Background: We aimed to evaluate the performance of a deep learning (DL)-based Radiomics strategy designed for analyzing contrast-enhanced ultrasound (CEUS) to not only predict the progression-free survival (PFS) of radiofrequency ablation (RFA) and surgical resection (SR) but also optimize the treatment selection between them for patients with very-early or early-stage hepatocellular carcinoma (HCC). Methods: We retrospectively enrolled 419 patients examined by CEUS within 1 week before receiving RFA or SR (RFA: 214, SR: 205) from January 2008 to 2016. Two Radiomics signatures were constructed by the Radiomics model R-RFA and R-SR to stratify PFS of different treatment groups. Then, RFA and SR nomograms were built by incorporating Radiomics signatures and significant clinical variables to achieve individualized 2-year PFS prediction. Finally, we applied both Radiomics models and both nomograms to each enrolled patient to investigate whether there were space for treatment optimization and how much prognostic improvement could be expected. Results: R-RFA and R-SR showed remarkable discrimination (C-index: 0.726 for RFA, 0.741 for SR). RFA and SR nomograms provided good 2-year PFS prediction accuracy and good calibrations. We identified 17.3% RFA patients and 27.3% SR patients should swap their treatment, so their average probability of 2-year PFS would increase 12 and 15%, respectively. Conclusions: The proposed Radiomics models and nomograms achieved accurate preoperative prediction of PFS for RFA and SR, and they could facilitate the optimized treatment selection between them for patients with very-early or early-stage HCC.

Background Infectious complications after percutaneous thermal ablation are seldom discussed, but better understanding of risk factors and early prediction is critical. Purpose To estimate the incidence of infectious complications after percutaneous thermal ablation of liver malignancies and to develop prediction models. Materials and Methods This single-center retrospective study reviewed the data of 3167 patients who underwent 7545 percutaneous US-guided thermal ablation procedures of liver malignancies between January 2010 and January 2022. All procedures with infectious complications were included as the case group. For each case, one treatment date-matched control subject without infection was randomly selected following a nested case-control design. Independent factors of overall and hepatobiliary infection were investigated with multivariable logistic regression. Results A total of 80 patients (median age, 59 years; IQR, 51-68 years; 64 men, 16 women) developed infectious complications after 80 ablation procedures; the incidence was 1.1% (80 of 7545 procedures). Of those with infection, 18% (14 of 80 patients) were severe, and 10% (eight of 80 patients) died as a result. Independent risk factors for overall infectious complication included prior biliary intervention (odds ratio [OR], 18.6; 95% CI: 4, 86; P < .001), prior transarterial chemoembolization (TACE) (OR, 2.4; 95% CI: 1.0, 5.8; P = .045), and the largest tumor size (OR, 1.9; 95% CI: 1.3, 2.8; P = .002); on this basis, subcapsular location was an additional risk factor of hepatobiliary infection. Prediction models for overall and hepatobiliary infection had an area under the receiver operating characteristics curve (AUC) of 0.77 and 0.82, respectively, both of which showed better AUC compared with the models, including prior biliary intervention alone (AUC = 0.63 and 0.65, respectively; P = .01 and P = .005, respectively). Conclusion Infectious complications after percutaneous thermal ablation of liver malignancies were uncommon but potentially fatal. Independent predictors were prior biliary intervention, prior transarterial chemoembolization, and the largest tumor size. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Ben-Arie and Sosna in this issue.