Improving radiation therapy by reducing CT image artifacts caused by metal implants
Official title: Constrained Disentanglement (CODE) Network for CT Metal Artifact Reduction in Radiation Therapy
Funded at Rensselaer Polytechnic Institute · NIH-10184493 · Data updated 2026-11-12
This study is working on improving radiation therapy for cancer patients with metal implants, like screws or plates, that can mess up the CT images used to plan their treatment, so they can get more accurate care and better results.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Rensselaer Polytechnic Institute NIH-funded |
| Lab location | 1 site (Troy, United States) |
| Project start | September 15, 2021 |
| Project end | September 14, 2025 |
| Funding year | 2021 |
| Award (this year) | $2,593,824 |
| NIH project number | 1R01EB031102-01 |
| Project ID | NIH-10184493 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are cancer patients who require radiation therapy and have metal implants.
✕Less likely to help
Patients without metal implants or those not undergoing radiation therapy may not benefit from this research.
What this research studies
This research focuses on enhancing radiation therapy for cancer patients who have metal implants that can distort CT images used for treatment planning. By developing advanced deep learning techniques, the project aims to eliminate these image artifacts, which currently affect about 15% of patients undergoing radiation therapy. The approach includes using adversarial learning to estimate missing data and applying constrained disentanglement networks to improve image reconstruction. The ultimate goal is to create more accurate treatment plans that lead to better patient outcomes.
Why it matters
Potential benefit: If successful, this research could significantly improve the accuracy of radiation therapy planning, leading to better treatment outcomes for cancer patients with metal implants.
How similar studies have gone: Previous research has shown promise in using deep learning techniques for image reconstruction, indicating potential success for this novel approach.
Where this research is happening
-
Rensselaer Polytechnic Institute
Troy, United States Active
Researchers
- Principal investigator: Wang, Ge — Rensselaer Polytechnic Institute
- Study coordinator: Wang, Ge
Related research
Other NIH-funded projects on the same topics.
-
Protecting small blood vessels from radiation by boosting mitochondrial health
It aims to prevent radiation-related damage to tiny blood vessels and reduce later thinking and memory problems in people who get radiation therapy by protecting cell mitochondria.
-
Proton SBRT for refractory ventricular tachycardia with real-time 3D/4D imaging
A patient-facing study exploring a proton-based, noninvasive radiation therapy to treat stubborn VT using advanced 3D and 4D imaging to target the heart safely.
-
Embedding symptom support in radiation therapy for prostate cancer
A multi-site study tests whether delivering mindfulness-based symptom support right inside radiation therapy is feasible and acceptable for men with prostate cancer.
-
Targeting SREBP2 to boost radiation therapy in HPV-negative head and neck cancer
This grant aims to see if blocking SREBP2 can make radiation therapy work better for people with HPV-negative Head and Neck Squamous Cell Carcinoma.
-
Genetic and Immune Factors in Squaring the Room: Sacituzumab plus Radiation for Bladder Cancer
A study aims to understand why combining sacituzumab with radiation helps some bladder cancer patients more than others, with the goal of making bladder-sparing therapy more effective.
-
CivaDerm: a new four-day skin cancer radiation bandage
A new four‑day radiation bandage for non-melanoma skin cancer aims to treat facial and other areas without multiple clinic visits or big scars.
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.