ASN's Mission

ASN leads the fight to prevent, treat, and cure kidney diseases throughout the world by educating health professionals and scientists, advancing research and innovation, communicating new knowledge, and advocating for the highest quality care for patients.

learn more

Contact ASN

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

email@asn-online.org

202-640-4660

The Latest on Twitter

Kidney Week

Abstract: SA-OR35

Computationally Extracted Peritubular Capillary Shape Is Associated with Progression in Glomerular Diseases

Session Information

Category: Glomerular Diseases

  • 1203 Glomerular Diseases: Clinical, Outcomes, and Trials

Authors

  • Chen, Yijiang, Case Western Reserve University, Cleveland, Ohio, United States
  • Zee, Jarcy, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • Janowczyk, Andrew, Case Western Reserve University, Cleveland, Ohio, United States
  • Toro, Paula, Case Western Reserve University, Cleveland, Ohio, United States
  • Lafata, Kyle, Duke University School of Medicine, Durham, North Carolina, United States
  • Mariani, Laura H., University of Michigan Michigan Medicine, Ann Arbor, Michigan, United States
  • Holzman, Lawrence B., University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • Hodgin, Jeffrey B., University of Michigan Michigan Medicine, Ann Arbor, Michigan, United States
  • Madabhushi, Anant, Case Western Reserve University, Cleveland, Ohio, United States
  • Barisoni, Laura, Duke University School of Medicine, Durham, North Carolina, United States
Background

In CKD models, the association between peritubular capillary (PTC) density and outcome has been demonstrated, but little is known about PTC pathomic features in glomerular diseases. We explored whether computer extracted features quantifying PTC shape and density can predict risk of progression (40% eGFR decline or kidney failure) in proteinuric diseases.

Methods

N=358 PAS-stained whole slide images from the NEPTUNE database were included: 133 Focal Segmental Glomerulosclerosis (FSGS), 55 IgA Nephropathy (IgAN), 109 Minimal Change Disease (MCD), and 61 Membranous Nephropathy (MN). The presence of segmental sclerosis (SS) further subclassified IgAN and MN. The kidney cortex was manually annotated, and a pre-trained deep learning model generated PTC segmentations (Fig. 1). Average PTC flatness (the PTC major and minor axis ratio) and cortical density (PTC pixels/unit cortical area) were digitally measured. Unadjusted Cox proportional hazards models were used to associate normalized PTC flatness and density with outcome across and within each disease, within cases with SS (FSGS, IgAN+SS, MN+SS) and w/o SS (MCD, IgAN w/o SS, MN w/o SS), and within gender and age.

Results

PTC flatness ≥0.469 significantly associated with a hazard ratio (95% CI) of progression of 1.99 (1.19-3.33) compared with normalized PTC flatness <0.469 (p=0.0109) (Fig. 1). PTC cortical density ≥ 0.135 associated with a hazard ratio (95% CI) of progression of 0.689 (0.398 – 1.19) compared with normalized PTC cortical density <0.135 (p=0.16). PTC flatness significantly associated with outcome in FSGS (p=0.045), in the presence of SS (p=0.022), in males (p=0.0138), and adults (p=0.016), but not in children, females, or patients w/o SS.

Conclusion

PTC flatness was significantly associated with progression in glomerular diseases, particularly in patients with SS. This association is age and gender dependent.

Figure 1

Funding

  • Private Foundation Support