A radiomics model to predict the invasiveness of thymic epithelial tumors based on contrastenhanced computed tomography.
Oncol Rep
; 43(4): 1256-1266, 2020 04.
Article
em En
| MEDLINE
| ID: mdl-32323834
ABSTRACT
In the present study, we aimed to construct a radiomics model using contrastenhanced 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 highrisk TETs were assigned to training (90 tumors), internal validation (49 tumors) and external validation (40 tumors) cohorts. Radiomics features extracted from preoperative contrastenhanced 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 nonzero coefficients were used to develop a radiomics score, which significantly differed between low and highrisk TETs (P<0.001). The subjective finding, infiltration, was independently associated with highrisk 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) 0.6270.819; sensitivity, 85.7%; specificity, 60.4%], 88.9% (AUC, 0.944; 95% CI 0.8740.981; sensitivity, 92.9%; specificity, 85.4%), and 90.0% (AUC, 0.953; 95% CI 0.8870.987; sensitivity, 92.9%; specificity, 87.5%), respectively. Decisioncurve analysis showed that the combined model added more net benefit than the singleparameter models. In conclusion, a radiomics signature based on contrastenhanced CT has the potential to differentiate between low and highrisk TETs. The model incorporating the radiomics signature and subjective finding may facilitate the individualized, preoperative prediction of the pathological invasiveness of TETs.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Neoplasias do Timo
/
Interpretação de Imagem Radiográfica Assistida por Computador
/
Biomarcadores Tumorais
/
Tomografia Computadorizada por Raios X
/
Neoplasias Epiteliais e Glandulares
/
Meios de Contraste
Tipo de estudo:
Etiology_studies
/
Observational_studies
/
Prognostic_studies
/
Risk_factors_studies
Limite:
Adult
/
Aged
/
Aged80
/
Female
/
Humans
/
Male
/
Middle aged
Idioma:
En
Revista:
Oncol Rep
Ano de publicação:
2020
Tipo de documento:
Article