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

Nickolai J Matuschewski^{1

2}, Rabea Sobirey^{1

2}, Margarita Revzin¹, Tal Zeevi^{1

3}, Moritz Gross^{1

2}, Victor Kasolowsky^{1

2}, Annabella Shewarega¹, Ellen Meister^{1

2}, Tabea Kao^{1

2}, Jonathan Tefera¹, Khaled Bousabarah⁴, Ramesh Batra⁵, Mario Strazzabosco⁶, MingDe Lin^{1

7}, Bernhard Gebauer², Lynn Jeanette Savic², James Duncan^{1

6}, David C Madoff^{1

8

9}, Xuchen Zhang¹⁰, Julius Chapiro^{1

3

6}

Affiliations

¹ Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
² Department of Radiology, Charité-Universitaetsmedizin Berlin, corporate member of Freie Universitaet Berlin and Humboldt-Universitaet, 10117 Berlin, Germany.
³ Department of Biomedical Engineering, School of Engineering and Applied Sciences, 17 Hillhouse Avenue, New Haven, CT 06520, USA.
⁴ Visage Imaging GmbH, Lepsiusstraße 70, 12163 Berlin, Germany.
⁵ Transplantation and Immunology, Department of Surgery, Yale University School of Medicine, 333 Cedar Street, New Haven, CT, 06520, USA.
⁶ Department of Medicine, Liver Center, Section of Digestive Diseases, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
⁷ Visage Imaging, 12625 High Bluff Drive, Suite 205, San Diego, CA 29130, USA.
⁸ Department of Medicine, Section of Medical Oncology, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
⁹ Department of Surgery, Section of Surgical Oncology, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
¹⁰ Department of Surgical Pathology, Yale University School of Medicine, 333 Cedar St., New Haven, CT 06250, USA.

PMID: 40762840
PMCID: PMC12405729 (available on 2026-08-01)
DOI: 10.1148/radiol.242750

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

Nickolai J Matuschewski et al. Radiology. 2025 Aug.

. 2025 Aug;316(2):e242750.

doi: 10.1148/radiol.242750.

Authors

Affiliations

¹ Department of Radiology and Biomedical Imaging, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
² Department of Radiology, Charité-Universitaetsmedizin Berlin, corporate member of Freie Universitaet Berlin and Humboldt-Universitaet, 10117 Berlin, Germany.
³ Department of Biomedical Engineering, School of Engineering and Applied Sciences, 17 Hillhouse Avenue, New Haven, CT 06520, USA.
⁴ Visage Imaging GmbH, Lepsiusstraße 70, 12163 Berlin, Germany.
⁵ Transplantation and Immunology, Department of Surgery, Yale University School of Medicine, 333 Cedar Street, New Haven, CT, 06520, USA.
⁶ Department of Medicine, Liver Center, Section of Digestive Diseases, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
⁷ Visage Imaging, 12625 High Bluff Drive, Suite 205, San Diego, CA 29130, USA.
⁸ Department of Medicine, Section of Medical Oncology, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
⁹ Department of Surgery, Section of Surgical Oncology, Yale University School of Medicine, 333 Cedar St, New Haven, CT 06520, USA.
¹⁰ Department of Surgical Pathology, Yale University School of Medicine, 333 Cedar St., New Haven, CT 06250, USA.

PMID: 40762840
PMCID: PMC12405729 (available on 2026-08-01)
DOI: 10.1148/radiol.242750

Abstract

Background: 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.

Purpose: 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.

Materials and Methods: 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.

Results: 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; P < .001) and 0.41 (95% CI: 0.21, 0.62; P = .003), respectively, for p53.

Conclusion: Quantitative MRI markers derived from whole tumor and liver volumes can potentially predict p53, PD-L1, and CTNNB1 status in HCC.

Supplemental material is available for this article.

See also the editorial by Cannella in this issue.

PubMed Disclaimer

Conflict of interest statement

Disclosures of conflicts of interest: N.J.M. Stock or stock options in Merck & Co. R.S. No relevant relationships. M.R. No relevant relationships. T.Z. No relevant relationships. M.G. Support for attending meetings and/or travel from the Rolf W. Günther Foundation for radiological sciences. V.K. Patents planned, issued or pending with Yale University. A.S. Grants or contracts from Heinrich Hertz Foundation, Ministry of Culture and Science of the German State of North Rhine-Westphalia, Rolf W. Günther Foundation for Radiological Sciences, German Academic Exchange Service, Dr. Constantine Cope Medical Student Award from the Society of Interventional Radiology, Trainee Research Award from the RSNA; support for attending meetings and/or travel from AASLD. E.M. No relevant relationships. T.K. No relevant relationships. J.T. No relevant relationships. K.B. No relevant relationships. R.B. No relevant relationships. M.S. No relevant relationships. M.D.L. Support from Visage Imaging (NIH/NCI R01 CA160771 NIH/NCI R01 CA206180); leadership or fiduciary role in other board, society, committee or advocacy group, paid or unpaid from Tau Beta Pi Engineering Honor Society; stock or stock options in Visage Imaging. B.G. Consulting fees from INARI, BAYER, BOSTON, Parexel/CALYX, EWIMED, Beacon Bioscience/ICON; payment or honoraria for lectures, presentations, speakers bureaus, manuscript writing or educational events from BD, COOK, SIRTeX, Guerbet, Terumo, MSD, Roche, Siemens, Merck, Elsai, AstraZeneca, Pfizer. L.J.S. Grants or contracts from Guerbet German Research Foundation; consulting fees from Guerbet; payment or honoraria for lectures, presentations, speakers bureaus, manuscript writing or educational event from Guerbet; support for attending meetings and/or travel from Guerbet, SIO, SIR; participation on a Data Safety Monitoring Board or Advisory Board for Guerbet and Replimune; leadership or fiduciary role in other board, society, committee or advocacy group, paid or unpaid from RSNA. J.D. Support from NIH/NCI; payment or honoraria for lectures, presentations, speakers bureaus, manuscript writing or educational events from University of Pennsylvania; patents planned, issued or pending (US Patent App. 17 265862); leadership or fiduciary role in other board, society, committee or advocacy group, paid or unpaid (co-Editor-in-Chief, Medical Image Analysis journal [Elsevier]). D.C.M. Consultant to the Editor of Radiology. X.Z. No relevant relationships. J.C. Grants or contracts from Boston Scientific; consulting fees from AstraZeneca, Eisai, Guerbet, Bayer; associate editor of Radiology.

References

1. Rumgay H , Arnold M , Ferlay J , et al . Global burden of primary liver cancer in 2020 and predictions to 2040 . J Hepatol 2022. ; 77 ( 6 ): 1598 – 1606 . - PMC - PubMed
1. Akinyemiju T , Abera S , Ahmed M , et al. ; Global Burden of Disease Liver Cancer Collaboration . The Burden of Primary Liver Cancer and Underlying Etiologies From 1990 to 2015 at the Global, Regional, and National Level: Results From the Global Burden of Disease Study 2015 . JAMA Oncol 2017. ; 3 ( 12 ): 1683 – 1691 . - PMC - PubMed
1. Park JW , Chen M , Colombo M , et al . Global patterns of hepatocellular carcinoma management from diagnosis to death: the BRIDGE Study . Liver Int 2015. ; 35 ( 9 ): 2155 – 2166 . - PMC - PubMed
1. Finn RS , Qin S , Ikeda M , et al. ; IMbrave150 Investigators . Atezolizumab plus Bevacizumab in Unresectable Hepatocellular Carcinoma . N Engl J Med 2020. ; 382 ( 20 ): 1894 – 1905 . - PubMed
1. Losic B , Craig AJ , Villacorta-Martin C , et al . Intratumoral heterogeneity and clonal evolution in liver cancer . Nat Commun 2020. ; 11 ( 1 ): 291 . - PMC - PubMed

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

Substances

Actions
Actions
Actions
Actions
Actions
Actions

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

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

Affiliations

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

Authors

Affiliations

Abstract

Conflict of interest statement

References

MeSH terms

Substances

Grants and funding