Related Experiment Video
Updated: Jun 30, 2025
07:03
Imaging and Quantification of the Hepatic Vasculature of Mice Using Ultrafast Doppler Ultrasound
Published on: July 19, 2024
785
Ultrasound-based Radiomics Predicts Short-term Outcomes in Hepatitis B Virus-related Acute-on-chronic Liver Failure
Xingzhi Huang1, Songsong Yuan2, Pan Xu1
1Department of Ultrasonography, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China.
Current Medical Imaging
|March 18, 2024
Summary
Ultrasound radiomics can predict outcomes in hepatitis B virus-associated acute-on-chronic liver failure (HBV-ACLF). This noninvasive approach complements clinical data, improving prognostic accuracy for better patient management.
Area of Science:
- Medical imaging
- Hepatology
- Computational pathology
Background:
- Prognosis in hepatitis B virus-associated acute-on-chronic liver failure (HBV-ACLF) is complex due to patient heterogeneity.
- Radiomics presents a potential noninvasive method for predicting outcomes in HBV-ACLF.
Purpose of the Study:
- To evaluate the efficacy of ultrasound-based radiomics in predicting outcomes for patients with HBV-ACLF.
Main Methods:
- 455 radiomic features were extracted from hepatic ultrasound images of 264 HBV-ACLF patients (184 training, 80 validation).
- A radiomic signature was developed using Cox-LASSO for 30-day mortality prediction.
- A combined clinical-radiomic nomogram (CCR-nomogram) was constructed and validated.
Main Results:
- The radiomic signature demonstrated good predictive performance (C-index 0.746 training, 0.747 validation).
- The CCR-nomogram achieved higher accuracy (C-indices 0.834 training, 0.819 validation).
- Radiomic features significantly improved prediction models (IDI 0.108-0.264, NRI 0.292-0.540).
Conclusions:
- Ultrasound radiomics provides valuable prognostic information in HBV-ACLF.
- This approach can enhance the accuracy of outcome prediction when combined with clinical data.
