AI and Cancer Research ── Liver ── 2026-10-05

A single new liver cancer paper shown in three steps: cohort, method, results. The cohort is 1928 hepatocellular carcinoma patients from five institutions. The method, MAVEN, is a fully automated deep learning system integrating MRI, whole-slide pathology images and clinical variables. Results: AUC 0.932 in the internal test cohort and 0.879-0.891 across four external cohorts, with risk stratification associated with early recurrence-free survival. Only the abstract was checked. — Image abstract — the whole article on one page (click to enlarge)

1 Liver papers. Lead: MAVEN: an automated multimodal framework for predicting VETC and early recurrence in HCC

Journals covered and how papers are chosen: see the index

Liver cancer: treatment, trials and AI

MAVEN: an automated multimodal framework for predicting VETC and early recurrence in HCC
npj Precision Oncology · 2026-10-02 · Evidence: Multicenter observational study (5 institutions, 1928 patients; model development with external validation)
Abstract
Accurate identification of aggressive tumor phenotypes remains a major challenge in hepatocellular carcinoma (HCC). Here, we developed and validated MAVEN (Multimodal Automated VETC Estimation Network), a fully automated multimodal deep learning system integrating magnetic resonance imaging (MRI), whole-slide histopathology images (WSIs), and clinical variables for predicting vessels encapsulating tumor clusters (VETC) and early recurrence risk. In this multicenter study including 1928 patients from five institutions, MAVEN demonstrated superior performance compared with unimodal and bimodal models, achieving an area under the curve (AUC) of 0.932 in the internal test cohort and 0.879-0.891 across four independent external cohorts. MAVEN-based risk stratification was significantly associated with early recurrence-free survival across all cohorts. Model explainability analyses revealed that both radiologic and histopathologic features contributed to prediction, with consistent spatial localization of high-risk regions. These findings suggest that multimodal integration enables robust and generalizable prediction of tumor aggressiveness and postoperative risk stratification.
Journal IF-equivalent: 8.9 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Liu W, Shen Z, Yang L, Zou W, Zhu Y, Li Y, et al. MAVEN: an automated multimodal framework for predicting VETC and early recurrence in HCC. npj Precis Onc. 2026 Oct 2 [Epub ahead of print]. doi:10.1038/s41698-026-01720-7.
Checked: Abstract only

← Back to this issue