Clinical relevance of computationally derived tubular features and their spatial relationships with the interstitial microenvironment in minimal change disease/focal segmental glomerulosclerosis

Fan Fan¹, Qian Liu², Jarcy Zee³, Takaya Ozeki⁴, Dawit Demeke⁵, Yingbao Yang⁵, Markus Bitzer⁴, Christopher L O'Connor⁴, Alton B Farris⁶, Bangchen Wang⁷, Manav Shah¹, Jackson Jacobs¹, Laura Mariani⁴, Kyle J Lafata⁸, Jeremy Rubin⁹, Yijiang Chen¹⁰, Lawrence B Holzman¹¹, Jeffrey B Hodgin⁵, Anant Madabhushi¹², Laura Barisoni¹³, Andrew Janowczyk¹⁴

Affiliations

¹ Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA.
² Children's Hospital of Philadelphia Research Institute, Philadelphia, Pennsylvania, USA.
³ Children's Hospital of Philadelphia Research Institute, Philadelphia, Pennsylvania, USA; Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA.
⁴ Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan, USA.
⁵ Department of Pathology, University of Michigan, Ann Arbor, Michigan, USA.
⁶ Department of Pathology and Laboratory Medicine, Emory University, Atlanta, Georgia, USA.
⁷ Division of AI and Computational Pathology, Department of Pathology, Duke University, Durham, North Carolina, USA.
⁸ Department of Radiation Oncology, Duke University, Durham, North Carolina, USA.
⁹ Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA.
¹⁰ Department of Radiation Oncology, School of Medicine, Stanford University, Stanford, California, USA.
¹¹ Division of Nephrology and Hypertension, Department of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
¹² Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA; Atlanta Veterans Administration Medical Center, Atlanta, Georgia, USA.
¹³ Division of AI and Computational Pathology, Department of Pathology, Duke University, Durham, North Carolina, USA; Division of Nephrology, Department of Medicine, Duke University, Durham, North Carolina, USA. Electronic address: laura.barisoni@duke.edu.
¹⁴ Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA; Division of Precision Oncology, Department of Oncology, University Hospital of Geneva, Geneva, Switzerland; Division of Clinical Pathology, Department of Diagnostics, University Hospital of Geneva, Geneva, Switzerland. Electronic address: andrew.r.janowczyk@emory.edu.

PMID: 40409668
PMCID: PMC12302419 (available on 2026-05-21)
DOI: 10.1016/j.kint.2025.04.026

Observational Study

Clinical relevance of computationally derived tubular features and their spatial relationships with the interstitial microenvironment in minimal change disease/focal segmental glomerulosclerosis

Fan Fan et al. Kidney Int. 2025 Aug.

. 2025 Aug;108(2):293-309.

doi: 10.1016/j.kint.2025.04.026. Epub 2025 May 21.

Authors

Affiliations

¹ Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA.
² Children's Hospital of Philadelphia Research Institute, Philadelphia, Pennsylvania, USA.
³ Children's Hospital of Philadelphia Research Institute, Philadelphia, Pennsylvania, USA; Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA.
⁴ Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan, USA.
⁵ Department of Pathology, University of Michigan, Ann Arbor, Michigan, USA.
⁶ Department of Pathology and Laboratory Medicine, Emory University, Atlanta, Georgia, USA.
⁷ Division of AI and Computational Pathology, Department of Pathology, Duke University, Durham, North Carolina, USA.
⁸ Department of Radiation Oncology, Duke University, Durham, North Carolina, USA.
⁹ Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, USA.
¹⁰ Department of Radiation Oncology, School of Medicine, Stanford University, Stanford, California, USA.
¹¹ Division of Nephrology and Hypertension, Department of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
¹² Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA; Atlanta Veterans Administration Medical Center, Atlanta, Georgia, USA.
¹³ Division of AI and Computational Pathology, Department of Pathology, Duke University, Durham, North Carolina, USA; Division of Nephrology, Department of Medicine, Duke University, Durham, North Carolina, USA. Electronic address: laura.barisoni@duke.edu.
¹⁴ Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA; Division of Precision Oncology, Department of Oncology, University Hospital of Geneva, Geneva, Switzerland; Division of Clinical Pathology, Department of Diagnostics, University Hospital of Geneva, Geneva, Switzerland. Electronic address: andrew.r.janowczyk@emory.edu.

PMID: 40409668
PMCID: PMC12302419 (available on 2026-05-21)
DOI: 10.1016/j.kint.2025.04.026

Abstract

Background: Visual scoring of tubular damage has limitations in capturing the full spectrum of structural changes and prognostic potential. Here, we investigated if computationally quantified tubular features can enhance prognostication and reveal spatial relationships with interstitial fibrosis.

