Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Nov;45(11):e70348.
doi: 10.1111/liv.70348.

Radiomics-Based Prognostication in Primary Sclerosing Cholangitis: A Proof-of-Concept Study

Laura Cristoferi  1 , Cesare Maino  2 , Davide Paolo Bernasconi  3   4 , Ilaria Ripamonti  5 , Miki Scaravaglio  5 , Alberto Savino  5 , Eugenia Pesatori  6 , Alessio Gerussi  1   5 , Eugenia Nofit  1 , Olga Falco  5 , Daphne D'Amato  5 , Francesca Gallivanone  7 , Chiara Alberzoni  2 , Raffaella Viganò  8 , Chiara Mazzarelli  8 , Luca Saverio Belli  8 , Marco Emilio Dinelli  9 , Massimiliano Mutignani  10 , Maria Grazia Valsecchi  3 , Rocco Corso  2 , Pietro Invernizzi  1   5 , Marco Carbone  5   8 , Davide Ippolito  2   5 , Elisabetta De Bernardi  3   5
Affiliations

Radiomics-Based Prognostication in Primary Sclerosing Cholangitis: A Proof-of-Concept Study

Laura Cristoferi et al. Liver Int. 2025 Nov.

Abstract

Background and aim: Risk assessment in primary sclerosing cholangitis (PSC) by magnetic resonance imaging (MRI) relies on semi-quantitative analysis, which can result in interpretation variability. Radiomics may offer a quantitative approach for risk stratification. This study aims to explore and validate MRI-derived radiomic features to identify high-risk PSC patients.

Methods: In this prospective study (January 2019-December 2022), consecutive PSC patients undergoing routine gadoxetate disodium-enhanced MRI were recruited. Using PyRadiomics, whole liver parenchyma features were extracted from five MRI sequences according to the Image Biomarker Standardisation Initiative (IBSI). Patients were categorised into risk groups based on the Mayo risk score (MRS) and liver stiffness measurement (LSM). Features associated with high-risk patients were selected and validated in an independent cohort. A survival analysis was conducted in the combined cohort to assess the prognostic value of the radiomic features for clinical events.

Results: One hundred and two PSC patients were enrolled in this study. Five radiomics features were associated with high risk in the training cohort. In the validation setting, GLRLM-Run Entropy in the fat-saturation T2 weighted imaging (FS-T2W) sequence was the only significant feature, with an odds ratio of 3.90 (CI 1.46-10.42, p = 0.007) for MRS and 2.97 (CI 1.33-6.66, p = 0.008) for LSM. Its prognostic potential on clinical outcome was confirmed by Cox regression analysis in the combined cohort (hazard ratio per 0.1 increase = 1.480, CI 1.226-1.786), showing excellent predictive performance (C-index = 0.857).

Conclusions: GLRLM-Run Entropy in FS-T2W is a novel radiomics-based biomarker for risk stratification in PSC patients. It is quantitative, standardised, easy to compute and cost-free, positioning it as a potential key innovation in PSC radiology-based biomarkers.

Trial registration: Clinicaltrial.gov ID: NC705618145.

Keywords: artificial intelligence; autoimmune liver diseases; quantitative radiology; radiomics; risk stratification; surrogate biomarkers.

PubMed Disclaimer

Conflict of interest statement

Data Transparency Statement: Deidentified individual participant data that underlie the reported results will be made available 3 months after publication for a period of 5 years. Proposals for access should be sent to pietro.invernizzi@unimib.it.

The authors declare no conflicts of interest.

Figures

FIGURE 1
FIGURE 1
Boxplots (A) and Density plots (B) of FS‐T2W GLRLM‐Run Entropy in the training cohort when using MRS (A) and LSM (B) as outcome.
FIGURE 2
FIGURE 2
Kaplan–Meier curves for clinical outcome (liver transplantation, liver‐related death, hepatic decompensation in the combined cohort by groups according to FS‐T2W GLRLM‐Run Entropy split using its median value (4.27)). Log Rank < 0.0001.
FIGURE 3
FIGURE 3
Two FS‐T2W sequences analysed in this study. Patient A is a low‐risk patient (MRS < 0, alkaline phosphatase within normal range, LSM 6.5 kPa, stable disease over time; GLRLM‐Run Entropy 4.14). Patient B exhibits intense fibro‐inflammatory activity (alkaline phosphatase 3.4×ULN, LSM 15.3 kPa) and underwent liver transplantation 20 months post‐MRI due to cholangiocarcinoma onset (GLRLM‐Run Entropy 4.94). The differences appreciable to the human eye are minimal but are quantitatively reflected in the radiomic feature.
See this image and copyright information in PMC

References

    1. Chazouilleres O., Beuers U., Bergquist A., et al., “EASL Clinical Practice Guidelines on Sclerosing Cholangitis,” Journal of Hepatology 77, no. 3 (2022): 761–806, 10.1016/J.JHEP.2022.05.011. - DOI - PubMed
    1. Grigoriadis A., Ringe K. I., Andersson M., Kartalis N., and Bergquist A., “Assessment of Prognostic Value and Interreader Agreement of ANALI Scores in Patients With Primary Sclerosing Cholangitis,” European Journal of Radiology 142 (2021): 109884, 10.1016/J.EJRAD.2021.109884. - DOI - PubMed
    1. “Introduction to Radiomics” (2020), 10.2967/jnumed.118.222893. - DOI
    1. Gerussi A., Scaravaglio M., Cristoferi L., et al., “Artificial Intelligence for Precision Medicine in Autoimmune Liver Disease,” Frontiers in Immunology 13 (2022): 966329, 10.3389/FIMMU.2022.966329. - DOI - PMC - PubMed
    1. Cazzagon N., El Mouhadi S., Vanderbecq Q., et al., “Quantitative Magnetic Resonance Cholangiopancreatography Metrics Are Associated With Disease Severity and Outcomes in People With Primary Sclerosing Cholangitis,” JHEP Reports 4, no. 11 (2022): 100577, 10.1016/J.JHEPR.2022.100577. - DOI - PMC - PubMed

LinkOut - more resources