Dataset Information

Dynamic contrast-enhanced MRI can quantitatively identify malignant transformation of sinonasal inverted papilloma.

ABSTRACT:

Objective

To investigate the diagnostic performance of quantitative and semi-quantitative parameters derived from dynamic contrast-enhanced MRI (DCE-MRI) in differentiating sinonasal inverted papilloma (SIP) from SIP with coexisting malignant transformation into squamous cell carcinoma (MT-SIP).

Methods

This retrospective study included 122 patients with 88 SIP and 34 MT-SIP. Quantitative and semi-quantitative parameters derived from DCE-MRI were compared between SIP and MT-SIP. The multivariate logistic regression analysis was performed to identify independent indicators and construct regression model for distinguishing MT-SIP and SIP. Diagnostic performance of independent indicators and regression model were evaluated using receiver operating coefficient (ROC) analysis and compared using DeLong test.

Results

There were significant differences in maximum slope of increase, contrast-enhancement ratio, bolus arrival time, volume of extravascular extracellular space (V_e), and rate constant (K_ep) between SIP and MT-SIP (p < 0.05). There were no significant differences in initial area under the gadolinium curve (p = 0.174) and volume transfer constant (p = 0.105) between two groups. Multivariate analysis results showed that V_e and K_ep were identified as the independent indicators for differentiating MT-SIP from SIP (p < 0.001). Areas under the ROC curves (AUCs) for predicting MT-SIP were 0.779 for V_e and 0.766 for K_ep. The AUC of the combination of V_e and K_ep was 0.831, yielding 83% specificity and 76.5% sensitivity.

Conclusion

DCE-MRI can quantitatively differentiate between MT-SIP and SIP. The combination of V_e and K_ep yielded an optimal performance for discriminating SIP from its malignant mimics.

Advances in knowledge

DCE-MRI with quantitative and semi-quantitative parameters can provide valuable evidences for quantitatively identifying MT-SIP.

SUBMITTER: Li Z

PROVIDER: S-EPMC10996421 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Dynamic contrast-enhanced MRI can quantitatively identify malignant transformation of sinonasal inverted papilloma.

Li Zheng Z Xian Mu M Guo Jian J Wang Cheng Shuo CS Zhang Luo L Xian Junfang J

The British journal of radiology 20220303 1134

<h4>Objective</h4>To investigate the diagnostic performance of quantitative and semi-quantitative parameters derived from dynamic contrast-enhanced MRI (DCE-MRI) in differentiating sinonasal inverted papilloma (SIP) from SIP with coexisting malignant transformation into squamous cell carcinoma (MT-SIP).<h4>Methods</h4>This retrospective study included 122 patients with 88 SIP and 34 MT-SIP. Quantitative and semi-quantitative parameters derived from DCE-MRI were compared between SIP and MT-SIP. T ...[more]

PMID: 35234501

Similar Datasets

Project description:Objective To explore the best MRI radiomics-based machine learning model for differentiation of sinonasal inverted papilloma (SNIP) and malignant sinonasal tumor (MST), and investigate whether the combination of radiomics features and clinic–radiological features can produce a superior diagnostic performance. Methods The database of 247 patients with SNIP (n=106) or MST (n=141) were analyzed. Dataset from scanner A were randomly divided into training set (n=135) and test set 1 (n=58) in a ratio of 7:3, and dataset from scanner B and C were used as an additional independent test set 2 (n=54). Fourteen clinic-radiological features were analyzed by using univariate analysis, and those with significant differences were applied to construct clinical model. Based on the radiomics features extracted from single sequence (T2WI or CE-T1WI) and combined sequence, four commonly used classifiers (logistic regression (LR), support vector machine (SVM), decision tree (DT) and k-nearest neighbor (KNN)) were employed to constitute twelve different machine learning models, and the best-performing one was confirmed as the optimal radiomics model. Furthermore, a combined model incorporated best radiomics feature subsets and clinic-radiological features was developed. The diagnostic performances of these models were assessed by the area under the receiver operating characteristic (ROC) curve (AUC) and the calibration curves. Results Five clinic-radiological features (age, convoluted cerebriform pattern sign, heterogeneity, adjacent bone involvement and infiltration of surrounding tissue) were considered to be significantly different between the tumor groups (P < 0.05). Among the twelve machine learning models, the T2WI-SVM model exhibited optimal predictive efficacy for classification tasks on the two test sets, with the AUC of 0.878 and 0.914, respectively. For three types of diagnostic models, the combined model achieved highest AUC of 0.912 (95%CI: 0.807-0.970) and 0.927 (95%CI: 0.823-0.980) for differentiation of SNIP and MST in test 1 and test 2 sets, which performed prominently better than clinical model (P=0.011, 0.005), but not significantly different from the optimal radiomics model (P=0.100, 0.452). Conclusion The machine learning model based on T2WI sequence and SVM classifier achieved best performance in differentiation of SNIP and MST, and the combination of radiomics features and clinic-radiological features significantly improved the diagnostic capability of the model.

Project description:BackgroundDNA methylation may be involved in the regulation of malignant transformation from sinonasal inverted papilloma (SNIP) to squamous cell carcinoma (SCC). The study of gene methylation changes and screening of differentially methylated loci (DMLs) are helpful to predict the possible key genes in the malignant transformation of SNIP-SCC.Materials and methodsMicroarray dataset GSE125399 was downloaded from the Gene Expression Omnibus (GEO) database and differentially methylated loci (DMLs) were analyzed using R language (Limma package). ClusterProfiler R package was used to perform Gene Ontology (GO) analysis on up-methylated genes and draw bubble maps. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway and its visualization analysis were analyzed to speculate the possible key Genes in SNIP-SCC malignant transformation. Subsequently, SNIP cases archived in our department were collected, tissue microarray was made, and immunohistochemical staining was performed to analyze the expression levels of UCKL1, GSTT1, HLA-G, MAML2 and NRGN in different grades of sinonasal papilloma tissues.ResultsAnalysis of dataset GSE125399 identified 56 DMLs, including 49 upregulated DMLs and 7 downregulated DMLs. Thirty-one genes containing upregulated DNA methylation loci and three genes containing downregulated DNA methylation loci were obtained by methylation microarray annotation analysis. In addition, KEGG pathway visualization analysis of 31 up-methylated genes showed that there were four significantly up-methylated genes including UCKL1, GSTT1, HLA-G and MAML2, and one significantly down-methylated gene NRGN. Subsequently, compared with non-neoplasia nasal epithelial tissues, the expression of HLA-G and NRGN was upregulated in grade I, II, III and IV tissues, while the expression of MAML2 was lost. The protein expression changes of MAML2 and NRGN were significantly negatively correlated with their gene methylation levels.ConclusionsBy analyzing the methylation dataset, we obtained four up-regulated methylation genes UCKL1, GSTT1, HLA-G and MAML2 and one down-regulated gene NRGN. MAML2, a tumor suppressor gene with high methylation modification but loss of protein expression, and NRGN, a tumor gene with low methylation modification but upregulated protein expression, can be used as biological indicators to judge the malignant transformation of SNIP-SCC.

Dataset Information

Dynamic contrast-enhanced MRI can quantitatively identify malignant transformation of sinonasal inverted papilloma.

Objective

Methods

Results

Conclusion

Advances in knowledge

Publications

Dynamic contrast-enhanced MRI can quantitatively identify malignant transformation of sinonasal inverted papilloma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets