Noninvasive Tumor Profiling: Quantitative Contrast-Enhanced MRI Markers Predict PD-L1 and CTNNB1 Status in Hepatocellular Carcinoma.

Abstract

Systemic molecular-targeted therapy is the standard of care for patients presenting with advanced-stage hepatocellular carcinoma (HCC); however, tumor response rates are limited, mainly owing to HCC biomolecular and pathologic heterogeneity. Therefore, novel markers for noninvasive molecular profiling are needed. To determine whether advanced image analysis and machine learning on routinely acquired MRI scans can help predict HCC molecular profiles, thereby allowing biomarker-guided treatment allocations. This single-center retrospective study included treatment-naive patients with HCC who underwent tumor resection or liver transplant between September 2006 and February 2022. Multiparametric contrast-enhanced MRI data were obtained, and quantitative and qualitative imaging markers were extracted from lesion and liver segmentations. Pathologic analysis of the resected samples was performed via immunohistochemistry to assess p53 loss of function; catenin beta 1 (CTNNB1) activation; forkhead box M1 activation; and programmed cell death ligand 1 (PD-L1), phosphorylated AKT serine/threonine kinase, phosphorylated SMAD2/3, and sterol O-acyltransferase 1 expression. For each molecular profile outcome, a multivariable logistic regression model was built separately using quantitative imaging, qualitative imaging, or clinical data. The area under the receiver operating characteristic curve (AUC) was used to evaluate model discriminatory performance, and DeLong tests were performed to compare AUCs across models trained on the different data. Seventy-five patients with T1-weighted, contrast-enhanced, dynamic MRI scans (mean age, 65.7 years ± 9.43 [SD]; 60 males) were included. Receiver operating characteristic curve analysis demonstrated the good discriminatory performance of logistic regression models trained on quantitative imaging data for PD-L1, p53, and CTNNB1, with AUCs of 0.85 (95% CI: 0.74, 0.96), 0.79 (95% CI: 0.66, 0.93), and 0.7 (95% CI: 0.46, 0.93), respectively. Models trained on clinical and qualitative imaging data yielded lower AUCs across profiles, of 0.36 (95% CI: 0.2, 0.53; <i>P</i> < .001) and 0.41 (95% CI: 0.21, 0.62; <i>P</i> = .003), respectively, for p53. Quantitative MRI markers derived from whole tumor and liver volumes can potentially predict p53, PD-L1, and CTNNB1 status in HCC. © RSNA, 2025 <i>Supplemental material is available for this article.</i> See also the editorial by Cannella in this issue.