CT radiomic features for predicting resectability of oesophageal squamous cell carcinoma as given by feature analysis: a case control study

Abstract

Background: Computed tomography (CT) is commonly used in all stages of oesophageal squamous cell carcinoma (SCC) management. Compared to basic CT features, CT radiomic features can objectively obtain more information about intratumour heterogeneity. Although CT radiomics has been proved useful for predicting treatment response to chemoradiotherapy in oesophageal cancer, the best way to use CT radiomic biomarkers as predictive markers for determining resectability of oesophageal SCC remains to be developed. This study aimed to develop CT radiomic features related to resectability of oesophageal SCC with five predictive models and to determine the most predictive model.

Methods: Five hundred ninety-one patients with oesophageal SCC undergoing contrast-enhanced CT were enrolled in this study, and were composed by 270 resectable cases and 321 unresectable cases. Of the 270 resectable oesophageal SCCs, 91 cases were primary resectable tumours; and the remained 179 cases received neoadjuvant therapy after CT, shrank on therapy, and changed to resectable tumours. Four hundred thirteen oesophageal SCCs including 189 resectable cancers and 224 unresectable cancers were randomly allocated to the training cohort; and 178 oesophageal SCCs including 81 resectable tumours and 97 unresectable tumours were allocated to the validation group. Four hundred ninety-five radiomic features were extracted from CT data for identifying resectability of oesophageal SCC. Useful radiomic features were generated by dimension reduction using least absolute shrinkage and selection operator. The optimal radiomic features were chosen using multivariable logistic regression, random forest, support vector machine, X-Gradient boost and decision tree classifiers. Discriminating performance was assessed with area under receiver operating characteristic curve (AUC), accuracy and F-1score.

Results: Eight radiomic features were selected to create radiomic models related to resectability of oesophageal SCC (P-values < 0.01 for both cohorts). Multivariable logistic regression model showed the best performance (AUC = 0.92 ± 0.04 and 0.87 ± 0.02, accuracy = 0.87 and 0.86, and F-1score = 0.93 and 0.86 in training and validation cohorts, respectively) in comparison with any other model (P-value < 0.001). Good calibration was observed for multivariable logistic regression model.

Conclusion: CT radiomic models could help predict resectability of oesophageal SCC, and multivariable logistic regression model is the most predictive model.

Keywords: Computed tomography; Diagnosis; Esophagectomy; Esophagus; Squamous cell carcinoma.

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1

The CT data flow sequence in this research. Tumour contours are segmented manually by slice-by-slice delineating. In the training cohort, we select the extracted features depending on some rules. Based on the selected features, we build and validate the radiomic indicators. Ultimately, this research reveals that resectability of oesophageal squamous cell carcinoma is correlated with the radiomic indicators. LASSO, least absolute shrinkage and selection operator

Fig. 2

The tumour contours are segmented manually on thoracic contrast-enhanced CT image

Fig. 3

The least absolute shrinkage and selection operator (LASSO) binary logistic regression model used to select texture feature. a Tuning parameter (λ) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The area under the receiver operating characteristic curve (AUC) is plotted versus log(λ). Dotted vertical lines are drawn at the optimal values by using the minimum criteria and the 1 standard error of the minimum criteria (the 1-SE criteria). log(λ) = −6.214, with λ chosen of 0.02. b LASSO coefficient profiles of the 483 texture features. A coefficient profile plot is produced against the log(λ) sequence. Vertical line is drawn at the value selected using 10-fold cross-validation, where optimal λ results in 42 non-zero coefficients

Fig. 4

The receiver operating characteristic (ROC) curves of the multivariable logistic regression, random forest, support vector machine, X-Gradient boost, and decision tree demonstrate the determination of resectability of oesophageal squamous cell carcinoma in the validation cohort. XGboost = X-Gradient boost

Fig. 5

Calibration curves of the multivariable logistic regression, random forest, support vector machine, X-Gradient boost, and decision tree are for the prediction of resectability of oesophageal squamous cell carcinoma in the validation cohort. Actual and Predicted represent real and predicted oesophageal squamous cell carcinoma resection rates, respectively. XGboost = X-Gradient boost