Objective: To explore and clarify the correlation between short-term aggressive intrasegmental recurrence (AIR) and functional magnetic resonance imaging after radiofrequency ablation of hepatocellular carcinoma (HCC). Methods: A retrospective analysis of 1 262 patients with HCC who underwent radiofrequency ablation (RFA) in our hospital from January 2012 to June 2018, all patients were confirmed by pathology as HCC, of which 30 patients were found to have AIR during radiographic follow-up within 3 months after surgery, another 35 patients with disease progression who were controlled in a short period of time were randomly selected as the control group. All the enrolled patients underwent dynamic enhanced magnetic resonance imaging (DCE-MRI) and diffusion weighted imaging (DWI) scanning before surgery, and the differences in clinical data, lesion location, and functional magnetic resonance parameters between the two groups were compared, and their correlation with AIR after RFA was analyzed. Chi-square test, t test and Pearson test were used. Results: The lesions in the AIR group were significantly more in the Ⅰand Ⅳsegments than that in the control group (P<0.05), and there was no significant difference in other liver segments (P>0.05). There was no significant difference in the lesion morphology between the two groups (P>0.05), and there was a significant difference in the early enhancement pattern of the lesions (P<0.05), and the early arterial enhancement rate and apparent diffusion coefficient (ADC) value of the AIR group were significantly lower than the control group (P<0.05). Further correlation analysis found that early enhancement of the arterial artery, early arterial enhancement rate, ADC value and lesion location were associated with AIR and were positively correlated, r values were 0.455, 0.633, 0.518, 0.375 and 0.287 (P<0.05). Conclusion The short-term AIR and functional imaging parameters (arterial early enhancement, early arterial enhancement rate, ADC value) and the liver segment (Ⅰ and Ⅳ) were highly correlated with radiofrequency ablation.

Objective:To develop a prediction model based on imaging features by contrast-enhanced MRI radiomics combined with clinical features for early recurrence of hepatocellular carcinoma (HCC) after radical resection.Methods:A retrospective study was carried out on 109 HCC patients who underwent radical resection at the Fifth Affiliated Hospital of Wenzhou Medical University from January 2015 to December 2020. Of 109 patients enrolled in this study, there were 96 males and 13 females, aged (58.3±10.7) years. Based on whether there was recurrence within 12 months after operation, the patients were divided into the early recurrence group ( n=31) and the control group ( n=78). These 109 patients were then randomly divided into the validation set ( n=23) and the training set ( n=86) at a ratio of 1∶4. Based on preoperative multi-phase contrast-enhanced MRI scanning, the tumor lesions were delineated on the Radcloud platform, and 1 409 quantitative radiomic features were extracted. Dimension reduction and screening of these features were carried out using variance threshold, SelectKBest and LASSO. Combined with clinical features (alpha fetoprotein, tumor size), several prediction model were established through machine learning. The predictive efficiencies of these models were evaluated using the area under the receiver operating characteristic (ROC) curve, accuracy rate, recall rate and balanced F score. Results:The proportions of irregular tumor shape and unclear tumor boundary, as well as maximum tumor diameter in the early recurrence group were significantly higher than that in the control group, but the proportion of pseudocapsule was significantly lower than that in the control group (all P<0.05). A total of 465 features were screened from the 1 409 features using the variance threshold method, followed by 38 features were screened using the method of SelectKBest. Finally 7 optimal radiomic features were screened based on the LASSO method. When combined with clinical features, 5 prediction models were established through machine learning. These models were support vector machine, Gaussian naive bayes, logistic regression, Multinomial naive bayes and K-nearest neighbor (KNN), respectively. Among these 5 models, the prediction efficiency of the KNN model was relatively highest, with the area under the ROC curve, accuracy rate, recall rate and balanced F score being 0.90, 0.98, 0.74 and 0.84 in the training set, and 0.76, 0.92, 0.75 and 0.83 in the verification set, respectively. Thus, the KNN model was selected as the best prediction model in this study. Conclusion:The prediction model of KNN was developed for early recurrence of HCC after radical resection based on preoperative contrast-enhanced MRI radiomics combined with clinical features.