Early Prediction of Response of Hepatocellular Carcinoma to Yttrium-90 Radiation Segmentectomy Using a Machine Learning MR Imaging Radiomic Approach

Purpose: To assess the accuracy of a machine learning (ML) approach based on magnetic resonance (MR) imaging radiomic quantification obtained before treatment and early after treatment for prediction of early hepatocellular carcinoma (HCC) response to yttrium-90 transarterial radioembolization (TARE). Materials and Methods: In this retrospective single-center study of 76 patients with HCC, baseline and early (1–2 months) post-TARE MR images were collected. Semiautomated tumor segmentation facilitated extraction of shape, first-order histogram, and custom signal intensity–based radiomic features, which were then trained (n = 46) using a ML XGBoost model and validated on a separate cohort (n = 30) not used in training to predict treatment response assessed at 4–6 months (based on modified Response and Evaluation Criteria in Solid Tumors criteria). Performance of this ML radiomic model was compared with those of models comprising clinical parameters and standard imaging characteristics using area under the receiver operating curve (AUROC) analysis for prediction of complete response (CR). Results: Seventy-six tumors with a mean (±SD) diameter of 2.6 cm ± 1.6 were included. Sixty, 12, 1, and 3 patients were classified as having CR, partial response, stable disease, and progressive disease, respectively, at 4–6 months posttreatment on the basis of MR images. In the validation cohort, the radiomic model showed good performance (AUROC, 0.89) for prediction of CR, compared with models comprising clinical and standard imaging criteria (AUROC, 0.58 and 0.59, respectively). Baseline imaging features appeared to be more heavily weighted in the radiomic model. Conclusions: The use of ML modeling of radiomic data combining baseline and early follow-up MR imaging could predict HCC response to TARE. These models need to be investigated further in an independent cohort.