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: FR-PO032

Automated Pipeline for Peritubular Capillary Inflammation Scoring

Session Information

Category: Augmented Intelligence, Digital Health, and Data Science

  • 300 Augmented Intelligence, Digital Health, and Data Science

Authors

  • Gupta, Akshita, University of Florida Department of Health Outcomes and Biomedical Informatics, Gainesville, Florida, United States
  • Border, Samuel, University of Florida Department of Biomedical Engineering, Gainesville, Florida, United States
  • Delsante, Marco, Johns Hopkins University Department of Pathology, Baltimore, Maryland, United States
  • Mimar, Sayat, University of Florida Department of Medicine - Quantitative Health Section, Gainesville, Florida, United States
  • Paul, Anindya S., University of Florida Department of Medicine - Quantitative Health Section, Gainesville, Florida, United States
  • Rosenberg, Avi Z., Johns Hopkins University Department of Pathology, Baltimore, Maryland, United States
  • Sarder, Pinaki, University of Florida Department of Medicine - Quantitative Health Section, Gainesville, Florida, United States
Background

Antibody-mediated rejection (AMR) can occur after kidney transplantation and is characterized by immune cell-mediated microvascular injury in response to donor-specific antibodies (DSA) and results in progressive graft survival and function. Using dual immunostaining for endothelium (anti-CD34)/leukocytes (anti-CD45), we identified peritubular capillaries (PTCs) and intracapillary leukocytes to determine the inflamed peritubular capillary ratio (iptcr), a quantitative Microvascular Inflammation (MVI) score that in a previous study correlated with renal graft failure and DSA strength.

Methods

Initially, we selected our stain vectors through QuPath. Used them to implement color deconvolution to separate CD34 (Red) (PTCs) and CD45 (DAB) (leukocytes). Thresholding and noise removal techniques were applied to each WSI to segment PTCs and leukocytes. The iptcr was determined by the ratio of total leukocyte (>1 cell) containing PTCs to total PTCs. Automated iptcr scores were compared to ground truth iptcr from manual scoring.

Results

There was a high correlation between pathologist and automated iptcr score (R-square: 0.83). Perhaps even more important automated iptcr was 4X faster versus manual pathologist scoring for each WSI.

Conclusion

Our automated approach based on using a relatively simple analytical pipeline (intensity transformation/enhancement, texture analysis, binarization, and morphological processing) makes iptcr scoring feasible. Our early results demonstrate the potential of the iptcr score pipeline as an efficient supplementary tool for improved AMR evaluation to replace the current discontinuous scoring system in place. Further validation and exploration of larger cohort are warranted.

Funding

  • NIDDK Support