Abstract
Background and Aims
Interstitial fibrosis / tubular atrophy (IFTA) is a common, irreversible and progressive form of chronic allograft injury, and it is considered a critical predictor of kidney allograft outcomes. Inflammation, both microvascular and interstitial, is on the contrary regarded as a reversible form of graft injury. Since treatments for rejection and other causes of graft dysfunction bear substantial toxicity and could have limited efficacy, the extent of irreversible graft scarring is a crucial information for the clinician, to evaluate risks and benefits of specific therapies. The diagnosis of kidney graft pathology is acquired through graft biopsy, which is an invasive procedure and can be subjected to sampling bias. Magnetic resonance imaging (MRI), especially with functional techniques, has emerged as a possibility for non-invasive estimation of tissue fibrosis; nevertheless, functional MRI is not widely available. Texture analysis MRI (TA-MRI) is a radiomic technique that provides a quantitative assessment of tissue heterogeneity from standard MRI images, generating features that can be fitted into a machine-learning model to assess their ability to predict clinical or histological parameters.
Method
Single-center cross-sectional observational cohort study enrolling kidney transplant recipients who underwent graft biopsy and graft MRI imaging within 6 months from biopsy, both on clinical indication, at the “Azienda Ospedaliero-Universitaria di Modena”, Italy. The study was approved by the local Ethical Committee (AOU0010167/20). The primary outcome was to identify the best TA-MRI features subset for estimation of IFTA > 50% in graft biopsy. Secondary outcomes were estimation of: IFTA > 25%, presence of total inflammation (ti) and microvascular inflammation (glomerulitis + peritubular capillaritis [g+ptc]). Graft biopsy was reported according to Banff 2017 system. Radiomic analysis was performed on axial T2 pre-contrast and T1 fat-suppressed post-contrast sequences. The whole renal parenchyma (PAR) was segmented and labelled on T2 and T1, renal cortex (COR) only on T2. After imaging preprocessing, PyRadiomics was used to extract radiomic features. After removal of shape features, 93 features were included and reduced using LASSO regression to produce radiomic signatures. These were introduced in Machine Learning (ML) models to test the association with outcomes. Results are reported as AUC and a value of sensitivity and specificity.
Results
Sixty patients were included in the study, and 67 graft biopsy – graft MRI pairs were available for analysis. Demographic and clinical characteristics of enrolled patients are depicted in table 1; histological diagnosis and main Banff histological parameters from graft biopsies in table 2. Among ML models, three showed an acceptable performance. T2 COR “firstorder_minimum/firstorder_range/glrlm_run_entropy” for IFTA>50% (AUC=0.77, sensitivity=73%, specificity=71%), T1 PAR “firstorder_energy” for IFTA>25% (AUC=0.71, sensitivity=74%, specificity=51%), T1 PAR “firstorder_energy/gldm_small_dependence_low_gray_level_emphasis” for g+ptc >0 (AUC=0.74, sensitivity= 78%, specificity=68%); see figures 1–3. No acceptable prediction was detected for ti >0.
Conclusion
Our study shows that TA-MRI feature signatures can predict the degree of IFTA in graft biopsies, with an acceptable diagnostic performance. These results suggest to further investigating TA-MRI from standard MRI sequences as potential tool to assess graft chronic parenchymal injury. Moreover, since graft biopsy results can be jeopardized by limited sample size, we hypothesize that evaluation of IFTA through TA-MRI could provide more comprehensive information regarding the whole parenchyma. To test this hypothesis, we are currently evaluating the association of TA-MRI radiomic features and baseline eGFR and eGFR variation over time.
A user-friendly tool for cloud-based whole slide image segmentation, with examples from renal histopathology
