Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response

Backgrounds: : Since breast cancer patients respond diversely to immunotherapy, exploration of novel biomarkers for precisely predicting clinical response are urgently required to enhance therapeutic efficacy. The purpose of our present research was to construct and independently validate a biomarker of tumor microenvironment (TME) phenotypes via a machine learning-based radiomics way. The interrelationship between the biomarker, TME phenotypes and recipients’ clinical response would also be revealed. Methods In this retrospective multi-cohort investigation, five separate cohorts of breast cancer patients were recruited to measure breast cancer TME phenotypes via a radiomics signature, which was constructed and validated by integrating RNA-seq data with DCE-MRI images for predicting immunotherapy response. Initially, we constructed TME phenotypes using RNA-seq of 1089 breast cancer patients in the TCGA database. Then, parallel DCE-MRI images and RNA-seq of 94 breast cancer patients obtained from TCIA were applied to develop a radiomics-based TME phenotypes signature by Random Forest in machine learning. In an internal validation set, the repeatability of radiomics signature was validated. Two additional independent external validation sets were analyzed to reassess this signature. The Immune phenotype cohort (n = 158) divided enrolled subjects into immune-inflamed and immune-desert phenotypes based on CD8 cell infiltration; these data were utilized to examine the relationship between the immune phenotypes and this signature. A final Immunotherapy-treated cohort with 77 cases who received anti-PD-1/PD-L1 treatment was utilized to evaluate the predictive efficiency of this signature in terms of clinical outcomes. Results The TME phenotypes of breast cancer was separated into two heterogeneous clusters: Cluster A, a "immune-inflamed" cluster, containing substantial innate and adaptive immune cell infiltration, and Cluster B, a "immune-desert" cluster, with modest TME cell infiltration. We constructed a radiomics signature for the TME phenotypes ([AUC] = 0.855; 95% CI: 0.777–0.932; P  < 0.05) and verified it in an internal validation set (0.844; 0.606-1; P  < 0.05). In the known immune phenotypes cohort, the signature can identified either immune-inflamed or immune-desert tumor (0.814; 0.717–0.911; P  < 0.05). In the Immunotherapy-treated cohort, patients with objective response had higher baseline radiomics scores than those with stable or progressing disease ( P  < 0.05); moreover, the radiomics signature deserved an AUC of 0.784 (0.643–0.926; P  < 0.05) for predicting immunotherapy response. Conclusions Our imaging biomarker, a practicable radiomics signature, is beneficial for predicting the TME phenotypes and clinical response in anti-PD-1/PD-L1-treated breast cancer patients. The "immune-desert" phenotype belonging to “cold tumor” should be provoked for transforming into "immune-inflamed" phenotype namely as "hot tumor".