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

ASN / Education & Meetings / Kidney Week /

Please note that you are viewing an archived section from 2023 and some content may be unavailable. To unlock all content for 2023, please visit the archives.

Abstract: TH-PO806

Clinical Relevance of Computationally Derived Spatial Relationships Between Interstitial Fibrosis and Tubular Atrophy (IFTA) and Peritubular Capillary Features 

Session Information

Category: Pathology and Lab Medicine

  • 1800 Pathology and Lab Medicine

Authors

  • Chen, Yijiang, Case Western Reserve University Department of Biomedical Engineering, Cleveland, Ohio, United States
  • Wang, Bangchen, Duke University Department of Pathology, Durham, North Carolina, United States
  • Demeke, Dawit S., University of Michigan Department of Pathology, Ann Arbor, Michigan, United States
  • Fan, Fan, Case Western Reserve University Department of Biomedical Engineering, Cleveland, Ohio, United States
  • Berthier, Celine C., University of Michigan Department of Internal Medicine, Ann Arbor, Michigan, United States
  • Hodgin, Jeffrey B., University of Michigan Department of Pathology, Ann Arbor, Michigan, United States
  • Janowczyk, Andrew, Emory University, Atlanta, United States
  • Barisoni, Laura, Duke University Department of Pathology, Durham, North Carolina, United States
  • Madabhushi, Anant, Emory University, Atlanta, Georgia, United States
Background

The status of the tubulointerstitium and microvasculature is clinically relevant in glomerular diseases. While extent of interstitial fibrosis and tubular atrophy (IFTA) and peritubular capillaries (PTC) shape are independently associated with glomerular disease progression, the prognostic relevance of PTC shape features stratified by IFTA remains unknown.

Methods

N = 344 PAS-stained whole slide images (114 MCD/MCD-like, 132 FSGS, 61 MN and 37 IgAN) from the NEPTUNE/CureGN datasets were manually segmented for cortex and IFTA. A deep learning model was applied for PTC segmentation. The WSIs were split into training (St) and testing (Sv) datasets (1:1). 100 pathomic features quantifying cortical PTC shape were extracted from PTCs in IFTA and non-IFTA regions. Clinical outcome was defined as 40% eGFR decline or kidney failure. Lasso regression models were constructed on St, identifying top PTC shape features in IFTA and non-IFTA regions. The same features and model parameters were applied on Sv for independent validation. A prognostic model built with IFTA cortical density alone was created for comparison. Cox proportional hazards models and KM curves were used to evaluate prognostic relevance of the models.

Results

PTC shape features in IFTA regions were prognostic of disease progression, while PTC shape features in non-IFTA regions were not. The association between cortical IFTA density and disease progress was included for comparison (Figure 1). The top PTC shape features selected from IFTA regions are listed in Table 1.

Conclusion

IFTA density and PTC shape characteristics in IFTA regions are biomarkers of disease progression in patients with glomerular diseases. These results suggest that PTCs within IFTA regions tend to undergo morphologic changes, and these morphologic features are associated with kidney failure.

Funding

  • NIDDK Support