1. Quantitative texture analysis based on dynamic contrast enhanced MRI for differential diagnosis between primary thymic lymphoma from thymic carcinoma.
- Author
-
Zhu, Jia-jia, Shen, Jie, Zhang, Wei, Wang, Fen, Yuan, Mei, Xu, Hai, and Yu, Tong-fu
- Subjects
CONTRAST-enhanced magnetic resonance imaging ,DIFFERENTIAL diagnosis ,FEATURE extraction ,CARCINOMA ,LYMPHOMAS ,MAGNETIC resonance imaging ,RECEIVER operating characteristic curves ,CURVES - Abstract
To evaluate the value of texture analysis based on dynamic contrast enhanced MRI (DCE-MRI) in the differential diagnosis of thymic carcinoma and thymic lymphoma. Sixty-nine patients with pathologically confirmed (thymic carcinoma, n = 32; thymic lymphoma, n = 37) were enrolled in this retrospective study. K
trans , Kep and Ve maps were automatically generated, and texture features were extracted, including mean, median, 5th/95th percentile, skewness, kurtosis, diff-variance, diff-entropy, contrast and entropy. The differences in parameters between the two groups were compared and the diagnostic efficacy was calculated. The Ktrans -related significant features yielded an area under the curve (AUC) of 0.769 (sensitivity 90.6%, specificity 51.4%) for the differentiation between thymic carcinoma and thymic lymphoma. The Kep -related significant features yielded an AUC of 0.780 (sensitivity 87.5%, specificity 62.2%). The Ve -related significant features yielded an AUC of 0.807 (sensitivity 75.0%, specificity 78.4%). The combination of DCE-MRI textural features yielded an AUC of 0.962 (sensitivity 93.8%, specificity 89.2%). Five parameters were screened out, including age, Ktrans -entropy, Kep -entropy, Ve -entropy, and Ve -P95. The combination of these five parameters yielded the best discrimination efficiency (AUC of 0.943, 93.7% sensitivity, 81.1% specificity). Texture analysis of DCE-MRI may be helpful to distinguish thymic carcinoma from thymic lymphoma. [ABSTRACT FROM AUTHOR]- Published
- 2022
- Full Text
- View/download PDF