AI-Guided Surveillance and Curative Salvage of Recurrence After Hepatocellular Carcinoma Resection or Ablation

Hepatocellular carcinoma, the most common type of primary liver cancer, can recur after liver resection or thermal ablation performed with curative intent. Follow-up imaging is commonly scheduled at fixed intervals, although the risk of recurrence differs among patients and may change over time. This study will test whether a locked artificial intelligence system can use routinely collected clinical, laboratory, and imaging information to recommend when the next surveillance scan should occur. Adults with no radiological evidence of viable hepatocellular carcinoma after microscopically margin-negative liver resection or complete radiofrequency or microwave ablation will be randomly assigned in a 1:1 ratio to artificial intelligence-guided risk-adapted surveillance or fixed-interval surveillance. In the artificial intelligence-guided group, participants classified as having high, intermediate, or low current recurrence risk will generally undergo the next protocol-scheduled contrast-enhanced imaging examination after 3, 4, or 6 months, respectively. Participants in the control group will undergo protocol-scheduled imaging every 4 months. The risk thresholds are designed so that the expected total number of protocol-scheduled imaging examinations is approximately comparable between the two groups over 24 months. The artificial intelligence system provides surveillance recommendations only. It does not diagnose recurrence, determine eligibility for liver transplantation, or select anticancer treatment. Clinically indicated examinations may be performed at any time in either group. When recurrence is confirmed, participants in both groups will undergo the same protocol-defined multidisciplinary evaluation, and potentially curative-intent treatment may be considered when clinically appropriate. The primary purpose is to determine whether artificial intelligence-guided surveillance increases the probability of being alive at 24 months without having a recurrence that is no longer amenable to protocol-defined curative-intent treatment. The study evaluates the timing and allocation of surveillance rather than an adjuvant anticancer treatment and is not intended to prevent the biological occurrence of recurrence.

Inclusion Criteria: * Age 18 years or older at the time of informed consent. * First diagnosis of hepatocellular carcinoma, confirmed by histopathology for participants undergoing liver resection, or by histopathology or accepted guideline-concordant imaging criteria for participants undergoing thermal ablation. * Completion of first curative-intent treatment consisting of either R0 liver resection with microscopically tumor-negative margins or complete radiofrequency or microwave ablation of all known hepatocellular carcinoma. * Qualifying multiphasic contrast-enhanced CT or MRI obtained 28 to 56 days after completion of the final curative-intent procedure. * Qualifying imaging confirming no viable tumor at the resection bed or ablation site, no new intrahepatic hepatocellular carcinoma, and no macrovascular invasion, regional nodal disease, or extrahepatic metastasis. * No unresolved lesion requiring immediate diagnostic evaluation or treatment at the time of randomization. * Randomization within 14 days after the qualifying post-treatment imaging assessment and before the first protocol-scheduled surveillance examination. * Eastern Cooperative Oncology Group performance status of 0 or 1. * Child-Pugh class A liver function. * Medically fit for at least one protocol-defined curative-intent salvage treatment should an anatomically amenable recurrence be detected. * Able to undergo repeated protocol-required multiphasic contrast-enhanced CT or MRI examinations. * Availability of the minimum mandatory baseline data elements required to generate an output from the locked artificial intelligence system. * Able and willing to comply with trial procedures and provide written informed consent. Exclusion Criteria: * Any previous episode of hepatocellular carcinoma or previous hepatocellular carcinoma-directed treatment before the current index diagnosis. * Microscopically or macroscopically positive surgical margins (R1 or R2 resection). * Residual viable tumor after thermal ablation. * Any radiological evidence of residual, recurrent, nodal, or metastatic hepatocellular carcinoma at screening. * Macrovascular invasion, regional lymph-node metastasis, or extrahepatic metastasis associated with the index hepatocellular carcinoma. * Index treatment involving liver transplantation, combined resection and ablation, transarterial therapy, radiotherapy, systemic anticancer therapy, or another hepatocellular carcinoma-directed treatment other than the qualifying R0 resection or complete radiofrequency or microwave ablation. * Previous liver transplantation, active placement on a liver-transplant waiting list, or planned liver transplantation in the absence of documented recurrent hepatocellular carcinoma. * Planned or ongoing adjuvant antineoplastic treatment intended to reduce hepatocellular carcinoma recurrence after the qualifying procedure. Guideline-concordant antiviral treatment and management of the underlying liver disease are permitted. * Concurrent participation in another interventional study expected to affect hepatocellular carcinoma recurrence, survival, surveillance intensity, or eligibility for curative-intent salvage treatment. * Combined hepatocellular-cholangiocarcinoma or another non-hepatocellular primary hepatic malignancy. * A permanent medical contraindication that would preclude all protocol-defined curative-intent salvage treatment options. * Inability to undergo any protocol-permitted contrast-enhanced CT or MRI modality because of contraindication to all available imaging and contrast options. * Active malignancy other than hepatocellular carcinoma that requires anticancer treatment or is expected to materially interfere with survival, surveillance adherence, or outcome assessment during the primary 24-month follow-up period. * Uncontrolled hepatic decompensation, including refractory ascites or clinically significant hepatic encephalopathy. * Pregnancy at the time of randomization. * Inability or unwillingness to provide informed consent or comply with protocol-specified follow-up.