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.
Autosomal dominant polycystic kidney disease (ADPKD) is a single-gene disorder characterized by the development of numerous cysts in the renal tubules. Deep learning algorithms, a subset of artificial intelligence techniques, provide powerful and effective solutions for these tasks, and various architectures have been proposed in the literature in recent years.
Accurate tools for forecasting individual outcomes in patients with autosomal dominant polycystic kidney disease (ADPKD) are lacking. In this study, we present a method developed using artificial intelligence (AI) for the regular measurement of total kidney volume (TKV).
We propose an artificial intelligence (AI)-driven approach using instance segmentation models based on the YOLOv9 architecture. The model was trained and validated on a dataset comprising 236 patients and 472 kidneys, with a total of 15,200 MRI slices obtained from five different MRI scanners. Four skilled radiologists carried out the initial manual annotations, and a 5-fold cross-validation at the patient level was performed to ensure the results could be generalized.
The YOLOv9 model achieved a Dice score of 0.8747 and an IoU of 0.812, outperforming YOLOv8 (Dice: 0.8713, IoU: 0.8057). Kidney volume estimation using the YOLOv9 model showed an average absolute percentage error of 6.08% compared with expert annotations. These results indicate a high concordance between the AI predictions and expert-derived volumes. Manual delineations had a bilateral average absolute variability of ~20%, reinforcing the benefit of AI methods.
The proposed AI-based methodology enables rapid, reliable, and reproducible measurement of TKV in patients with ADPKD. The YOLOv9c-Seg model demonstrated a strong agreement with expert annotations and offered a scalable solution for clinical integration. This study highlights the potential of real-time, license-free AI models to support clinical decision-making and enhance efficiency in nephrology imaging workflows.
