AI-based CT prediction of microvascular invasion in liver cancer

Development of a Computer-Aided Diagnosis System for Hepatocellular Carcinoma Microvascular Invasion Based on Preoperative Image Analysis

Observational Chinese Academy of Sciences · NCT07170345

This project will test whether an AI-powered tool using preoperative multiphase CT can predict microvascular invasion in adults with hepatocellular carcinoma who are scheduled for surgery.

Quick facts

Study typeObservational
Enrollment400 (estimated)
Ages18 Years to 18 Years
SexAll
SponsorChinese Academy of Sciences Government
Locations19 sites (Fuzhou, Fujian and 18 other locations)
Trial IDNCT07170345 on ClinicalTrials.gov

What this trial studies

This is a prospective, multicenter observational study developing and validating a computer-aided diagnostic (CAD) system that combines deep learning image features, predefined imaging signatures, and clinical prior knowledge from multiphase CT scans to predict microvascular invasion (MVI) in HCC. Participants are adults with confirmed HCC who undergo preoperative multiphase CT within one month before planned hepatic resection or transplantation and have postoperative histopathology documenting MVI status. The CAD system's predictions will be compared to the gold-standard postoperative pathology to measure diagnostic performance and cross-center generalizability. The study emphasizes interpretability and adaptability across multiple Chinese hospitals to improve clinical applicability.

Who should consider this trial

Good fit: Adults (age ≥18) with confirmed hepatocellular carcinoma who are eligible for hepatic resection or liver transplantation and who have preoperative multiphase CT performed within one month and postoperative pathology available for MVI status.

Not a fit: Patients who received prior antitumor therapies, who have major vascular invasion, extrahepatic metastasis, diffuse tumors, tumor rupture, or who lack key imaging or pathological data are unlikely to benefit from this preoperative prediction tool.

Why it matters

Potential benefit: If successful, the tool could give surgeons and care teams information about MVI before surgery to help choose surgical margins and adjuvant treatments that may reduce early recurrence.

How similar studies have performed: Previous imaging-based and AI approaches have shown promising signals for preoperative MVI prediction but have been limited by poor generalizability and interpretability, so this study builds on prior work to improve clinical applicability.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Age ≥ 18 years.
* Confirmed diagnosis of hepatocellular carcinoma (HCC) according to the Chinese Clinical Practice Guidelines for Primary Liver Cancer.
* Eligible for surgical intervention (hepatic resection or liver transplantation) according to the Chinese Clinical Practice Guidelines for Cancer, including stages Ia, Ib, and IIa.
* Preoperative imaging examination performed within 1 month before surgery.
* Availability of histopathological evaluation with documented microvascular invasion (MVI) status.

Exclusion Criteria:

* History of prior antitumor treatment, including preoperative surgical intervention, transarterial chemoembolization (TACE), radiofrequency ablation (RFA), systemic therapy, or any other preoperative intervention.
* Presence of major vascular invasion, bile duct invasion/thrombosis, extrahepatic metastasis, or lymph node involvement.
* Diffuse hepatocellular carcinoma or tumor rupture with hemorrhage.
* Lack of key data required for primary analysis.
* Poor image quality that prevents reliable qualitative or radiomics analysis.

Where this trial is running

Fuzhou, Fujian and 18 other locations

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 CarcinomaMicrovascular InvasionComputer-Aided Diagnosis SystemArtificial IntelligenceMedical ImageMultimodal Model
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.