Skip to content

Development of an intelligent system for focal liver lesions based on multiparametric MRI: an international multicenter study

Development of an intelligent system for focal liver lesions based on multiparametric MRI: an international multicenter study

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2200061931
Enrollment
Unknown
Registered
2022-07-11
Start date
2022-07-15
Completion date
Unknown
Last updated
2023-04-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Hepatocellular carcinoma

Interventions

Gold Standard:1. Three senior reviewers reached a consensus on the reading results
2. Histopathological examination within 30 days or imaging follow-up for at least 2 years.
Index test:Artificial&#32
intelligence&#32

Sponsors

West China Hospital, Sichuan University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Age >= 18 years old; 2. Patients with high risk factors for HCC, including chronic hepatitis B, liver cirrhosis, and previous or current HCC; 3. Multi-parameter enhanced MRI examination at baseline; 4. Accurate and reliable gold standard results of liver lesions, including histopathological examination within 30 days after baseline MRI examination or imaging follow-up for at least 2 years.

Exclusion criteria

Exclusion criteria: 1. Liver cirrhosis caused by various vascular or congenital causes (such as Budd-Chiari syndrome, hereditary hemorrhagic telangiectasia, etc.); 2. Previously received treatment for focal liver lesions; 3. The quality of multi-parameter enhanced MRI images is poor (such as: severe motion artifacts, lack of scan sequences that make it impossible to evaluate lesions); 4. Histopathological examination or post-baseline imaging follow-up is not enough to confirm the diagnosis of focal liver lesions.

Design outcomes

Primary

MeasureTime frame
Detection rate of the AI model;Individual LI-RADS feature classification accuracy of the AI model;LI-RADS categorization accuracy of the AI model;HCC diagnostic accuracy of the AI model;

Secondary

MeasureTime frame
Time evaluating per-patient/per-lesion;MR sequence identification accuracy of the AI model;

Countries

China

Contacts

Public ContactBin Song

Department of Radiology, West China Hospital, Sichuan University

cjr.songbin@vip.163.com+86 18980601592

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026