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.

Contrast-Enhanced CT-Based Radiomics Analysis in Predicting Lymphovascular Invasion in Esophageal Squamous Cell Carcinoma

“…Conventional CT images are primarily used to extract morphological information from tumor tissues, but recent researches have shown that quantitative CT texture features can provide additional information (19,20). Different from conventional CT image features, radiomics features can objectively reflect the heterogeneity of the tumor and allow more invisible information to be obtained (21,22). Increasing studies have demonstrated the incremental value of texture analysis and radiomics approaches in predicting tumor grading, staging, response to treatment, and survival for gastrointestinal carcinoma (23)(24)(25)(26).…”

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

“…4 a, b ROC curves comparing the radiomics model based on the TW1-2 sequence and the clinical model for the training cohort (a) and the validation cohort (b); c, d The discrimination and calibration of the radiomics model based on TW1-2 were validated by a decision curve and Hosmer-Lemeshow test features (n = 8). We inferred that the possible reason for the different performances may be because, compared with the model constructed by MLR, the model constructed by SVM is too complex to prevent overfitting [27].…”

“…However, the model constructed by MLR performed better than that constructed by SVM based on the T1WI features (n = 7) and T2WI features (n = 8). We inferred that the possible reason for the different performances may be because, compared with the model constructed by MLR, the model constructed by SVM is too complex to prevent over-fitting [ 27 ].…”

Radiomic model for differentiating parotid pleomorphic adenoma from parotid adenolymphoma based on MRI images

“…However, the model constructed by MLR performed better than that constructed by SVM based on the T1WI features (n=7) and T2WI features (n=8). We inferred the possible reason may be that, compared with the model constructed by MLR, the model constructed by SVM is too complex to avoid over-fitting [23] .…”