Multicentric 68Ga-PSMA PET radiomics for treatment response assessment of 177Lu-PSMA-617 radioligand therapy in patients with metastatic castration-resistant prostate cancer

Abstract

Objective The treatment with 177 Lutetium PSMA ( 177 Lu-PSMA) in patients with metastatic castration-resistant prostate cancer (mCRPC) has recently been approved by FDA and EMA. Since treatment success is highly variable between patients, the prediction of treatment response and identification of short- and long-term survivors after treatment could help to tailor mCRPC diagnosis and treatment accordingly. The aim of this study is to investigate the value of radiomics parameters extracted from pretreatment 68 Ga-PSMA PET images for prediction of treatment response. Methods Forty-five mCRPC patients treated with 177 Lu-PSMA-617 from two university hospital centers were retrospectively reviewed for this study. Radiomics features were extracted from the volumetric segmentations of metastases in the bone. A random forest model was trained and validated to predict treatment response based on age and conventionally used PET parameters, radiomics features, and combinations thereof. Further, overall survival was predicted by using the identified radiomics signature and compared to a Cox regression model based on age and PET parameters. Results The machine learning model based on a combined radiomics signature of three features and patient age achieved an AUC of 0.82 in 5-fold cross validation and outperformed models based on age and PET parameters or radiomics features (AUC, 0.75 and 0.76, respectively). A Cox regression model based on this radiomics signature showed the best performance to predict the overall survival (C-index, 0.67). Conclusion Our results demonstrate that a machine learning model to predict response to 177 Lu-PSMA treatment based on a combination of radiomics and patient age outperforms a model based on age and PET parameters. Moreover, the identified radiomics signature based on pretreatment 68 Ga-PSMA PET images might be able to identify patients with an improved outcome and serve as a supportive tool in clinical decision making.