FindTrial
Sign In

Developing and validating deep learning models in staging liver fibrosis

A deep learning model for staging liver fibrosis based on clinical features and dynamic contrast-enhanced CT images

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2000032229
Enrollment
Unknown
Registered
2020-04-23
Start date
2020-05-01
Completion date
Unknown
Last updated
2020-04-27

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

Conditions

Liver fibrosis

Interventions

Gold Standard:Paraffin pathological diagnosis results
Index test:Medical&#32
artificial&#32
intelligence&#32
technology&#32

Sponsors

Renji Hospital Affiliated to Shanghai Jiaotong University School of Medicine
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. Patients aged 18 and above; 2. Patients with pathological report including liver fibrosis stage; 3. Patients without liver operation history; 4. There were no patients with liver tumors larger than 10 cm in diameter; 5. Patients who had CT examination within 3 months after liver pathological evaluation.

Exclusion criteria

Exclusion criteria: 1. Patients with incomplete clinical data; 2. Patients unable to obtain CT images; 3. Patients whose liver tissue is not enough to stage fibrosis.

Design outcomes

Primary

MeasureTime frame
Deep learning features based on CT images;Bayesian Network features based on clinical data;Pathological diagnosis of paraffin;SEN, SPE, ACC, AUC of ROC;—

Countries

China

Contacts

Public ContactFeng Xue

Renji Hospital Affiliated to Shanghai Jiaotong University School of Medicine

fengxue6879@163.com+86 13701813929

Outcome results

None listed

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