AUTHOR=Qazi Arisar Fakhar Ali , Salinas-Miranda Emmanuel , Ale Ali Hamideh , Lajkosz Katherine , Chen Catherine , Azhie Amirhossein , Healy Gerard M. , Deniffel Dominik , Haider Masoom A. , Bhat Mamatha 

TITLE=Development of a Radiomics-Based Model to Predict Graft Fibrosis in Liver Transplant Recipients: A Pilot Study

JOURNAL=Transplant International

VOLUME=Volume 36 - 2023

YEAR=2023

URL=https://www.frontierspartnerships.org/journals/transplant-international/articles/10.3389/ti.2023.11149

DOI=10.3389/ti.2023.11149

ISSN=1432-2277

ABSTRACT=Liver Transplantation (LT) is complicated by recurrent fibrosis in 40% of recipients.We evaluated the ability of clinical and radiomic features to flag patients at risk of developing future graft fibrosis. CT scans of 254 patients at 3-6 months post-LT were retrospectively analyzed. Volumetric radiomic features were extracted from portal phase using an Artificial Intelligence-based tool (PyRadiomics). The primary endpoint was clinically significant (≥F2) graft fibrosis. A 10-fold cross-validated LASSO model using clinical and radiomic features was developed. 75 patients (29.5%) developed ≥F2 fibrosis by a median of 19 (4.3 -121.8) months. The maximum liver attenuation at venous phase (a radiomic feature reflecting venous perfusion), primary etiology, donor/recipient age, recurrence of disease, brain-dead donor, tacrolimus use at 3 months, and APRI score at 3 months were predictive of ≥F2 fibrosis. Combination of radiomics and the clinical features increased the AUC to 0.811 from 0.793 for the clinical-only model (p=0.008) and from 0.664 for the radiomics-only model (p<0.001) to predict future ≥F2 fibrosis. This pilot study exploring the role of radiomics, demonstrates that addition of radiomic features in clinical model increased the model's performance. Further studies are required to investigate the generalizability of this experimental tool.