FindTrial
Sign In

Deep Learning-Based Radiomics Models on Predicting Complications of liver transplantation

Functional development and application of quantitative method for fat detection of different human tissues by panoramic multimodal CT

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2200059026
Enrollment
Unknown
Registered
2022-04-23
Start date
2022-05-01
Completion date
Unknown
Last updated
2024-02-05

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

Conditions

Chronic liver disease

Interventions

Complication group:Deep learning

Sponsors

First Hospital of Jilin University
Lead Sponsor

Eligibility

Sex/Gender
Male
Age
18 Years to 70 Years

Inclusion criteria

Inclusion criteria: 1. All patients underwent OLT; 2. The enrolled patients were elder than 18 years old; 3. The patient underwent abdominal CT plain scan or plain plus enhancement examination within one month before liver transplantation; 4. Patients with primary hepatocellular carcinoma met the Hangzhou criteria for liver transplantation.

Exclusion criteria

Exclusion criteria: 1. Abdominal CT plain scans with poor image quality and artifact duplication make it impossible to measure the relevant indexes and outline the region of interest (ROI) on the level of third lumbar; 2. Patients who failed to follow up at the specified time interval.

Design outcomes

Primary

MeasureTime frame
Radiomics features;—

Countries

China

Contacts

Public ContactJiping Wang

First Hospital of Jilin University

jiping@jlu.edu.cn+86 15104311639

Outcome results

None listed

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