Prediction of Significant Liver Fibrosis
- Conditions
- Liver Fibrosis
- Registration Number
- NCT06509230
- Lead Sponsor
- Huang Haijun
- Brief Summary
The deep learning method based on convolutional neural network (CNN) was used to extract the relevant features of liver fibrosis classification from the multi-modal information of digital pathological sections, clinical parameters and biomarkers of a large number of existing cases of liver puncture, and the U-Net architecture of CNN was used to segment and extract the features of clinical medical images.
- Detailed Description
Patients with chronic hepatitis B underwent B-ultrasound-guided liver biopsy, and were divided into mild liver fibrosis group (fibrosis grade 0-1, S1), significant liver fibrosis group (fibrosis grade 2, S2), advanced liver fibrosis group and early cirrhosis group (fibrosis grade 3-4, S3-4) according to the pathological results.In this study, 200 patients with different degrees of liver fibrosis and 200 normal volunteers were collected from 2018 to 2022, and their clinical biochemical data, imaging data and peripheral blood samples were collected.The pathological microenvironment characteristics, imaging characteristics, clinical parameter characteristics and other data of patients were extracted, and the distillation learning method based on teacher-student model was adopted to develop and construct a multi-modal big data analysis model for accurate grading of liver fibrosis, so as to achieve a non-invasive intelligent grading diagnosis system for liver fibrosis.
Recruitment & Eligibility
- Status
- RECRUITING
- Sex
- All
- Target Recruitment
- 700
- Age of 18-60 years old
- The diagnosis of chronic hepatitis B is in line with the diagnostic criteria of China's 2019 Chronic Hepatitis B Prevention and Treatment Guidelines, and the diagnosis of non-alcoholic fatty liver is in line with the Asian Pacific Hepatology Association guidelines
- Imaging showed no liver cancer
- There are contraindications for liver biopsy
- Liver pathology did not meet the criteria
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Model development 2024.6-2024.12 Imaging (such as CT scan, MRI, X-ray, etc.) features and clinical parameters of patients were extracted, including population baseline characteristics (such as age, gender, comorbiditions, etc.), blood biochemical indicators (such as blood glucose, lipids, liver function indicators, etc.), and blood cytology indicators (such as white blood cell count, red blood cell count, etc.). Completed case selection and cohort establishment, multi-modal feature extraction and model development
- Secondary Outcome Measures
Name Time Method Build a multi-modal big data liver fibrosis early warning cloud platform system 2025.1-2025.12 We intend to design a cloud platform with data storage, processing and analysis components.Select the appropriate technology stack to ensure that the platform has the ability to handle large-scale data, and has good scalability and performance.The previously built multimodal liver fibrosis precision typing model was then embedded into the platform, ensuring that the model could handle a variety of data types and integrate seamlessly with other components of the platform.At the same time, the stream processing technology is used to integrate the real-time monitoring and analysis function of the platform, so as to make rapid prediction and classification of the newly acquired liver fibrosis case data.The accuracy and stability of the model were further verified in the multi-center clinical data, and the multi-modal big data liver fibrosis early warning cloud platform system was built
Trial Locations
- Locations (1)
Haijun Huang
🇨🇳Hangzhou, Zhejiang, China