ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on X

Kidney Week

Abstract: SA-PO0004

Kidease 1.0: A Web-Based Platform for Histopathological Image Analysis on Deceased Donor Kidney Biopsies

Session Information

Category: Artificial Intelligence, Digital Health, and Data Science

  • 300 Artificial Intelligence, Digital Health, and Data Science

Authors

  • Abdelazim, Haitham M, University of Florida, Gainesville, Florida, United States
  • Paul, Anindya S., University of Florida, Gainesville, Florida, United States
  • Rodrigues, Luis, Centro Hospitalar e Universitario de Coimbra EPE, Coimbra, Coimbra District, Portugal
  • Gupta, Akshita, University of Florida, Gainesville, Florida, United States
  • Sarder, Pinaki, University of Florida, Gainesville, Florida, United States
Background

In kidney transplantation, histopathologic evaluation of deceased donor kidney biopsies plays a central role in determining organ suitability and allocation. In most cases, donor kidney biopsies are assessed by general or on-call pathologists working under time-critical conditions with differences in experience and training between specialties. We developed Kidease to standardize and streamline the evaluation of donor biopsies through integrated Computational Renal Pathology Suite (ComPRePS) computational pathology infrastructure, clinical data linkage and semi-automated scoring.

Methods

Kidease was developed in close collaboration with clinicians and pathologists. During testing, more than 200 whole-slide images (WSI) were uploaded to the platform, where pathologists annotated, segmented and scored key histologic lesions using a collaborative human-AI Remuzzi classification workflow by automatically generating morphometric pathomics via ComPRePS.

Results

Kidease is accessible via https://kidease.rc.ufl.edu. Compared to manual processes, assessment with Kidease provides a clear and guided workflow that is also fast, interactive and improves the user experience during initial testing. Users can upload images and integrate their clinical information, review analysis results and interact with other pathologists within the platform, enabling confident decision making.

Conclusion

Kidease lays the foundation for a reproducible, data-driven approach to kidney transplant evaluation. A fully integrated web-based platform with user-friendly interface that supports multi-institutional access and cross-site collaboration, enabling future integration of other artificial intelligence tools to improve prediction of transplant outcomes.

Funding

  • NIDDK Support

Digital Object Identifier (DOI)