A magnetic resonance imaging radiomics approach predicts hepatocellular carcinoma response to stereotactic body radiation therapy

Abstract

Background and purpose

Predicting hepatocellular carcinoma (HCC) response to Stereotactic Body Radiation Therapy (SBRT) can be challenging. Here, we assessed the value of a radiomics-based machine learning (ML) approach for predicting HCC response to SBRT, using pre-treatment and early post-treatment magnetic resonance imaging (MRI).

Materials and Methods

This retrospective single-center study included 87 patients (M 67, mean age 65.3 ± 9.1y) with HCC treated with SBRT who underwent gadoxetate MRI both pre- and early post-treatment (around 9.5 weeks). Tumor radiomics features were extracted on pre- and post-SBRT MRIs on pre- and post-contrast T1-weighted imaging (T1WI) [pre-contrast, arterial phase (AP), portal venous phase (PVP), transitional phase and hepatobiliary phase]. Long term response was assessed using modified RECIST criteria. Different ML models were developed based on 1st and 2nd order radiomics features to predict long-term objective response (partial and complete response) versus no response (stable and progressive disease). The cohort was randomly divided into training/validation (70 %) and testing 30 %.

Results

A total of 87 tumors were assessed (mean size 2.7 ± 1.6 cm). Objective long-term response was observed in 43 (49.4 %) patients. The best predictive outcomes were achieved using models combining pre- and early post-treatment radiomics, with top performing model combining pre-treatment T1WI-pre-contrast, pre-treatment T1WI-AP and post-treatment T1WI-PVP, achieving an AUC of 0.85 [95 % CI: 0.67–––1], sensitivity of 0.7 and specificity of 1.

Conclusions

Our initial findings show promising results for ML radiomics in predicting long-term response of HCC to SBRT, which may have implications for management decisions.