Haiyu Kang,1,* Zhong Liu,2,* Bin Huang,2,* Shuang Liang,1 Kai Yang,2 Huahui Liu,1 Minhua Lu,2 Ronghua Yan,3 Xin Chen,2 Erjiao Xu1 

1Department of Medical Ultrasonics, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong Province, People’s Republic of China; 2National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong Province, People’s Republic of China; 3Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, Guangdong Province, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Erjiao Xu, Department of Medical Ultrasonics, The Eighth Affiliated Hospital of Sun Yat-sen University, No. 3025 Shennan Middle Road, Futian Street, Futian District, Shenzhen, Guangdong Province, 518033, People’s Republic of China, Email xuerjiao@mail.sysu.edu.cn Xin Chen, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, 1066 Xueyuan Road, Shenzhen, Guangdong Province, 518055, People’s Republic of China, Email chenxin@szu.edu.cn

Purpose: Intra-operative factors are crucial to early recurrence of hepatocellular carcinoma (HCC) after microwave ablation (MWA), but few models have been developed based on intra-operative data to predict HCC recurrence after MWA. To quantify the intra-operative factors associated with MWA and establish an artificial intelligence (AI) model for predicting early recurrence of HCC after ablation based on contrast-enhanced ultrasound (CEUS) fusion imaging.
Patients and Methods: 79 hCC patients, who underwent MWA with one-year follow-up and intraoperative CEUS fusion imaging assessment were retrospectively included. Three classifiers (support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP)) were developed to predict early HCC recurrence from CEUS fusion images. Thirteen ablation-specific features were defined and screened using minimum redundancy maximum relevance (mRMR), and leave-one-out cross-validation (LOOCV) was adopted for performance evaluation. Comparative analyses were conducted among classifiers and between a senior interventional doctor and the best classifier in terms of the area under the receiver operating characteristic curve (AUC).
Results: Of 79 eligible patients who were included, 22 were in the early-recurrence (age 60.18 ± 10.97; 20 males) and 57 were in the non-early recurrence (age 58.81 ± 10.89; 50 males). Six features were selected out by mRMR for early recurrence prediction and AUCs of three models were 0.84 (95% CI: 0.74, 0.94) 0.79 (95% CI: 0.69, 0.89) and 0.77 (95% CI: 0.67, 0.88) (p = 0.20 and 0.23 for SVM and RF, respectively), which was significantly better than that achieved by senior doctor’s assessment (AUC, 0.56; 95% CI: 0.44, 0.68; p = 0.002 for MLP).
Conclusion: The prediction model based on ablation-specific features using intra-operative ultrasound fusion imaging data was feasible to predict early recurrence of HCC after MWA and showed great potential in guiding the real-time adjustment of the intra-operative ablation strategy so as to achieve precise ablation.

Keywords: hepatocellular carcinoma, HCC, microwave ablation, MWA, fusion imaging, artificial intelligence AI, early recurrence prediction