EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Deep Learning for Coronary Stenosis Detection in Heavily Calcified Plaques at Coronary CT Angiography: A Stepwise, Multicenter Study

Rui Wang iD, Siwen Wang, LiBo Zhang, U Joseph Schoepf iD, Fandong Zhang iD, Wei Chen iD, Zhen Zhou iD, Zhe Fang iD, Bin Hu, Yizhou Yu iD, Jiayin Zhang iD, Ximing Wang iD und 2 weitere

Radiology: Artificial Intelligence · 01.01.2026 · 8 (1)

DOI: 10.1148/ryai.250109 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Radiology: Artificial Intelligence, erschienen am 01.01.2026. Verfasst von Rui Wang und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, No. 2 Anzhen Rd, Chaoyang District, Beijing, PR China 100029. Hauptthemen laut MEDLINE: Computed Tomography Angiography, Coronary Angiography, Coronary Stenosis, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Key R&D Program of China, Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proposed deep learning model automatically quantified coronary luminal stenosis in patients with heavily calcified plaques at coronary CT angiography and improved radiologists’ diagnostic performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computed Tomography AngiographyCoronary AngiographyCoronary StenosisDeep LearningPlaque, AtheroscleroticRadiographic Image Interpretation, Computer-AssistedVascular CalcificationAgedFemaleHumansMaleMiddle AgedChinaRetrospective Studies

Stichwörter der Autor:innen

ArteriosclerosisCT AngiographyCalcificationsCalculiCardiacDiagnosisHeartQuantification

Autor:innen und Institutionen

  • Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, No. 2 Anzhen Rd, Chaoyang District, Beijing, PR China 100029.
  • Deepwise Artificial Intelligence (AI) Lab, Deepwise Inc, Beijing, PR China.
  • Department of Radiology, General Hospital of Northern Theater Command, Liaoning, PR China.
  • Division of Cardiovascular Imaging, Department of Radiology and Radiological Science and Division of Cardiology, Department of Medicine, Medical University of South Carolina, Charleston, SC.
  • Department of Cardiology, Beijing Daxing District Hospital of Integrated Chinese and Western Medicine, Beijing, PR China.
  • Department of Cardiology, Beijing Anzhen Hospital, Capital Medical University, Beijing, PR China.

ORCID-Profile: Rui Wang, U Joseph Schoepf, Fandong Zhang, Wei Chen, Zhen Zhou, Zhe Fang, Yizhou Yu, Jiayin Zhang, Ximing Wang, Longjiang Zhang, Lei Xu

Förderung

  • National Key R&D Program of China
  • Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Beijing Municipal Administration of Hospitals Incubating Program

Zitieren

APA

Wang, R., Wang, S., Zhang, L., Schoepf, U. J., Zhang, F., Chen, W., Zhou, Z., Fang, Z., Hu, B., Yu, Y., Zhang, J., Wang, X., Zhang, L., & Xu, L. (2026). Deep Learning for Coronary Stenosis Detection in Heavily Calcified Plaques at Coronary CT Angiography: A Stepwise, Multicenter Study. Radiology: Artificial Intelligence, 8(1). https://doi.org/10.1148/ryai.250109

Vancouver

Wang R, Wang S, Zhang L, Schoepf UJ, Zhang F, Chen W, et al. Deep Learning for Coronary Stenosis Detection in Heavily Calcified Plaques at Coronary CT Angiography: A Stepwise, Multicenter Study. Radiology: Artificial Intelligence. 2026;8(1). doi:10.1148/ryai.250109

BibTeX
@article{Wang2026,
  author = {Wang, Rui and Wang, Siwen and Zhang, LiBo and Schoepf, U Joseph and Zhang, Fandong and Chen, Wei and Zhou, Zhen and Fang, Zhe and Hu, Bin and Yu, Yizhou and Zhang, Jiayin and Wang, Ximing and Zhang, Longjiang and Xu, Lei},
  title = {Deep Learning for Coronary Stenosis Detection in Heavily Calcified Plaques at Coronary CT Angiography: A Stepwise, Multicenter Study},
  journal = {Radiology: Artificial Intelligence},
  year = {2026},
  volume = {8},
  number = {1},
  doi = {10.1148/ryai.250109}
}
Kostenlos starten →