CT radiomics prediction of CXCL9 expression and survival in ovarian cancer

Abstract

Background: C-X-C motif chemokine ligand 9 (CXCL9), which is involved in the pathological processes of various human cancers, has become a hot topic in recent years. We developed a radiomic model to identify CXCL9 status in ovarian cancer (OC) and evaluated its prognostic significance.

Methods: We analyzed enhanced CT scans, transcriptome sequencing data, and corresponding clinical characteristics of CXCL9 in OC using the TCIA and TCGA databases. We used the repeat least absolute shrinkage (LASSO) and recursive feature elimination(RFE) methods to determine radiomic features after extraction and normalization. We constructed a radiomic model for CXCL9 prediction based on logistic regression and internal tenfold cross-validation. Finally, a 60-month overall survival (OS) nomogram was established to analyze survival data based on Cox regression.

Results: CXCL9 mRNA levels and several other genes involving in T-cell infiltration were significantly relevant to OS in OC patients. The radiomic score (rad_score) of our radiomic model was calculated based on the five features for CXCL9 prediction. The areas under receiver operating characteristic (ROC) curves (AUC-ROC) for the training cohort was 0.781, while that for the validation cohort was 0.743. Patients with a high rad_score had better overall survival (P < 0.001). In addition, calibration curves and decision curve analysis (DCA) showed good consistency between the prediction and actual observations, demonstrating the clinical utility of our model.

Conclusion: In patients with OC, the radiomics signature(RS) of CT scans can distinguish the level of CXCL9 expression and predict prognosis, potentially fulfilling the ultimate purpose of precision medicine.

Keywords: CXCL9; Ovarian cancer; Overall survival; Prognosis; Radiomics.

Fig. 1

CXCL9 expression comparison, survival analysis, Cox regression analysis of TCGA-OV cohort. A The expression level of CXCL9 in OC tissues was signifcantly higher than that in normal tissues; B The Kaplan–Meier curve showed that high CXCL9 expression was significantly associated with improvement in patients’ OS; C Univariate and multivariate COX regression demonstrated the protective impact of high CXCL9 expression on the OS.* P < 0.05, ** P < 0.01, *** P < 0.001

Fig. 2

Univariate subgroup analysis and interaction test. High CXCL9 expression level was protective in OC patients aged < 60 years or accepted chemotherapy. Age and CXCL9 expression, chemotherapy and CXCL9 expression had no significant interaction effects on the OS

Fig. 3

Relationship analysis between CXCL9 expression level and clinical characteristics, immuno-infiltrations analysis. A High CXCL9 expression was positively associated with the lymphatic invasion; B The expression levels of CD44, TNFRSF9 and LAG3 were significantly increased in the CXCL9-high group;C CXCL9 was positively correlated with CD8 + T cell infiltration abundance.* P < 0.05, ** P < 0.01, *** P < 0.001

Fig. 4

Feature selection of the radiomic model.A Features histogram;B Feature reduction in the repeat LASSO logistic regression model;C Five optimal features:glcm_Idn, gldm_DependenceNonUniformityNormalized, shape_SurfaceVolumeRatio, glcm_ClusterProminence and shape_SurfaceArea

Fig. 5

Evaluation of the radiomic model for prediction of CXCL9 expression: A Receiver operating characteristic(ROC) curves in the training set and the validation set; B Precision recall(PR) curves in the training set;C calibration curves;D Decision curve analysis(DCA); E Box plots of predicted probabilities in CXCL9-high and CXCL9-low groups

Fig. 6

Nomogram and model evaluation. A Creation of the nomogram to predict the overall survival of a patient with ovarian cancer. B Calibration curves of the risk score; C The time-dependent ROC of the risk score; D DCA