Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
Development of Fully Automated Models for Staging Liver Fibrosis Using Non-Contrast MRI and Artificial Intelligence: A Retrospective Multicenter Study
33 Pages Posted: 25 Jun 2024
More...Abstract
Background: Accurate identification of early liver fibrosis (LF) is essential for clinical management in chronic liver disease. While non-contrast MRI (NC-MRI) yields valuable information for liver assessment, its effectiveness in predicting LF remains underexplored. This study aimed to develop and validate artificial intelligence (AI)-powered models utilizing NC-MRI for staging LF.
Methods: A total of 1726 patients from center A were retrospectively collected and divided into development (n = 1208) and internal test (n = 518) cohorts. An external test cohort consisting of 337 individuals from six centers was also included. All participants underwent NC-MRI (T1-weighted imaging, T1WI; and T2-fat-suppressed imaging, T2FS) and liver biopsies. Two classification models (CMs), named T1 and T2FS, were trained on respective image types using 3D contextual transformer networks and evaluated on both test cohorts. Additionally, three CMs—Clinic, Image, and Fusion—were developed using clinical features, T1 and T2FS scores, and their integration via logistic regression. Classification effectiveness of CMs was assessed using the area under the receiver operating characteristic curve (AUC). A comparison was conducted between the optimal models (OMs) and other methods (FibroScan, five serum biomarkers, and six radiologists).
Findings: Fusion models outperformed the Image, T2FS, T1, and Clinic models in both test cohorts, achieving AUCs of 0.810 for significant fibrosis, 0.881 for advanced fibrosis, and 0.918 for cirrhosis, respectively, in the internal test cohort, and 0.808, 0.868, and 0.925 in the external test cohort. The OMs, Fusion models, demonstrated superior performance in AUC, surpassing FibroScan, serum biomarkers (APRI, FIB-4, GPR, RPR, and King score), and radiologists (three senior and three junior) for staging LF. Radiologists, with the aid of the OMs, can further improve the performance of LF assessment.
Interpretation: AI-powered models utilizing NC-MRI, including T1WI and T2FS, accurately stage LF.
Funding: National Natural Science Foun-dation of China (No. 82071885); The Innovation Talent Program in Science and Tech-nologies for Young and Middle-aged Scientists of Shenyang (RC210265); General Pro-gram of the Liaoning Provincial Education Department (LJKMZ20221160); Liaoning Provincial Science and Technology Plan Joint Foundation.
Declaration of Interest: We declare no competing interests related to this study.
Ethical Approval: Approval for this retrospective study was obtained from the Institutional Ethics Review Board at the hospital (Ref. No.2024PS863K), with the need for informed consent waived due to its retrospective nature.
Keywords: Liver Fibrosis, Non-Contrast MRI, Artificial Intelligence, Multicenter Study
Suggested Citation: Suggested Citation