Early-stage liver fibrosis is reversible; thus, accurate staging of liver fibrosis is of great importance.. Liver biopsy is the gold standard for the diagnosis of liver fibrosis; however, its invasive nature limits its clinical application. Accurate noninvasive staging of liver fibrosis remains challenging. Thus, there is an urgent need for a precise and reliable noninvasive diagnostic approach. A topological deep learning model combining topological data analysis and EfficientViT framework (TopoEfficientViT) was developed to effectively capture global contextual relationships in hepatobiliary phase MR images for assessment of staging liver fibrosis. Our retrospective study included patients with chronic liver diseases from June 2018 to July 2025, which was approved by our Institutional Review Board. Our data from a hospital site (Site A) in our institution were divided into a training set (n = 275) and a validation set (n = 75). The test set (n=65) was composed of data from a separate hospital site (Site B) in the same institution. A total of 415 patients (323 males, mean age 56.52±9.54 years; 92 females, mean age 58.86±9.68 years) were enrolled in the study. In the training set, the AUC and accuracy of TopoEfficientViT for staging liver fibrosis F1-2 vs. F3-4 were 0.942 and 0.906, respectively; for staging liver fibrosis F1-3 vs. F4 were 0.957 and 0.891, respectively. In the validation set, the AUC and accuracy for staging liver fibrosis F1-2 vs. F3-4 were 0.849 and 0.76, respectively; for staging liver fibrosis F1-3 vs. F4 were 0.861and 0.813, respectively. In the test set, the AUC and accuracy for staging liver fibrosis F1-2 vs. F3-4 were 0.829 and 0.769, respectively; for staging liver fibrosis F1-3 vs. F4 were 0.791 and 0.785, respectively. The TopoEfficientViT model had high predictive performance for staging liver fibrosis by integrating multi-scale persistent homology topology with convolutional networks.
Cystic echinococcosis (CE), caused by the metacestode of Echinococcus granulosus sensu lato, is a zoonosis that remains endemic across the Middle East, the Mediterranean basin, North Africa and South America, and the liver is the organ most frequently involved. Because serological assays are of limited sensitivity and specificity, imaging carries the diagnostic burden: ultrasonography (US) is the cornerstone for initial diagnosis, staging, treatment planning and longitudinal follow-up; computed tomography (CT) best defines anatomical location, vascular relationships, mural calcification and acute complications such as rupture and superinfection; and magnetic resonance imaging (MRI) more faithfully reproduces US-defined staging morphology than CT and provides superior soft-tissue contrast for assessing biliary involvement and separating CE cysts from cystic neoplasms. The aim of this pictorial review is fourfold: to illustrate the US, CT and MRI appearance of each World Health Organization Informal Working Group on Echinococcosis (WHO-IWGE) stage of hepatic CE and to explain how stage assignment translates directly into a stage-specific treatment decision—anti-parasitic treatment, percutaneous treatment, surgery or watch-and-wait; to present, stage by stage, the hepatic lesions that mimic CE and the findings that discriminate them; to depict the wall signs of the CE cyst that become visible with high-frequency linear transducers, including the three-layered wall, adherent brood capsules and hydatid sand; and to review the imaging of complicated CE together with the expected post-treatment appearance, procedure-related complications and the imaging strategy for detecting recurrence.
Advanced fibrosis in metabolic dysfunction-associated steatotic liver disease (MASLD) involves metabolic and anatomic remodeling beyond the liver. We developed and internally validated an interpretable CT-based score integrating abdominal body-composition and organ measurements and compared it with the Fibrosis-4 (FIB-4) index. We retrospectively studied 151 patients with biopsy-confirmed MASLD (86 advanced [F3–F4], 65 early-stage [F0–F2] fibrosis). Deep learning-based segmentation quantified abdominal adipose tissue, skeletal muscle, bone, liver, and spleen measurements. The CT-Fibrosis Score was developed using repeated (50×) stratified 5-fold cross-validation, with imputation, standardization, and feature selection confined to each training fold and inner 5-fold cross-validation for hyperparameter selection. Performance was based on out-of-fold predictions and compared with FIB-4 using the DeLong test. Sensitivity analyses addressed missing data, age dependence, and ascites. Four features were consistently selected: age, bone-to-abdominal-cavity volume ratio, visceral adipose tissue (VAT) density, and spleen index. The CT-Fibrosis Score achieved an out-of-fold AUC of 0.77 (95
To investigate the feasibility of automatic training data generation using virtual non-contrast (VNC) images of dual-energy CT and to evaluate the performance of medical segmentation models trained on auto-generated data. Training images were generated from contrast-enhanced CT (CECT) scans using VNC algorithm. Corresponding training labels were generated from iodine-density images via intensity thresholding. The paired VNC images and labels constituted the dataset (791 cases in total) for training non-enhanced CT (NECT) segmentation models. We attempted to train segmentation models with VNC images alone, as well as the combination of VNC and real NECT images. Models trained with auto-generated data effectively performed renal vein segmentation on NECT images, achieving Dice score of 69.60
