Using AI on CT and MRI scans to predict immunotherapy response and survival for liver cancer patients

Predicting Immunotherapy Response and Survival of Liver Cancer Patients Using Artificial Intelligence and Radiomics (Radiology-AI-Liver)

Observational Union Hospital, Tongji Medical College, Huazhong University of Science and Technology · NCT07059936

This project will test whether artificial intelligence applied to CT and MRI scans can predict which adults with hepatocellular carcinoma will respond to immunotherapy and their likely survival.

Quick facts

Study typeObservational
Enrollment350 (estimated)
Ages18 Years and up
SexAll
SponsorUnion Hospital, Tongji Medical College, Huazhong University of Science and Technology Academic / other
Drugs / interventionsimmunotherapy
Locations1 site (Wuhan, Hubei)
Trial IDNCT07059936 on ClinicalTrials.gov

What this trial studies

Researchers will collect pre-treatment (and possibly post-treatment) CT and MR images from hepatocellular carcinoma patients treated at Union Hospital between July 2025 and July 2026 and link them with clinical outcomes. An automated pipeline will segment tumors, extract radiomics features, select the most informative features, and train machine-learning classification models to predict immunotherapy response and survival. Patients with poor image quality, incomplete data, another primary cancer, or unclear pathology will be excluded to preserve model reliability. The work is observational and based on retrospective clinical imaging and pathology data from a single center in Wuhan.

Who should consider this trial

Good fit: Adults over 18 with biopsy-confirmed hepatocellular carcinoma treated at Union Hospital between July 2025 and July 2026 who have at least one pre-treatment CT or MR scan are the intended participants.

Not a fit: Patients with poor-quality images, missing clinical data or follow-up, another primary malignancy, or an unclear pathological diagnosis are unlikely to benefit from the model.

Why it matters

Potential benefit: If successful, the approach could help personalize treatment by identifying patients likely to benefit from immunotherapy and avoiding ineffective therapies for others.

How similar studies have performed: Previous small studies using radiomics and AI to predict immunotherapy response in liver cancer have shown promise but remain exploratory and not yet widely validated.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

1. Patients were treated for hepatocellular carcinoma in Wuhan Union Hospital from July 2025 to July 2026;
2. Aged \> 18 years old;
3. At least one CT scan or MR scan before treatment;
4. Tissue biopsy pathological examination confirmed the diagnosis of the above tumors.

Exclusion criteria:

1. Poor image quality;
2. Incomplete clinical data or loss of follow-up;
3. Presence of another primary malignancy other than liver cancer;
4. Unclear pathological diagnosis.

Where this trial is running

Wuhan, Hubei

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Hepatocellular Carcinoma
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.