Intratumoral and peritumoral PET/CT-based radiomics for non-invasively and dynamically predicting immunotherapy response in NSCLC

Abstract

Background: We aimed to develop a machine learning model based on intratumoral and peritumoral ¹⁸F-FDG PET/CT radiomics to non-invasively and dynamically predict the response to immunotherapy in non-small cell lung cancer (NSCLC).

Methods: This retrospective study included 296 NSCLC patients, including a training cohort (N = 183), a testing cohort (N = 78), and a TCIA radiogenomic cohort (N = 35). The extreme gradient boosting algorithm was employed to develop the radiomic models.

Results: The COMB-Radscore, which was developed by combining radiomic features from PET, CT, and PET/CT images, had the most satisfactory predictive performance with AUC (ROC) 0.894 and 0.819 in the training and testing cohorts, respectively. Survival analysis has demonstrated that COMB-Radscore is an independent prognostic factor for progression-free survival and overall survival. Moreover, COMB-Radscore demonstrates excellent dynamic predictive performance, with an AUC (ROC) of 0.857, enabling the earlier detection of potential disease progression in patients compared to radiological evaluation solely relying on tumor size. Further radiogenomic analysis showed that the COMB-Radscore was associated with infiltration abundance and functional status of CD8 + T cells.

Conclusions: The radiomic model holds promise as a precise, personalized, and dynamic decision support tool for the treatment of NSCLC patients.

Fig. 1. Overall study design.

VOI volume of interest, GLCM gray-level co-occurrence matrix, GLDM gray-level dependence matrix, GLRLM gray-level run-length matrix, GLSZM gray-level size-zone matrix, NGTDM neighboring gray-tone difference matrix, ICC intraclass/interclass correlation coefficient, mRMR minimum redundancy maximum relevance, LASSO least absolute shrinkage and selection operator, RFE recursive feature elimination, XGBoost extreme gradient boosting, COMB-Radscore combined Radscore, ROC curves receiver operating characteristic curves, AUC area under the curve, CI confidence interval, HR hazard ratio, DCB durable clinical benefit, NDB no durable clinical benefit, PD-L1 (TPS) programmed cell death ligand 1 (tumor proportion score), RNASeq RNA sequencing, mIF multiplex immunofluorescence.

Fig. 2. Performance evaluation of prediction models.

ROC curves (a), calibration curves (b), decision curves (c) and PR curves (d) of the four radiomic models in the testing cohort. e Difference in COMB-Radscore between DCB and NDB groups in the testing cohort. f Response (DCB/NDB) and COMB-Radscore for each patient in the testing cohort. ROC curves receiver operating characteristic curves, PR curves precision-recall curves, AUC area under the curve, CI confidence interval, DCB durable clinical benefit, NDB no durable clinical benefit.

Fig. 3. Clinical utility of the COMB-Radscore.

Kaplan-Meier analysis of PFS (a) and OS (b) for the low and high COMB-Radscore groups in the training (left) and testing (right) cohorts. c Proportional composition of different patient responses between the low and high COMB-Radscore groups in the training (left) and testing (right) cohorts. HR hazard ratio, CI confidence interval, PFS progression-free survival, OS overall survival, CR complete response, PR partial response, SD stable disease, PD progressive disease. The definitions of CR, PR, SD, and PD were based on the RECIST V.1.1 criteria.

Fig. 4. Dynamic predictive ability of and changes in COMB-Radscore.

a ROC curve of COMB-Radscore (Follow-up) in the follow-up cohort. b Kaplan-Meier analysis of PFS (Follow-up) for low and high COMB-Radscore (Follow-up) groups in the follow-up cohort. c Changes in COMB-Radscore of patients in the DCB (Follow-up) group and NDB (Follow-up) group. d Changes in COMB-Radscore of two representative patients during treatment. ROC curve receiver operating characteristic curve, AUC area under the curve, CI confidence interval, HR hazard ratio, DCB durable clinical benefit, NDB no durable clinical benefit, PFS progression-free survival, BOR best overall response, PR partial response, PD progressive disease.

Fig. 5. Complementarity between COMB-Radscore and TPS-Lung.

a ROC curve of TPS-Lung in the COMB-Radscore prediction failure cohort. b ROC curve of COMB-Radscore in the TPS-Lung prediction failure cohort. c Kaplan-Meier analysis of PFS of four groups of patients stratified by COMB-Radscore and TPS-Lung. d ROC curves of the TPS-Radscore, COMB-Radscore, and TPS-Lung in the sub-training (left) and sub-testing (right) cohorts. ROC curves, receiver operating characteristic curves, AUC, area under the curve, CI confidence interval, HR hazard ratio, PFS progression-free survival, TPS tumor proportion score.

Fig. 6. Differences in the tumor immune microenvironment between low and high COMB-Radscore groups.

Difference in four immune phenotype scores (a), abundances of 22 immune cells (b), cytolytic activity and T-cell–inflamed GEP score (c) between the low and high COMB-Radscore groups in the Internal radiogenomics cohort. d Difference in CD3 + CD8 + T cells, CD3 + CD8 + PRF1 + T cells, CD3 + CD8 + PD1 + T cells, and CD3 + CD8 + PD1 + PRF1 + T cells between the low and high COMB-Radscore groups in the Multiple immunofluorescence cohort. e Micrographs of the multiplex immunofluorescence for two representative patients. MHC major histocompatibility complex, EC effector cells, SC suppressor cells, CP checkpoints, IPS immunophenoscore, GEP gene expression profile, DAPI 4′,6-diamidino-2-phenylindole, CD3 cluster of differentiation 3, CD8 cluster of differentiation 8, PRF1 perforin-1, PD1 programmed cell death protein 1.