Methods: Deep-learning and image-analysis approaches were employed on 254/266 Periodic acid Schiff-stained whole slide image (WSI) kidney biopsies from participants in the NEPTUNE/CureGN prospective observational cohort studies (135/153 with focal segmental glomerulosclerosis (FSGS) and 119/113 with minimal change disease (MCD)) to segment cortex, tubular lumen (TL), epithelium (TE), nuclei (TN), and basement membrane (TBM). One hundred four pathomic features were extracted from these segmented tubular substructures and aggregated at the patient level using summary statistics. In the NEPTUNE dataset, tubular features were quantified at the WSI level and in manually segmented regions of mature interstitial fibrosis and tubular atrophy (IFTA), pre-IFTA, and non-IFTA. Minimum Redundancy Maximum Relevance was then used to select features most associated with disease progression and proteinuria remission. Ridge-penalized Cox models evaluated their predictive discrimination compared to clinical/demographic data and visual-assessment. Models were evaluated in the CureGN dataset.

Results: Nine features were predictive of disease progression and/or proteinuria remission. Models with tubular features had high prognostic accuracy in both NEPTUNE and CureGN, and higher prognostic accuracy for both outcomes compared to conventional parameters alone in NEPTUNE. TBM thickness/area and TE flattening and/or reduced cell size progressively increased from non- to pre- and mature IFTA.

Conclusions: Previously underrecognized computationally derived and quantifiable tubular characteristics may contribute to improving prognostic accuracy and risk stratification in patients with FSGS/MCD. Future studies are needed to test their generalizability across different diseases and populations before they can be deployed in clinical practice.

Keywords: computational pathology; focal segmental glomerulosclerosis; hand-crafted features; image-based biomarkers; machine learning; pathomics.

PubMed Disclaimer

Update of

Clinical Relevance of Computationally Derived Tubular Features: Spatial Relationships and the Development of Tubulointerstitial Scarring in MCD/FSGS.
Fan F, Liu Q, Zee J, Ozeki T, Demeke D, Yang Y, Farris AB, Wang B, Shah M, Jacobs J, Mariani L, Lafata K, Rubin J, Chen Y, Holzman L, Hodgin JB, Madabhushi A, Barisoni L, Janowczyk A. Fan F, et al. medRxiv [Preprint]. 2024 Jul 21:2024.07.19.24310619. doi: 10.1101/2024.07.19.24310619. medRxiv. 2024. Update in: Kidney Int. 2025 Aug;108(2):293-309. doi: 10.1016/j.kint.2025.04.026. PMID: 39072032 Free PMC article. Updated. Preprint.

References

1. Kopp JB, Anders HJ, Susztak K, et al. Podocytopathies. Nat Rev Dis Primer. 2020;6(1):1–24. doi: 10.1038/s41572-020-0196-7 - DOI - PMC - PubMed
1. Barisoni L, Schnaper H, Kopp J. A Proposed Taxonomy for the Podocytopathies: A Reassessment of the Primary Nephrotic Diseases. Clin J Am Soc Nephrol CJASN. 2007;2:529–542. doi: 10.2215/CJN.04121206 - DOI - PubMed
1. Waldman M, Crew RJ, Valeri A, et al. Adult minimal-change disease: clinical characteristics, treatment, and outcomes. Clin J Am Soc Nephrol CJASN. 2007;2(3):445–453.doi: 10.2215/CJN.03531006 - DOI - PubMed
1. Bose B, Cattran D, Toronto Glomerulonephritis Registry. Glomerular diseases: FSGS. Clin J Am Soc Nephrol CJASN. 2014;9(3):626–632. doi: 10.2215/CJN.05810513 - DOI - PMC - PubMed
1. Bazzi C. Prediction of ESRD and long-term remission by proteinuric markers in Primary Focal Segmental Glomerulosclerosis with Nephrotic Syndrome : a review. Nephrol Ren Dis. 2016;1(2). doi: 10.15761/NRD.1000108 - DOI

Publication types

Actions

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources
- Elsevier Science

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Clinical relevance of computationally derived tubular features and their spatial relationships with the interstitial microenvironment in minimal change disease/focal segmental glomerulosclerosis

Affiliations

Clinical relevance of computationally derived tubular features and their spatial relationships with the interstitial microenvironment in minimal change disease/focal segmental glomerulosclerosis

Authors

Affiliations

Abstract

Update of

References

Publication types

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources