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 Twitter

Kidney Week

Abstract: TH-PO569

Computationally Derived "Functional" Tubule Density Is Prognostic of Outcome in Glomerular Diseases

Session Information

  • Pathology and Lab Medicine
    November 03, 2022 | Location: Exhibit Hall, Orange County Convention Center‚ West Building
    Abstract Time: 10:00 AM - 12:00 PM

Category: Glomerular Diseases

  • 1303 Glomerular Diseases: Clinical‚ Outcomes‚ and Trials

Authors

  • Fan, Fan, Case Western Reserve University Department of Biomedical Engineering, Cleveland, Ohio, United States
  • Wang, Bangchen, Duke University Department of Pathology, Durham, North Carolina, United States
  • Ozeki, Takaya, University of Michigan Department of Internal Medicine, Ann Arbor, Michigan, United States
  • Rubin, Jeremy, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • Chen, Yijiang, Case Western Reserve University Department of Biomedical Engineering, Cleveland, Ohio, United States
  • Hodgin, Jeffrey B., University of Michigan Department of Internal Medicine, Ann Arbor, Michigan, United States
  • Mariani, Laura H., University of Michigan Department of Internal Medicine, Ann Arbor, Michigan, United States
  • Holzman, Lawrence B., University of Pennsylvania Department of Medicine, Philadelphia, Pennsylvania, United States
  • Lafata, Kyle, Duke University Department of Radiation Oncology, Durham, North Carolina, United States
  • Madabhushi, Anant, Case Western Reserve University Department of Biomedical Engineering, Cleveland, Ohio, United States
  • Barisoni, Laura, Duke University Department of Pathology, Durham, North Carolina, United States
  • Zee, Jarcy, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • Janowczyk, Andrew, Case Western Reserve University Department of Biomedical Engineering, Cleveland, Ohio, United States
Background

While tubular atrophy (TA) is associated with a decrease of functional tubules (FT) and disease progression in kidney diseases, reproducible visual quantification of TA remains challenging. In our study, the value of computationally derived FT density (FT pixel area per cortical pixel area) was explored.

Methods

N=239 PAS-stained whole slide images from the NEPTUNE digital pathology repository were studied (135 FSGS, 51 MCD, and 53 MCD-like). The kidney cortex was manually annotated by pathologists and a validated deep learning (DL) model was used to segment cortical FTs (Fig.1). Cortical FT density was subsequently computed for each biopsy. Spearman’s correlation coefficient was used to measure the correlation between the FT density and visually scored TA. Kaplan-Meier curves were estimated, and a log-rank test was used to assess the association between FT density measured in quartiles and the composite disease progression outcome of time from biopsy to 40% eGFR decline or kidney failure.

Results

The FT density decreased from MCD to MCD-like and to FSGS biopsies (Fig.2). There was a strong negative association between FT density and TA (ρ=-0.75, p<0.001). There was a significant difference in disease progression for subjects within different quartiles of FT; those with FT density < 0.39 having worse outcomes. Each 0.1 increase in FT density (< 0.49) was associated with 46% decreased hazards of disease progression, but when FT density was > 0.49, the association was not significant.

Conclusion

DL-derived FT density is a robust and feasible approach to measuring the status of the tubulointerstitium and a biomarker of clinical outcome, with potential predictive value in assessing the risk of progression.

DL model tubule segmentation results

a: FT density for three different cohorts, b: Kaplan-Meier curves of FT density association with outcome

Funding

  • NIDDK Support