Ensemble deep learning to detect tumor buds and judge risk in colorectal cancer
Official title: An ensemble deep learning model for tumor bud detection and risk stratification in colorectal carcinoma.
Funded at Ohio State University · NIH-11369668 · Data updated 2026-11-12
A computer tool will help doctors identify tumor buds in colorectal cancer slides and use that information to better estimate a patient’s prognosis.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Ohio State University NIH-funded |
| Lab location | 1 site (Columbus, UNITED STATES) |
| Project start | July 1, 2023 |
| Project end | June 30, 2028 |
| Funding year | 2026 |
| Award (this year) | $492,694 |
| NIH project number | 5R01CA276301-04 |
| Project ID | NIH-11369668 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients with colorectal cancer whose tissue samples are used for pathology testing.
✕Less likely to help
Patients whose tissue samples are not used for prognosis or who do not have colorectal cancer may not benefit.
What this research studies
This project builds an AI-based image analysis system to standardize how tumor budding is identified on standard pathology slides. The goal is to make tumor buds easier to see, more reproducible, and linked to patient outcomes like survival and disease progression. By refining color normalization and bud detection, clinicians could gain a clearer, quicker read on how aggressive a patient’s cancer may be. The approach combines advanced image processing with statistical links to clinical results to support treatment planning.
Why it matters
Potential benefit: If successful, patients may receive more accurate prognosis and more tailored treatment decisions.
How similar studies have gone: Previous approaches show promise but lack standardized, reproducible bud identification across slides.
Where this research is happening
-
Ohio State University
Columbus, United States Active
Researchers
- Principal investigator: Chen, Wei — Ohio State University
- Study coordinator: Chen, Wei
Related research
Other NIH-funded projects on the same topics.
-
Using AI to Improve Colorectal Cancer Prognosis
This project is creating a smart computer system to find tiny groups of cancer cells in colon tissue, helping doctors better understand a patient's colorectal cancer.
-
Using deep learning to detect tumor buds in colorectal cancer.
This study is working on a smart computer program that helps doctors spot tiny signs of tumor growth in colorectal cancer, which can help predict how well patients might do, so they can make better treatment choices.
-
BVES protein in colorectal cancer: stopping tumor spread by stabilizing cell junctions
This grant explores how BVES, a protein at cell junctions, prevents colorectal cancer cells from becoming more aggressive and how restoring BVES could lead to new ways to stop tumor growth.
-
AI-powered miRNA test to tell oral cancer from benign leukoplakia without surgery
A noninvasive brush-based test using artificial intelligence analyzes tiny RNA patterns to distinguish oral cancer from benign oral lesions, helping people avoid delays.
-
extracellular RNA in colorectal cancer: how RNAs travel between cells and impact tumors
A broad research program at Vanderbilt is studying how extracellular RNAs travel between cancer cells in colorectal cancer and influence tumor growth and treatment response.
-
Understanding how RNA communication affects colorectal cancer
This study is looking at how tiny pieces of RNA found outside of cells might affect the growth and spread of colorectal cancer, with the hope that understanding this could lead to new treatments for patients.
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.