Radiomics Signature Facilitates Organ-Saving Strategy in Patients With Esophageal Squamous Cell Cancer Receiving Neoadjuvant Chemoradiotherapy

Abstract

After neoadjuvant chemoradiotherapy (NCRT) in locally advanced esophageal squamous cell cancer (ESCC), roughly 40% of the patients may achieve pathologic complete response (pCR). Those patients may benefit from organ-saving strategy if the probability of pCR could be correctly identified before esophagectomy. A reliable approach to predict pathological response allows future studies to investigate individualized treatment plans.

Method: All eligible patients treated in our center from June 2012 to June 2019 were retrospectively collected. Radiomics features extracted from pre-/post-NCRT CT images were selected by univariate logistic and LASSO regression. A radiomics signature (RS) developed with selected features was combined with clinical variables to construct RS+clinical model with multivariate logistic regression, which was internally validated by bootstrapping. Performance and clinical usefulness of RS+clinical model were assessed by receiver operating characteristic (ROC) curves and decision curve analysis, respectively.

Results: Among the 121 eligible patients, 51 achieved pCR (42.1%) after NCRT. Eighteen radiomics features were selected and incorporated into RS. The RS+clinical model has improved prediction performance for pCR compared with the clinical model (corrected area under the ROC curve, 0.84 vs. 0.70). At the 60% probability threshold cutoff (i.e., the patient would opt for observation if his probability of pCR was >60%), net 13% surgeries could be avoided by RS+clinical model, equivalent to implementing organ-saving strategy in 31.37% of the 51 true-pCR cases.

Conclusion: The model built with CT radiomics features and clinical variables shows the potential of predicting pCR after NCRT; it provides significant clinical benefit in identifying qualified patients to receive individualized organ-saving treatment plans.

Keywords: esophageal cancer; neoadjuvant chemoradiation; organ-saving treatment; radiomics; response prediction.

Figure 1

Radiomics feature selection using the penalized logistic regression model with LASSO penalty. (A) The tuning parameter lambda(λ) selection with 10 folds cross-validation and binomial deviance curve was plotted against log(λ). The selected model was built with λmin(0.020), equivalent to log(λ) = -3.92. (B) Lasso regression coefficients profile. Coefficients are plottted against log(λ) depicting the trend of approaching zero as λ increase.

Figure 2

Calibration plot of the clinical model (A) and RS+clinical model (B). The calibration curves of clinical model and RS+clinical model showing the difference between the predicted probability of pCR and the observed (actual) probability. The “Ideal” line represents the perfect prediction as the predicted probabilities equal to the observed probabilities. The “Apparent” curve is the calibration of the primary cohort. The “Bias-corrected” curve was the calibration created by internal validation of 2000-replicate bootstrap on the primary cohort.

Figure 3

ROC curve analysis. Receiver-operating-characteristic cuve analysis of the two models indicating their ability to discriminate between pCR and non-pCR patients. The blue line represents the ROC curve of the clinical model and the corrected AUC is 0.70; the red line represents the ROC curve of the RS+clinical model and the corrected AUC is 0.84.

Figure 4

Decision curve analysis. Decision curves depicting the net benefit (y-axis) of the two models at a range of probability thresholds (i.e., minimum probability of pCR above which a patient would opt for observation rather than surgery; x-axis). The yellow and blue solid lines represent making the same decision in all patients (i.e., Sparing surgery for all patients or performing surgery for all patients, respectively). The net benefit was corrected by internal validation of 2,000-replicate bootstrap.

Figure 5

Nomogram of RS+clinical model. The nomogram built based on radiomics signature and clinical variables provide an easy-to-use tool in clinical practice.