Skip to content

Malignant screening of focal liver lesions based on deep learning

Malignant screening of focal liver lesions based on deep learning

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500112344
Enrollment
Unknown
Registered
2025-11-12
Start date
2025-11-21
Completion date
Unknown
Last updated
2025-11-17

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

Conditions

focal liver lesions

Interventions

Gold Standard:Hepatocellular carcinoma, intrahepatic cholangiocarcinoma and other malignant diseases must be pathologically confirmed
Benign lesions must satisfy either of the following conditions: (1) jointly diagnosed and confirmed by three radiologists
(2) verified through follow-up using two imaging modalities for at least six months.
Index test:The early screening process for liver cancer based on "CT imaging + deep learning"

Sponsors

West China Hospital, Sichuan University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1. Patient age >= 18 years; 2. No history of liver resection, transarterial chemoembolisation (TACE), or radiofrequency ablation (RFA) prior to CT examination; 3. Malignant tumour confirmed by pathology; 4. Benign lesions must meet either of the following criteria: (1) Diagnosis confirmed by three radiologists; (2) Verified through follow-up with at least two imaging modalities over a minimum period of six months.

Exclusion criteria

Exclusion criteria: 1. Substandard image quality; 2. Previous surgical intervention; 3. Mismatch between target detection box and lesion; 4. Absence of CT arterial phase (AP)/portal venous phase (PVP) images.

Design outcomes

Primary

MeasureTime frame
Area under the curve;Recall ;Precision;specificity;sensitivity;

Countries

China

Contacts

Public ContactWei Yi

Department of radiology, West China Hospital, Sichuan University

drweiyi057@163.com+86 181 0800 8568

Outcome results

None listed

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