-017-0506-5
- Management of thymic tumors: a survey of current practice among members of the European Society of Thoracic Surgeons.J Thorac Oncol. 2011; 6: 614-623https://doi.org/10.1097/JTO.0b013e318207cd74
- Diagnostic accuracy of color-coded virtual noncalcium reconstructions derived from portal venous phase dual-energy CT in the assessment of lumbar disk herniation.Eur Radiol. 2022; 32: 2168-2177https://doi.org/10.1007/s00330-021-08354-2
- Assessment of thoracic disk herniation by using virtual noncalcium dual-energy CT in comparison with standard grayscale CT.Eur Radiol. 2021; 31: 9221-9231https://doi.org/10.1007/s00330-021-07989-5
- Dual-energy computed tomography: advantages in the acute setting.Radiol Clin North Am. 2015; 53 (vii): 619-638https://doi.org/10.1016/j.rcl.2015.02.016
- Dual-energy CT-based iodine quantification to differentiate abdominal malignant lymphoma from lymph node metastasis.Eur J Radiol. 2018; 105: 255-260https://doi.org/10.1016/j.ejrad.2018.06.017
- The World Health Organization histologic classification system reflects the oncologic behavior of thymoma: a clinical study of 273 patients.Cancer. 2002; 94: 624-632https://doi.org/10.1002/cncr.10226
- Computational radiomics system to decode the radiographic phenotype.Cancer Res. 2017; 77: e104-e107https://doi.org/10.1158/0008-5472.CAN-17-0339
- 3D Slicer as an image computing platform for the Quantitative Imaging Network.Magn Reson Imaging. 2012; 30: 1323-1341https://doi.org/10.1016/j.mri.2012.05.001
- A guideline of selecting and reporting intraclass correlation coefficients for reliability research.J Chiropr Med. 2016; 15: 155-163https://doi.org/10.1016/j.jcm.2016.02.012
- Can computed tomography-based radiomics potentially discriminate between anterior mediastinal cysts and type B1 and B2 thymomas.Biomed Eng Online. 2020; 19: 89https://doi.org/10.1186/s12938-020-00833-9
- CT imaging-based machine learning model: a potential modality for predicting low-risk and high-risk groups of thymoma: “impact of surgical modality choice”.World J Surg Oncol. 2021; 19: 147https://doi.org/10.1186/s12957-021-02259-6
- Safe use of contrast media: what the radiologist needs to know.Radiographics. 2015; 35: 1738-1750https://doi.org/10.1148/rg.2015150033
- Dual energy CT in clinical routine: how it works and how it adds value.Emerg Radiol. 2021; 28: 103-117https://doi.org/10.1007/s10140-020-01785-2
- Dual-energy CT: new horizon in medical imaging.Korean J Radiol. 2017; 18: 555-569https://doi.org/10.3348/kjr.2017.18.4.555
- Dual-energy CT: oncologic applications.AJR Am J Roentgenol. 2012; 199: S98-S105https://doi.org/10.2214/AJR.12.9207
- Dual-energy CT perfusion imaging for differentiating invasive thymomas, thymic carcinomas, and lymphomas in adults.Clin Radiol. 2022; 77: e417-e424https://doi.org/10.1016/j.crad.2022.02.012
- Iodine quantification using dual-energy computed tomography for differentiating thymic tumors.J Comput Assist Tomogr. 2018; 42: 873-880https://doi.org/10.1097/RCT.0000000000000800
- Management of thymic tumors: a survey of current practice among members of the European Society of Thoracic Surgeons.J Thorac Oncol. 2011; 6: 614-623https://doi.org/10.1097/JTO.0b013e318207cd74
- Diagnostic accuracy of image-guided percutaneous fine needle aspiration biopsy of the mediastinum.Diagn Cytopathol. 2007; 35: 705-709https://doi.org/10.1002/dc.20738
- Thymoma. A clinicopathologic review.Cancer. 1987; 60: 2727-2743https://doi.org/10.1002/1097-0142(19871201)60:11<2727::aid-cncr2820601125>3.0.co;2-d
- Management of thymic tumors: a survey of current practice among members of the European Society of Thoracic Surgeons.J Thorac Oncol. 2011; 6: 614-623https://doi.org/10.1097/JTO.0b013e318207cd74
Article info
Publication history
Published online: April 25, 2023
Accepted:
March 23,
2023
Received in revised form:
March 22,
2023
Received:
February 15,
2023
Publication stage
In Press Corrected ProofIdentification
Copyright
© 2023 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved All rights reserved.
