AI-guided personalized pre- and post-surgery treatment to reduce liver cancer recurrence

A Multimodal Deep Learning-Driven Study for Perioperative Risk Stratification and Precision Intervention in Hepatocellular Carcinoma Recurrence

This will try using an AI tool to pick early-stage hepatocellular carcinoma patients at high risk of recurrence and give them medication before and after surgery to see if it reduces the chance the cancer comes back within two years.

Quick facts

• Phase: Phase1; Phase2
• Study type: Interventional
• Enrollment: 144 (estimated)
• Ages: 18 Years to 75 Years
• Sex: All
• Sponsor: Tongji Hospital (Academic / other)
• Drugs / interventions: lenvatinib
• Locations: 1 site (Wuhan, Hubei)
• Trial ID: NCT07282184 on ClinicalTrials.gov

What this trial studies

A multimodal deep learning model analyzes each patient's preoperative MRI and clinical data to predict individualized risk of aggressive post-resection recurrence. Patients flagged as high-risk by the model are offered neoadjuvant hepatic arterial infusion chemotherapy (HAIC) combined with lenvatinib and a PD-1 inhibitor before curative liver resection, with additional adjuvant therapy after surgery. Outcomes, including two-year recurrence-free survival and treatment safety, will be compared with the standard approach of surgery alone. The trial enrolls adults with BCLC 0–A disease, Child-Pugh A liver function, ECOG 0–1, and requires a recent standard preoperative MRI; it is conducted at Tongji Hospital in Wuhan.

Who should consider this trial

Good fit: Ideal candidates are adults aged 18–75 with early-stage (BCLC 0–A) hepatocellular carcinoma who are scheduled for curative-intent liver resection, have Child-Pugh A function, ECOG 0–1, and a usable preoperative MRI.

Not a fit: Patients with advanced-stage disease, impaired liver function (Child-Pugh >A), ECOG ≥2, inadequate imaging, or those classified as low-risk by the AI model are unlikely to receive the added perioperative regimen and therefore may not benefit from this approach.

Why it matters

Potential benefit: If successful, AI-guided perioperative therapy could reduce the two-year recurrence rate after curative liver resection by directing additional treatments to patients most likely to benefit.

How similar studies have performed: Components of the regimen (HAIC, lenvatinib, and PD-1 inhibitors) have shown activity in HCC and some combination or neoadjuvant studies are promising, but using a multimodal AI model to direct perioperative therapy is novel and not yet widely validated.

Eligibility criteria

Inclusion Criteria:

* Age and Consent: Patients aged 18-75 years who are able to understand and voluntarily sign an Informed Consent Form.
* Diagnosis: Clinical diagnosis of BCLC stage 0-A hepatocellular carcinoma, confirmed by histopathology or non-invasive imaging criteria per guidelines.
* Surgical Candidacy: Scheduled to undergo curative-intent liver resection.
* Risk Stratification: Predicted as high-risk for aggressive recurrence by the pre-operative multimodal deep learning model (PRE score ≥ 0.5).
* Liver Function: Child-Pugh liver function class A (score ≤ 7).
* Performance Status: ECOG Performance Status of 0 or 1.
* Imaging Requirement: Availability of a standard pre-operative MRI scan (including non-contrast, arterial, portal venous, and delayed phases) performed within 1 month prior to enrollment, with acceptable image quality.
* Follow-up Commitment: Willing and able to comply with the study procedures and scheduled follow-up for at least 2 years.

Exclusion Criteria:

* Pathology: Postoperative pathological confirmation of non-HCC malignancy (e.g., cholangiocarcinoma, combined hepatocellular-cholangiocarcinoma).
* Other Malignancies: History of other active malignancies within the past 5 years, except for appropriately treated carcinoma in situ of the cervix, non-melanoma skin cancer, or other cancers with a very low risk of recurrence.
* Early Mortality/Loss: Death from any cause or loss to follow-up within 90 days after surgery.
* Contraindications to Protocol Therapy: Known hypersensitivity to any component of the neoadjuvant therapy regimen (e.g., oxaliplatin, fluorouracil, PD-1 inhibitors, lenvatinib).
* Severe, uncontrolled medical conditions including but not limited to: Uncontrolled cardiac disease (e.g., NYHA Class III or IV heart failure), Severe renal dysfunction, Uncontrolled hypertension.
* Inability to Participate: Any condition that, in the opinion of the investigator, would compromise the patient's ability to participate in the study or interfere with the evaluation of the study objectives.

Where this trial is running

Wuhan, Hubei

• Tongji Hospital — Wuhan, Hubei, China (Recruiting)

Study contacts

• Study coordinator: Yang Wu, M.D.

Conditions Hepotacellular Carcinoma; deep learning; recurrence pattern; Hepatocellular Carcinoma; Neoadjuvant Therapy