Ke Su,1– 3,* Xin Liu,1,4,* Yue-Can Zeng,5,* Junnv Xu,6,* Han Li,2 Heran Wang,7 Shanshan Du,1 Huadong Wang,1 Jinbo Yue,8 Yong Yin,1 Zhenjiang Li1 

1Department of Radiation Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, People’s Republic of China; 2Department of Oncology, The Affiliated Hospital of Southwest Medical University, Luzhou, 646000, People’s Republic of China; 3Department of Radiation Oncology, National Cancer Center/ National Clinical Research Center for Cancer/ Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100000, People’s Republic of China; 4Department of Gynecological Radiotherapy, Harbin Medical University Cancer Hospital, Harbin, 150081, People’s Republic of China; 5Department of Radiation Oncology, Cancer Treatment Center, The Second Affiliated Hospital of Hainan Medical University, Haikou, 570311, People’s Republic of China; 6Department of Medical Oncology, The Second Affiliated Hospital, Hainan Medical University, Haikou, Hainan Province, 570311, People’s Republic of China; 7Department of Orthopedics, Shengjing Hospital of China Medical University, Shenyang, Liaoning, 110004, People’s Republic of China; 8Department of Abdominal Radiotherapy, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Yong Yin, Email yinyongsd@126.com Zhenjiang Li, Email zhenjli1987@163.com

Background: This study was conducted to assess the efficacy and safety of magnetic resonance (MR)-guided hypofractionated radiotherapy in patients with unresectable hepatocellular carcinoma (HCC). Machine learning-based radiomics was utilized to predict responses in these patients.
Methods: This retrospective study included 118 hCC patients who received MR-guided hypofractionated radiotherapy. The primary study endpoint was the objective response rate (ORR). Radiomics features were based on the gross tumor volume (GTV). K-means clustering was performed to differentiate cancer subtypes based on radiomics. Nine radiomics-utilizing machine learning models were built and validated internally through 5-fold cross-validation.
Results: The ORR, median progression-free survival (mPFS), and median overall survival (mOS) were 54.4%, 21.7 months, and 40.7 months, respectively. No patient experienced Grade 3/4 adverse events. 1130 radiomics features were extracted from the GTV, of which 7 were included for further analysis. K-means clustering identified 2 subtypes based on the selected features. Subtype 1 had significantly higher response, longer mPFS, and longer mOS than Subtype 2. In both internal and external validations, the multi-layer perceptron (MLP) model demonstrated superior predictive performance for response, achieving a receiver operating characteristic-area under the curve (ROC-AUC) of 0.804 and 0.842, respectively.
Conclusion: MR-guided radiotherapy was proven to be effective and safe for HCC. The machine learning radiomics model developed in this study could accurately predict the response of radiotherapy-treated inoperable HCC.

Keywords: machine learning models, radiomics, radiotherapy, hepatocellular carcinoma