1279-Noninvasive Phenotyping for Liver Cancer Prognosis

This study introduces MTV-Net, a novel artificial intelligence framework designed to analyze the vascular microenvironment of primary liver cancers through routine CT scans. By extracting quantitative vascular features, the researchers developed two noninvasive biomarkers that accurately identify tumor subtypes and predict post-surgical recurrence risk. This multi-task learning approach proved effective across different patient groups, offering a way to reclassify biologically complex tumors like combined hepatocellular-cholangiocarcinoma. Radiogenomics analysis further revealed that these imaging patterns are linked to specific gene pathways involved in vessel formation and tissue remodeling. Ultimately, this technology provides a biologically grounded tool to improve personalized treatment and prognostic accuracy without requiring invasive biopsies.References:Xin H, Wang Y, Xin H, et al. Noninvasive imaging analysis of vascular phenotypes improves prognostic stratification in primary liver cancer: a multi-cohort study[J]. npj Precision Oncology, 2025.前往小宇宙评论区与主播互动