Developing a new AI framework for better cancer treatment imaging
Official title: A Fully Decentralized Federated Learning Framework for Automated Image Segmentation in Cancer Radiotherapy
Funded at Columbia University Health Sciences · NIH-10831775 · Data updated 2026-11-12
This study is working on a new way to use artificial intelligence to help doctors better identify organs in CT scans for patients with liver and head and neck cancers who are getting radiation therapy, all while keeping your personal information safe and secure.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Columbia University Health Sciences NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project start | September 15, 2023 |
| Project end | August 31, 2025 |
| Funding year | 2021 |
| Award (this year) | $442,664 |
| NIH project number | 7R21EB030209-02 |
| Project ID | NIH-10831775 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients diagnosed with liver or head and neck cancers who are undergoing radiation therapy.
✕Less likely to help
Patients with cancers not involving the liver or head and neck, or those not receiving radiation therapy, may not benefit from this research.
What this research studies
This research focuses on creating an innovative decentralized framework that utilizes artificial intelligence to improve the accuracy of image segmentation in cancer radiotherapy. By allowing different institutions to train AI models on their local data without sharing sensitive patient information, the approach aims to enhance the generalization capabilities of these models across diverse clinical environments. The framework will specifically target automated organ segmentation in CT images for patients with liver and head and neck cancers undergoing radiation therapy, addressing a critical challenge in accurately delineating organs at risk during treatment.
Why it matters
Potential benefit: If successful, this research could lead to more precise and effective radiation therapy for cancer patients, improving treatment outcomes.
How similar studies have gone: Other research has shown promise in using decentralized AI approaches for medical imaging, indicating potential success for this novel method.
Where this research is happening
-
Columbia University Health Sciences
New York, United States Active
Researchers
- Principal investigator: Yuan, Yading — Columbia University Health Sciences
- Study coordinator: Yuan, Yading
Related research
Other NIH-funded projects on the same topics.
-
AI-powered radiotherapy planning for cervical and head-and-neck cancer
A computer program helps plan radiation therapy for cervical and head-and-neck cancer patients to make treatments faster and more accurate.
-
AI-powered radiotherapy planning for cervical and head-and-neck cancer
A United Kingdom study is testing AI software that helps plan radiotherapy for cervical and head-and-neck cancer patients to save time and reduce the workload for clinicians in low-resource settings.
-
AI-powered radiotherapy planning for cervical and head-and-neck cancer
A UK research team is testing an AI-based software to automatically outline cancer areas and plan radiation beams to speed up treatment for cervical and head-and-neck cancers in LMICs.
-
AI-Powered Radiotherapy Planning for Cervical and Head & Neck Cancer
A new AI tool helps plan radiation therapy for cervical and head-and-neck cancers to save time and reduce the need for specialized staff.
-
AI-powered radiotherapy planning for cervical and head-and-neck cancer
A UK study from University College London uses AI to plan radiotherapy for cervical and head-and-neck cancers to save time and reduce the need for specialized staff, aiming to help patients in LMICs.
-
AI-powered radiotherapy planning for cervical and head & neck cancer
A non-randomized study will test an AI system that helps plan radiotherapy for cervical and head & neck cancers to save time and resources in LMICs.
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.