Citations

Abstract The prevalence of steatotic liver disease (SLD) is rising globally, presenting a significant public health challenge. While non-contrast computed tomography (CT) scans hold promise for the opportunistic detection of SLD, their full potential has not been systematically explored. Clinical indicators, such as serum data, are crucial for monitoring the progression of SLD. We introduce a novel Multimodal AI for Opportunistic Steatotic Liver Disease Screening (MAOSS), which integrates demographic data, serum tests, conventional CT biomarkers, and deep learning-derived CT image features to enhance model performance and explainability. MAOSS employs an innovative learning strategy, trained on a large-scale dataset (n = 1,783) encompassing both histopathologically-confirmed SLD and radiologically-reported steatosis cases. The model underwent extensive retrospective validation using steatosis grades derived from both histology and MRI-PDFF across internal and external datasets (n = 913), as well as real-world patient data (n = 18,504). It accurately detected mild to severe steatosis (≥ S1) with AUCs ranging from 0.903 to 0.929. Notably, MAOSS significantly improved the overall AUC for radiologists (n = 11) from 0.709 to 0.798 (p < 0.001). Furthermore, MAOSS was applied to optimize the standard clinical pathway for a simulated primary risk screening of SLD patients (n = 1,192), resulting in the identification of 31% more patients at risk of steatohepatitis and liver fibrosis progression, highlighting its potential to enhance SLD detection and management.

Background and Aims: Transforming growth factor-beta 1 (TGFβ1) induces HSC activation into metastasis-promoting cancer-associated fibroblasts (CAFs), but how the process is fueled remains incompletely understood. We studied metabolic reprogramming induced by TGFβ1 in HSCs. Approaches and Results: Activation of cultured primary human HSCs was assessed by the expression of myofibroblast markers. Glucose transporter 1 (Glut1) of murine HSC was disrupted by Cre recombinase/LoxP sequence derived from bacteriophage P1 recombination (Cre/LoxP). Plasma membrane (PM) Glut1 and glycolysis were studied by biotinylation assay and the Angilent Seahorse XFe96 Analyzer. S.c. HSC/tumor co-implantation and portal vein injection of MC38 colorectal cancer cells into HSC-specific Glut1 knockout mice were performed to determine in vivo relevance. Transcriptome was obtained by RNA sequencing of HSCs and spatialomics with MC38 liver metastases. TGFβ1-induced CAF activation of HSCs was accompanied by elevation of PM Glut1, glucose uptake, and glycolysis. Targeting Glut1 or Src by short hairpin RNA, pharmacologic inhibition, or a Src SH3 domain deletion mutant abrogated TGFβ1-stimulated PM accumulation of Glut1, glycolysis, and CAF activation. Mechanistically, binding of the Src SH3 domain to SH3 domain–binding protein 5 led to a Src/SH3 domain–binding protein 5/Rab11/Glut1 complex that activated Rab11-dependent Glut1 PM transport under TGFβ1 stimulation. Deleting the Src SH3 domain or targeting Glut1 of HSCs by short hairpin RNA or Cre recombinase/LoxP sequence derived from bacteriophage P1 recombination suppressed CAF activation in mice and MC38 colorectal liver metastasis. Multi-omics revealed that Glut1 deficiency in HSCs/CAFs suppressed HSC expression of tumor-promoting factors and altered MC38 transcriptome, contributing to reduced MC38 liver metastases. Conclusion: The Src SH3 domain–facilitated metabolic reprogramming induced by TGFβ1 represents a target to inhibit CAF activation and the pro-metastatic liver microenvironment.