Computational Pathology for Lupus Nephritis
Abstract
One-third of all adults with SLE present with LN at diagnosis, and up to two-thirds manifest kidney involvement during the course of the disease. Also, as many as 10% will require dialysis and/or kidney transplant. The ability to accurately identify LN patients at risk for progression could shift the current management paradigm from treatment to prevention. However, the prognostic significance of histopathologic classification of LN has been questioned due to poor reproducibility, thus casting doubts on the validity of its clinical application. This is a problem that cannot be understated, as treatment decisions are routinely made based on kidney biopsy findings. Thus, novel approaches are required to obtain continuous, quantitative data to improve accuracy, reproducibility, and prognostic utility. Digital pathology, a dynamic, image-based environment for the acquisition, management, and analysis of information generated from digitized images, is emerging in the setting of clinical trials and research in kidney disease but has yet to be applied to lupus nephritis biopsy interpretation. Our proposal seeks to address FY19 Lupus Research Program focus areas concerned with improving our understanding of lupus disease heterogeneity by applying digital pathology and computer-assisted image analysis approaches to kidney biopsies in addition to molecular profiling with transcriptomics. We hypothesize that a more quantitative and integrative system (i.e., pathology and molecular) for classifying patients will significantly improve our ability to predict outcome and response to treatment for patients with lupus nephritis. The proposed study will use the extensive resources of the Clinical Phenotyping Resource and Biobank Core (C-PROBE) of the University of Michigan George M. O’Brien Kidney Center, a longitudinal cohort study with more than 5 years of detailed clinical phenotyping. To achieve our goal of improving the utility of the kidney biopsy to predict disease progression in lupus nephritis, we propose to: Aim 1: Identify quantitative morphologic predictors of clinical outcomes and clinically meaningful clusters of patients with common morphologic profiles using the NEPTUNE Digital Pathology Scoring System (NDPSS). Aim 2: Identify morphometric predictors of clinical outcomes using computer-aided image analysis algorithms to measure selected pathologic features. Aim 3: Identify transcriptomic determinants that associate with disease morphologic and morphometric profiles. By using quantitative methods to capture the structural changes in the diseased kidney, and sophisticated statistical and bioinformatics approaches to correlate outcomes and gene expression profiles, we expect that this work will result in new clinically predictive categorization of lupus nephritis. The identification of important structural features will inform future studies that aim to detect these biopsy features through computer automation. It should provide a foundation that ultimately enhances our technical approach to lupus nephritis and advance our ability to specify subjects for clinical glomerular disease research.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 10, 2021
- Source ID
- W81XWH2010436
Entities
People
- Jeffrey Hodgin
Organizations
- United States Army
- University of Michigan