AI prediction of liver cancer returning after surgery
Prospective Validation of Multimodal Deep Learning Models for Predicting Recurrence Patterns in Early-Stage Hepatocellular Carcinoma After Resection: A Natural Treatment Cohort Stratification Study
This study will test whether an AI program can identify people with early-stage liver cancer who are likely to have the cancer come back within two years after surgery.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 353 (estimated) |
| Ages | 18 Years to 75 Years |
| Sex | All |
| Sponsor | Tongji Hospital Academic / other |
| Locations | 1 site (Wuhan, Hubei) |
| Trial ID | NCT07062380 on ClinicalTrials.gov |
What this trial studies
This observational project will use a pretrained deep learning model to predict aggressive recurrence patterns after curative resection for early-stage hepatocellular carcinoma. Eligible patients will have a dynamic contrast-enhanced MRI within one month before surgery and will receive standard surgical care. Clinical, imaging, and follow-up data will be collected and the AI model’s predictions compared with actual recurrence observed during two years of imaging surveillance. The goal is to validate the model’s accuracy in a real-world surgical cohort and describe patterns of post-resection recurrence.
Who should consider this trial
Good fit: Ideal candidates are adults 18–75 years old with BCLC stage 0–A HCC scheduled for curative liver resection who have a good performance status (ECOG 0–1), Child-Pugh score ≤7, and a recent high-quality dynamic contrast-enhanced MRI.
Not a fit: Patients with non-HCC pathology after surgery, advanced-stage disease, severe organ dysfunction, inability to obtain suitable MRI, prior organ transplant, or who are pregnant/lactating are unlikely to benefit from this validation.
Why it matters
Potential benefit: If successful, the AI tool could help identify patients at higher risk of early recurrence so clinicians can tailor follow-up and adjuvant treatment more precisely.
How similar studies have performed: Retrospective studies using AI to predict HCC recurrence have shown promising results, but prospective or real-world validation studies remain limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Aged 18-75 years, regardless of gender. * BCLC stage 0-A, scheduled for curative liver resection. * Preoperative clinical diagnosis of hepatocellular carcinoma (HCC). * Availability of dynamic contrast-enhanced MRI within 1 month before surgery, with acceptable image quality. * Child-Pugh liver function score ≤7. * ECOG Performance Status (PS) 0-1. * No severe organic diseases of the heart, lungs, brain, or other vital organs. Exclusion Criteria: * Concurrent other malignancies (except cured non-melanoma skin cancer or cervical carcinoma in situ). * Postoperative pathology confirms non-HCC diagnosis. * Pregnant or lactating women. * History of organ transplantation. * Inability to comply with the study protocol or follow-up schedule.
Where this trial is running
Wuhan, Hubei
- Tongji Hospital — Wuhan, Hubei, China (Recruiting)
Study contacts
- Study coordinator: Yang Wu, M.D.
- Email: 255001907@qq.com
- Phone: +8613636076910
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.