Delta radiomics model for the prediction of progression-free survival time in advanced non-small-cell lung cancer patients after immunotherapy

Abstract

Objective: To assess the validity of pre- and posttreatment computed tomography (CT)-based radiomics signatures and delta radiomics signatures for predicting progression-free survival (PFS) in stage III-IV non-small-cell lung cancer (NSCLC) patients after immune checkpoint inhibitor (ICI) therapy.

Methods: Quantitative image features of the largest primary lung tumours were extracted on CT-enhanced imaging at baseline (time point 0, TP0) and after the 2^nd-3^rd immunotherapy cycles (time point 1, TP1). The critical features were selected to construct TP0, TP1 and delta radiomics signatures for the risk stratification of patient survival after ICI treatment. In addition, a prediction model integrating the clinicopathologic risk characteristics and phenotypic signature was developed for the prediction of PFS.

Results: The C-index of TP0, TP1 and delta radiomics models in the training and validation cohort were 0.64, 0.75, 0.80, and 0.61, 0.68, 0.78, respectively. The delta radiomics score exhibited good accuracy for distinguishing patients with slow and rapid progression to ICI treatment. The predictive accuracy of the combined prediction model was higher than that of the clinical prediction model in both training and validation sets (P<0.05), with a C-index of 0.83 and 0.70, respectively. Additionally, the delta radiomics model (C-index of 0.86) had a higher predictive accuracy compared to PD-L1 expression (C-index of 0.50) (P<0.0001).

Conclusions: The combined prediction model including clinicopathologic characteristics (tumour anatomical classification and brain metastasis) and the delta radiomics signature could achieve the individualized prediction of PFS in ICIs-treated NSCLC patients.

Keywords: delta; immunity; non-small-cell lung cancer; prediction model; radiomics.

Figure 1

(A) Tumour segmentation. The figure shows baseline CT images of target lesions and CT images after 2-3 cycles of treatment, tumour contours and three-dimensional visualizations. (B) TP0, TP1 and delta RMs were established based on pretherapy, posttherapy and delta RFs. (C) The best RM was selected for the risk stratification of drug resistance, while a nomogram was established for individualized prognosis prediction. (D) All prediction models were validated in the validation cohort.

Figure 2

LASSO Cox regression model for delta radiomics feature screening. (A) The dashed line on the left side of the horizontal coordinate represents the selection of the best log(λ) = -1.8905 in the model by tenfold cross-validation. (B) Coefficient convergence plots of the screened features, with black vertical lines corresponding to the best log(λ) values, screened for 12 nonzero coefficients of delta RFs.

Figure 3

Distribution of delta radiomics scores in the training cohort (A) and validation cohort (B). Delta radiomics scores above the cut-off value were categorized as the RP subgroup (red), and delta radiomics scores below the cut-off value were categorized as the SP subgroup (blue). There was an obvious difference in the distribution of the Delta Rad-score between the RP and SP subgroups.

Figure 4

Kaplan–Meier survival analysis was performed in the training cohort (A) and validation cohort (B), and PFS was markedly lower in the RP subgroup (yellow curve) than in the SP subgroup (blue curve). Statistical difference was assessed using the log-rank test.

Figure 5

Nomogram to predict the 7-month and one-year PFS probabilities of NSCLC patients after ICI treatment.

Figure 6

Calibration curves showing an excellent agreement between the predictions and observations of the 7-month and 1-year NSCLC progression probabilities in the training cohort (A) and validation cohort (B).

Figure 7

Comparison of the net benefits of the combined prediction model (green), delta radiomics prediction model (blue) and clinical prediction model (purple) using decision curve analysis.