Improving how we identify lupus kidney disease
Official title: Objective Classification of Lupus Nephritis
Funded at University of Houston · NIH-11125957 · Data updated 2026-11-12
This project uses computer technology to help doctors better identify and classify kidney disease in people with lupus.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Houston NIH-funded |
| Lab location | 1 site (Houston, United States) |
| Project start | August 20, 2023 |
| Project end | May 31, 2028 |
| Funding year | 2025 |
| Award (this year) | $600,680 |
| NIH project number | 5R01DK134055-03 |
| Project ID | NIH-11125957 on NIH RePORTER |
Who could benefit from this research
✓Could help
This work is relevant for adults and children who have been diagnosed with lupus kidney disease and have undergone a kidney biopsy.
✕Less likely to help
Patients who have not been diagnosed with lupus or do not have kidney involvement may not directly benefit from this specific research.
What this research studies
Lupus nephritis (LN) is a serious kidney complication for many people with lupus, and current methods for diagnosing it from kidney biopsies can sometimes vary between different doctors. This project aims to create advanced computer programs, known as deep learning, to analyze images from kidney biopsies. The goal is for these computer programs to classify the different types of lupus kidney disease as accurately and consistently as expert kidney doctors. Ultimately, this technology will also work to predict how a patient's kidney disease might progress based on their initial biopsy.
Why it matters
Potential benefit: If successful, this could lead to more accurate and consistent diagnoses of lupus kidney disease, potentially improving treatment plans and long-term kidney health for patients.
How similar studies have gone: While traditional methods for classifying lupus kidney disease have shown inconsistencies, this project explores a novel application of computer vision and deep learning to improve diagnostic accuracy.
Where this research is happening
-
University of Houston
Houston, United States Active
Researchers
- Principal investigator: Mohan, Chandra — University of Houston
- Study coordinator: Mohan, Chandra
Related research
Other NIH-funded projects on the same topics.
-
Glycoprotein urine markers that signal lupus nephritis treatment response
A novel test uses urine glycoprotein patterns to show how well lupus nephritis is responding to standard treatment.
-
PTPRS and lupus nephritis: a new target to reduce kidney damage in lupus
Aims to understand how PTPRS contributes to kidney inflammation and scarring in lupus nephritis and explore targeting it to help patients.
-
Sodium’s effect on kidney B cells in lupus kidney disease
This grant explores how high sodium in the kidneys affects B cells in lupus nephritis and whether blocking a key cellular pump could reduce kidney damage.
-
Oral CD11b Activator for Lupus Nephritis
A new oral CD11b activating drug is being explored to help people with lupus nephritis by targeting immune pathways that cause kidney inflammation.
-
Objective classification of lupus nephritis using computer vision
A new computer vision tool uses deep learning to classify lupus nephritis from kidney tissue images to help doctors predict outcomes for patients with lupus.
-
AI-powered look at lupus nephritis in humans and mice
Researchers will use artificial intelligence to compare kidney tissue from people with lupus nephritis to tissue from mouse models, aiming to understand why treatments work differently in humans.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.