Back
For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".
To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".
During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.
Preparing your E-Poster
Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.
E-Poster Submission Deadline
Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.
Please follow the instructions below to input your abstract title.
Abstract titles should be brief and reflect the content of the abstract.
Early detection of chronic kidney disease (CKD) is essential for improving patient outcomes. Interstitial fibrosis and tubular atrophy (IFTA) are key histopathologic predictors of CKD progression. Recently, noninvasive imaging—particularly ultrasound-based techniques enhanced by artificial intelligence (AI)—has been increasingly explored for predicting IFTA without the need for biopsy. However, the diagnostic performance of different AI models and imaging modalities remains unclear.
To systematically synthesize and compare the diagnostic accuracy—measured by the area under the curve (AUC) and 95% confidence interval (CI)—of AI-assisted imaging modalities, including B-mode ultrasound (US), shear wave elastography (SWE), and combined US+SWE, in predicting moderate-to-severe IFTA among patients with kidney disease.A systematic review and meta-analysis were conducted on published studies reporting AUC values of AI-based imaging models for IFTA detection. Literature searches were performed in PubMed, Scopus, and the Cochrane Library using MeSH terms such as “renal fibrosis,” “tubular atrophy,” “IFTA,” “artificial intelligence,” and “ultrasound.” Eligible studies included those employing imaging-based AI models to differentiate mild from moderate-to-severe IFTA. Studies were categorized by imaging modality. After excluding duplicates and studies lacking sufficient data, fixed-effect meta-analyses were performed to obtain pooled AUC values with 95% CIs. Egger’s test and funnel plots were applied to assess publication bias, and sensitivity analyses were conducted excluding studies with fewer than 30 patients.
Twenty studies comprising 1,547 patients were included: • B-mode US (n = 7): pooled AUC = 0.865 (95% CI: 0.847–0.883) • SWE (n = 10): pooled AUC = 0.837 (95% CI: 0.814–0.861) • US+SWE (n = 3): pooled AUC = 0.913 (95% CI: 0.881–0.945) Heterogeneity (I²) was minimal within subgroups. Sensitivity analyses yielded consistent results after excluding low-sample studies. Egger’s test indicated no significant publication bias (p > 0.05), though mild asymmetry was observed in the funnel plot.
AI-assisted ultrasound imaging—particularly the combination of B-mode and elastography—shows high diagnostic accuracy for noninvasive prediction of IFTA. Across modalities, AI-based models achieved robust performance (pooled AUC > 0.85). These findings support further development and clinical translation of AI-imaging tools in nephrology, enabling earlier detection and more precise characterization of renal fibrosis.
