Preoperative Prediction of Microvascular Invasion of Hepatocellular Carcinoma: Radiomics Algorithm Based on Ultrasound Original Radio Frequency Signals

Background：To evaluate the accuracy of radiomics algorithm based on original radio frequency (ORF) signals for prospective prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) lesions. Methods: This prospective included patients diagnosed with HCC and planned to accept surgical resection from Jan 2018 to Dec 2018. Ultrasound ORF data and gray scale ultrasound images of HCC lesions were collected before operation for further radiomics analysis. The diagnostic accuracy of ORF model was compared with models based on gray scale ultrasound images. Results: A total of 42 histopathologically proved HCC lesions were enrolled, including 21 lesions with MVI. Three ultrasound feature maps were calculated using signal analysis and processing (SAP) technology in first feature extraction. A total of 1050 radiomics features were extracted from each lesion. The performances of MVI prediction model based on ORF were better than those based on gray scale ultrasound images. The best area under curve (AUC), accuracy, sensitivity and specificity of ultrasound radiomics in prediction of MVI were 95.01 %, 92.86 %, 85.71 % and 100 % respectively. Conclusions: RA-ORF combining with SAP technology can effectively predict MVI, which has potential clinical application value for noninvasively preoperative prediction of MVI in HCC patients.