Deep learning to estimate kidney scarring from ultrasound
Official title: Development and Validation of a Deep Learning system to estimate Interstitial Fibrosis from a kidney ultrasonography image
Funded at University of California, San Diego · NIH-11374958 · Data updated 2026-11-12
A new AI-based tool uses ultrasound images to estimate kidney scarring (interstitial fibrosis) without needing a biopsy, helping people with chronic kidney disease and their doctors track disease.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Diego NIH-funded |
| Lab location | 1 site (La Jolla, United States) |
| Project start | September 22, 2023 |
| Project end | July 31, 2028 |
| Funding year | 2026 |
| Award (this year) | $664,838 |
| NIH project number | 4R01DK138395-04 |
| Project ID | NIH-11374958 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults with chronic kidney disease who undergo kidney ultrasound and may have or be at risk for interstitial fibrosis.
✕Less likely to help
Patients without chronic kidney disease or without ultrasound imaging data may not benefit.
What this research studies
This project uses kidney ultrasound images and deep learning to predict how much scarring is present, comparing the AI estimates to biopsy results as the reference standard. It aims to develop and test the algorithm with data from patients and to validate it in different clinical settings. If successful, it could provide a non-invasive way to monitor fibrosis over time and guide treatment decisions for chronic kidney disease.
Why it matters
Potential benefit: If successful, patients could have a non-invasive way to monitor kidney scarring and adjust therapies sooner.
How similar studies have gone: Preliminary data suggest ultrasound + AI can reflect fibrosis, but external validation is needed.
Where this research is happening
-
University of California, San Diego
La Jolla, United States Active
Researchers
- Principal investigator: Athavale, Ambarish — University of California, San Diego
- Study coordinator: Athavale, Ambarish
Related research
Other NIH-funded projects on the same topics.
-
Using AI with kidney ultrasound to find scarring
This project is creating an artificial intelligence tool that uses routine kidney ultrasound pictures to find and measure scarring in the kidneys for people with chronic kidney disease.
-
Using AI to analyze kidney ultrasound images for fibrosis assessment
This study is testing a new AI tool that looks at kidney ultrasound images to help doctors find and understand kidney damage without needing to do a painful biopsy, making it easier for patients to keep track of their kidney health.
-
Understanding heart fibrosis with AI, MRI, and genomics
A doctor-scientist is using artificial intelligence, advanced heart MRI, and genetic data to learn how scar tissue forms in the aging heart and how to prevent it.
-
Predicting Post-Covid Lung Scarring with Easy-to-Understand Deep Learning and Key Biomarkers
Aims to use explainable artificial intelligence and biomarker data from multiple hospitals to predict which patients will develop long-term lung scarring after COVID-19.
-
Early prediction of lung scarring after COVID using explainable AI
This project uses explainable AI on CT scans and medical records to find people at risk of lung scarring after COVID-19.
-
Measuring liver scarring using MRI and advanced computer techniques
This study is looking for a gentle way to check for liver scarring in people with chronic liver disease using advanced MRI technology and smart computer programs, so you won’t need any painful biopsies.
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.