Table 5 US imaging techniques in patients with liver disease
From: Artificial intelligence-based evaluation of prognosis in cirrhosis
First author, references | Image source | Statistical methods | Application scenario |
|---|---|---|---|
Hetland et al. [150] | UC/ CT | ROC analysis | Diagnosis of decompensated cirrhosis |
Bhanji et al. [152] | CT | Cox regression model | Prediction of HE |
Kang et al. [153] | CT | Cox regression model | Prediction of death in patients with compensated and early decompensated cirrhosis |
Engelmann et al. [154] | CT | Cox regression | Prediction of the occurrence of cirrhosis-related complications and mortality |
Kim et al. [156] | CT | Logistic regression | NAFLD fibrosis risk assessment |
Gidener et al. [159] | MRE | Cox regression analysis | Prediction of progression of CLD to cirrhosis |
Gidener et al. [160] | MRE | Cox regression analysis | Prediction of progression to compensated and decompensated cirrhosis in NAFLD |
Park et al. [161] | MRE | ROC analysis | NAFLD liver fibrosis recognition |
Loomba et al. [162] | MRE | ROC analysis | NAFLD liver fibrosis recognition |
Noureddin et al. [163] | MRI | Logistic regression | NAFLD liver fibrosis recognition |
Yu et al. [90] | MRI | Inverse probability weighting and propensity score matching analysis | Diagnosis of cirrhosis and HCC |
Wang et al. [165] | CT | Deep CNN model | Muscle division |
Liu et al. [167] | CT MRI | Deep CNN model | Recognition of portal hypertension |
Yu et al. [168] | CT | 3D FCN Model | HVPG classification |
Yasaka et al. [166] | MRI | DCNN model | Liver fibrosis staging |