Computer-Aided Diagnosis for Hepatocellular Carcinoma Microvascular Invasion
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18-18
SponsorChinese Academy of Sciences
About this trial
Hepatocellular carcinoma (HCC) is a common malignancy in China with a high mortality rate. Its early recurrence and long-term prognosis are closely associated with tumor aggressiveness. Microvascular invasion (MVI), defined as the presence of tumor cells within small branches of the portal or hepatic veins, is a key indicator of malignant biological behavior in HCC. Clinically, MVI is strongly correlated with postoperative early recurrence and serves as an important factor in determining surgical margin extension, adjuvant therapy, and postoperative management strategies.
At present, definitive diagnosis of MVI still relies on postoperative pathological examination, and stable, effective preoperative assessment methods are lacking. Although some studies have attempted to predict MVI using preoperative imaging features, their clinical translation remains limited by poor generalizability, weak interpretability, and insufficient cross-center adaptability.
This study aims to leverage multiphase preoperative CT imaging, artificial intelligence techniques, and clinical prior knowledge to develop a high-performance, generalizable, and interpretable computer-aided diagnostic system for preoperative prediction of HCC-MVI. An observational, prospective evaluation will be conducted to assess system performance and to facilitate the clinical translation of intelligent diagnostic technologies in real-world practice.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
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.
Disqualifiers
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.
Trial population
The study population consists of adult patients (≥18 years) with hepatocellular carcinoma who undergo curative-intent surgical treatment, including hepatic resection or liver transplantation, at participating clinical centers. Approximately 5,000 retrospective cases and 400 prospective cases will be included. All participants will have preoperative multiphase CT imaging and postoperative pathological evaluation with documented microvascular invasion (MVI) status.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Computer-Aided Diagnosis System for Preoperative Prediction of MVI in HCC
Diagnostic testThis intervention is an artificial intelligence-based computer-aided diagnosis (CAD) system developed to predict microvascular invasion (MVI) in patients with hepatocellular carcinoma using preoperative multiphase CT imaging. The system integrates deep learning, radiomics, and expert-defined imaging features to provide risk assessment and visualization of MVI prior to surgery. In this study, the CAD system will be evaluated retrospectively and prospectively in an observational manner only. The results will not influence clinical decision-making or patient management, and all treatments will follow standard of care.
Treatment groups
400 Participants
are divided into 19 treatment groups19
Treatment groupsSee each treatment group below.
Group A: Peking Union Medical College Hospital1 intervention
Group B: First Affiliated Hospital of Kunming Medical University1 intervention
Group C: Beijing YouAn Hospital1 intervention
Group D: Zhujiang Hospital1 intervention
Group E: Meng Chao Hepatobiliary Hospital of Fujian Medical University1 intervention
Group F: First Affiliated Hospital of Wenzhou Medical University1 intervention
Group G: Fifth Affiliated Hospital, Sun Yat-Sen University1 intervention
Group H: Henan Provincial People's Hospital1 intervention
Group I: Guangdong Provincial Hospital of Traditional Chinese Medicine1 intervention
Group J: Shengjing Hospital1 intervention
Group K: Beijing Tsinghua Changgeng Hospital1 intervention
Group L: Yunnan Cancer Hospital1 intervention
Group M: The First People's Hospital of Yunnan Province1 intervention
Group N: Guizhou Provincial People's Hospital1 intervention
Group O: First Affiliated Hospital of Guangxi Medical University1 intervention
Group P: West China Hospital1 intervention
Group Q: Zhuhai People's Hospital1 intervention
Group R: Dazhou Central Hospital1 intervention
Group S: Eastern Hepatobiliary Surgery Hospital1 intervention
Trial outcomes
Primary outcomes
1
Area Under the Receiver Operating Characteristic Curve (AUC)
The AUC will be calculated by comparing CAD system predictions with the reference standard of postoperative pathological diagnosis of microvascular invasion in hepatocellular carcinoma.
Time frame
Within 1 month after surgery2
Accuracy
Accuracy will be defined as the proportion of correctly classified cases (both MVI-positive and MVI-negative) by the CAD system compared with postoperative pathology.
Time frame
Within 1 month after surgerySecondary outcomes
1
Sensitivity
Sensitivity will be calculated as the proportion of true positive MVI cases correctly identified by the CAD system compared with postoperative pathology.
Time frame
Within 1 month after surgery2
Specificity
Specificity will be calculated as the proportion of true negative MVI cases correctly identified by the CAD system compared with postoperative pathology.
Time frame
Within 1 month after surgery3
Calibration
Calibration performance will be assessed using calibration curves, Hosmer-Lemeshow goodness-of-fit tests, and Brier scores, to determine agreement between predicted probabilities and observed MVI outcomes.
Time frame
Within 1 month after surgeryOther outcomes
1
Processing Time
Average computational time required for the CAD system to generate predictions and visualization outputs will be recorded to assess feasibility for integration into clinical workflow.
Time frame
Within 1 month after surgery2
Physician Confidence Score
Physician Confidence Score will be measured using a questionnaire that asks physicians to rate their confidence in assessing patient risk after reviewing CAD-generated probability scores and saliency maps. Responses will be collected on a 5-point Likert scale (1 = not confident at all, 2 = slightly confident, 3 = moderately confident, 4 = confident, 5 = very confident). The score will be recorded as the numerical Likert scale value selected by each physician.
Time frame
Within 1 month after surgerySponsors and contacts
Click on the lead sponsor to view all of their trials.
Chinese Academy of Sciences
Lead sponsor
Peking Union Medical College Hospital
Collaborator
First Affiliated Hospital of Kunming Medical University
Collaborator
Beijing YouAn Hospital
Collaborator
Zhujiang Hospital
Collaborator
Meng Chao Hepatobiliary Hospital of Fujian Medical University
Collaborator
First Affiliated Hospital of Wenzhou Medical University
Collaborator
Fifth Affiliated Hospital, Sun Yat-Sen University
Collaborator
Henan Provincial People's Hospital
Collaborator
Guangdong Provincial Hospital of Traditional Chinese Medicine
Collaborator
Shengjing Hospital
Collaborator
Beijing Tsinghua Changgeng Hospital
Collaborator
Yunnan Cancer Hospital
Collaborator
The First People's Hospital of Yunnan
Collaborator
Guizhou Provincial People's Hospital
Collaborator
First Affiliated Hospital of Guangxi Medical University
Collaborator
West China Hospital
Collaborator
ZhuHai Hospital
Collaborator
Dazhou Central Hospital
Collaborator
Eastern Hepatobiliary Surgery Hospital
Collaborator
Source ClinicalTrials.gov