Back to Search Start Over

Advanced biomedical imaging for accurate discrimination and prognostication of mediastinal masses.

Authors :
Mahmoudi S
Gruenewald LD
Eichler K
Martin SS
Booz C
Bernatz S
Lahrsow M
Yel I
Gotta J
Biciusca T
Mohammed H
Ziegengeist NS
Torgashov K
Hammerstingl RM
Sommer CM
Weber C
Almansour H
Bucolo G
D'Angelo T
Scholtz JE
Gruber-Rouh T
Vogl TJ
Koch V
Source :
European journal of clinical investigation [Eur J Clin Invest] 2023 Dec; Vol. 53 (12), pp. e14075. Date of Electronic Publication: 2023 Aug 12.
Publication Year :
2023

Abstract

Background: To investigate the potential of radiomic features and dual-source dual-energy CT (DECT) parameters in differentiating between benign and malignant mediastinal masses and predicting patient outcomes.<br />Methods: In this retrospective study, we analysed data from 90 patients (38 females, mean age 51 ± 25 years) with confirmed mediastinal masses who underwent contrast-enhanced DECT. Attenuation, radiomic features and DECT-derived imaging parameters were evaluated by two experienced readers. We performed analysis of variance (ANOVA) and Chi-square statistic tests for data comparison. Receiver operating characteristic curve analysis and Cox regression tests were used to differentiate between mediastinal masses.<br />Results: Of the 90 mediastinal masses, 49 (54%) were benign, including cases of thymic hyperplasia/thymic rebound (n = 10), mediastinitis (n = 16) and thymoma (n = 23). The remaining 41 (46%) lesions were classified as malignant, consisting of lymphoma (n = 28), mediastinal tumour (n = 4) and thymic carcinoma (n = 9). Significant differences were observed between benign and malignant mediastinal masses in all DECT-derived parameters (p ≤ .001) and 38 radiomic features (p ≤ .044) obtained from contrast-enhanced DECT. The combination of these methods achieved an area under the curve of .98 (95% CI, .893-1.000; p < .001) to differentiate between benign and malignant masses, with 100% sensitivity and 91% specificity. Throughout a follow-up of 1800 days, a multiparametric model incorporating radiomic features, DECT parameters and gender showed promising prognostic power in predicting all-cause mortality (c-index = .8 [95% CI, .702-.890], p < .001).<br />Conclusions: A multiparametric approach combining radiomic features and DECT-derived imaging biomarkers allows for accurate and noninvasive differentiation between benign and malignant masses in the anterior mediastinum.<br /> (© 2023 The Authors. European Journal of Clinical Investigation published by John Wiley & Sons Ltd on behalf of Stichting European Society for Clinical Investigation Journal Foundation.)

Details

Language :
English
ISSN :
1365-2362
Volume :
53
Issue :
12
Database :
MEDLINE
Journal :
European journal of clinical investigation
Publication Type :
Academic Journal
Accession number :
37571983
Full Text :
https://doi.org/10.1111/eci.14075