MRI-Based Radiomics Predicts FAP Expression and Immunosuppressive Tumor Microenvironment in Hepatocellular Carcinoma

Abstract

Purpose To develop a Magnetic resonance imaging (MRI) -based radiomics-clinical model for noninvasive prediction of fibroblast activation protein (FAP) expression in hepatocellular carcinoma (HCC), and to explore its association with tumor microenvironment (TME) characteristics and potential immunotherapy response. Patients and Methods This retrospective study included 104 patients with HCC from the Fourth Hospital of Hebei Medical University, 31 external MRI cases from The Cancer Imaging Archive (TCIA), and 363 transcriptomic profiles from The Cancer Genome Atlas (TCGA). Immunohistochemistry (IHC) assessed FAP expression. Tumor regions were manually segmented, and radiomics features were extracted using PyRadiomics. Multiple machine learning classifiers were used to construct and validate models for predicting FAP expression. Logistic regression was selected for its balanced performance between the training and validation cohorts, with the smallest area under the curve (AUC) difference among the five machine-learning algorithms. A radiomics-clinical combined model was further developed by integrating the radscore with clinical indicators. Radiogenomic analysis explored radscore-related transcriptomic features and immune infiltration characteristics. Results In the validation cohort, the AUC values of the intratumoral, peritumoral, and intratumoral + peritumoral radiomics models were 0.757, 0.502, and 0.784, respectively. The intratumoral + peritumoral model also achieved a sensitivity of 0.692 and a specificity of 0.788, indicating the best overall discriminatory performance among the three models. The radiomics-clinical combined model integrating the systemic immune-inflammation index (SII), prognostic nutritional index (PNI), and radscore achieved an AUC of 0.816 in the validation cohort. Radscore-related transcriptomic modules identified 10 hub genes for risk stratification. Patients in the high-risk group exhibited a more pronounced immunosuppressive TME and poorer predicted benefit from immunotherapy. Conclusion The MRI-based radiomics-clinical model effectively predicted FAP expression in HCC. Radscore reflected FAP-related immunosuppressive TME remodeling and may provide insights into potential immunotherapy response stratification, which requires further validation in independent immunotherapy-treated cohorts.