Abstract: SA-PO049
Neutrophil Extracellular Trap (NET) Quantification in Lupus Nephritis Potentiates NETs as a Prognostic Biomarker
Session Information
- Engineering-Based Approaches to Problems in Nephrology
November 09, 2019 | Location: Exhibit Hall, Walter E. Washington Convention Center
Abstract Time: 10:00 AM - 12:00 PM
Category: Bioengineering
- 300 Bioengineering
Authors
- Santo, Briana A., SUNY Buffalo, Buffalo, New York, United States
- Ginley, Brandon, SUNY Buffalo, Buffalo, New York, United States
- Lutnick, Brendon, SUNY Buffalo, Buffalo, New York, United States
- Jain, Sanjay, Washington University School of Medicine, St. Louis, Missouri, United States
- Segal, Brahm, Roswell Park Comprehensive Cancer Center, Buffalo, New York, United States
- Tomaszewski, John E., University at Buffalo, Buffalo, New York, United States
- Sarder, Pinaki, SUNY Buffalo, Buffalo, New York, United States
Background
Lupus Nephritis (LN) is a major risk factor for morbidity and mortality in Systemic Lupus Erythematosus (SLE), with 10% of patients developing ESRD. LN classification, which involves pathologist visual scoring of active and chronic lesions in renal biopsies, is limited due to lesion complexity. NETs have been implicated in SLE as immunogenic structures which contribute to lesion manifestation. Glomerular NET density may function as a predictive biomarker in LN, defining active to chronic lesion transition. We have developed a whole slide image (WSI) NET segmentation pipeline which enables computation of NET glomerular density in renal biopsies.
Methods
LN biopsies (n = 21) were labeled according to accepted immunofluorescence (IF) NET staining protocols, post-stained with H&E, and imaged. Our WSI NET segmentation pipeline, as well as a convolutional neural network for glomerular boundary segmentation, were applied. NET+ regions were identified and lesions were hand annotated in glomerulus images.
Results
A two-sampled t-test confirmed that glomerular NET density, for all active and chronic lesion affected glomeruli, is significantly different with p = 0.0002. Therefore, NET glomerular density co-occurrence with active lesion manifestation is statistically significant. NETs may serve as a prognostic biomarker in LN, and may functionally contribute to glomerular injury.
Conclusion
Our pipeline enables evaluation of glomerular NET density as a prognostic biomarker of LN progression, which could improve the clinical interpretation and treatment of LN in SLE. This pipeline may be used to compute NET density in other diseases featuring NET effected tissues, thus potentiating NET density as a universal prognostic biomarker. In addition, NET quantification will enable implementation of supervised classification for classifying NET structures in histology WSIs.
Funding
- NIDDK Support