EUVIMEDEUVIMED entdecken
Open Access

AAPM CT metal artifact reduction grand challenge

Eri Haneda, Nils Peters, Jiayong Zhang, Grigorios Karageorgos, Wenjun Xia, Harald Paganetti, Ge Wang, Yi Guo, Jianhua Ma, Hyoung Suk Park, Kiwan Jeon, Fuxin Fan und 2 weitere

Medical Physics · 2025-10 · 52 (10)

DOI: 10.1002/mp.70050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 08.10.2025. Verfasst von Eri Haneda und 13 weiteren Autor:innen. Beteiligte Einrichtung: GE HealthCare Technology and Innovation Center, Niskayuna, New York, USA. Hauptthemen laut MEDLINE: Artifacts, Metals, Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIBIB NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Metal artifact reduction (MAR) is a long‐standing challenge in CT imaging. The presence of highly attenuating objects, such as dental fillings, hip prostheses, spinal screws/rods, and gold fiducial markers, can introduce severe streak artifacts in CT images, often reducing their diagnostic value. Existing CT MAR studies typically define their own test cases and evaluation metrics, making it difficult to objectively and comprehensively compare the performance of different MAR methods. There is a widespread need for a universal CT MAR image quality benchmark to evaluate the clinical impact of new MAR methods and compare them to state‐of‐the‐art techniques.

Purpose

The goal of the AAPM CT Metal Artifact Reduction (CT‐MAR) grand challenge was to create and distribute a clinically representative 2D MAR performance benchmark, and to invite participants to objectively compare the performance of their MAR methods based on this benchmark. A secondary goal was to facilitate MAR development by disseminating a MAR training database and tools. After completion of the grand challenge, the MAR benchmark and the MAR training database will remain publicly accessible for future MAR developments and benchmarking.

Methods

Grand challenge participants were invited to submit results for their MAR algorithm. The challenge organizers provided 14,000 CT training datasets generated using a hybrid data simulation framework that combined real patient images—including lung, abdomen, liver, head, and pelvis—with virtual metal objects. Each training dataset included five types of data: CT sinograms (uncorrected and metal‐free), CT reconstructed images (uncorrected and metal‐free), and metal masks. In the final evaluation phase, 29 clinical uncorrected datasets with metal were provided in both the sinogram and image domains for participants to process with their MAR algorithms. Their results were evaluated using eight clinically relevant image quality metrics. The final ranking was determined and compared to an established normalized metal artifact reduction (NMAR) reference method. Additionally, we conducted a survey to better understand the methodologies used by participants.

Results

A total of 106 teams registered for the challenge, with 26 teams completing all phases of the challenge. 92% of these—including all top ten teams—used a deep learning (DL) approach, employing a variety of network architectures such as UNet, ResNet, GAN, diffusion models, and transformers. Additionally, 22% of the teams—including the top three teams—utilized a combination of sinogram‐ and image‐domain approaches. The results showed a broad distribution of the scores. Overall, the competition was marked by diverse methods and a wide range of results, including some truly exceptional results. More than 70% of the teams achieved a better overall score than the popular baseline NMAR method.

Conclusions

The CT‐MAR grand challenge provided an opportunity to benchmark state‐of‐the‐art MAR algorithms. Our hybrid data generation framework was a powerful tool for simulating large‐scale realistic datasets for MAR algorithm development. A clinically relevant universal MAR benchmark offered an objective and meaningful way to compare different approaches. The training data and benchmark were published online to support future MAR development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ArtifactsMetalsTomography, X-Ray ComputedImage Processing, Computer-AssistedHumansAlgorithms

Stichwörter der Autor:innen

AAPM grand challengecomputed tomographydeep learningmetal artifact reduction

Substanzen

Metals

Autor:innen und Institutionen

  • GE HealthCare Technology and Innovation Center, Niskayuna, New York, USA.
  • Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA.
  • Department of Radiation Oncology, University of Washington & Fred Hutch Cancer Center, Seattle, Washington, USA.
  • Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, New York, USA.
  • School of Biomedical Engineering, Southern Medical University, Guangdong, China.
  • School of Life Science and Technology, Xi'an Jiaotong University, Shaanxi, China.

Förderung

  • NIBIB NIH HHS

Zitieren

APA

Haneda, E., Peters, N., Zhang, J., Karageorgos, G., Xia, W., Paganetti, H., Wang, G., Guo, Y., Ma, J., Park, H. S., Jeon, K., Fan, F., Thies, M., & De Man, B. (2025). AAPM CT metal artifact reduction grand challenge. Medical Physics, 52(10). https://doi.org/10.1002/mp.70050

Vancouver

Haneda E, Peters N, Zhang J, Karageorgos G, Xia W, Paganetti H, et al. AAPM CT metal artifact reduction grand challenge. Medical Physics. 2025;52(10). doi:10.1002/mp.70050

BibTeX
@article{Haneda2025,
  author = {Haneda, Eri and Peters, Nils and Zhang, Jiayong and Karageorgos, Grigorios and Xia, Wenjun and Paganetti, Harald and Wang, Ge and Guo, Yi and Ma, Jianhua and Park, Hyoung Suk and Jeon, Kiwan and Fan, Fuxin and Thies, Mareike and De Man, Bruno},
  title = {AAPM CT metal artifact reduction grand challenge},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {10},
  doi = {10.1002/mp.70050}
}
Kostenlos starten →