EUVIMEDEUVIMED entdecken
Crossref

Accuracy of a deep learning-based algorithm for the detection of thoracic aortic calcifications in chest computed tomography and cardiovascular surgery planning

Ruben Saffar iD, Jonathan I Sperl iD, Tim Berger iD, Jana Vojtekova, Maximilian Kreibich iD, Muhammad Taha Hagar iD, Jakob B Weiss iD, Martin Soschynski iD, Fabian Bamberg iD, Martin Czerny iD, Christopher Schuppert iD, Christopher L Schlett iD

European Journal of Cardio-Thoracic Surgery · 2024

DOI: 10.1093/ejcts/ezae219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Cardio-Thoracic Surgery, 2024. Verfasst von Ruben Saffar und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, …. Hauptthemen laut MEDLINE: Deep Learning, Aorta, Thoracic, Vascular Calcification, Tomography, X-Ray Computed. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES To assess the accuracy of a deep learning-based algorithm for fully automated detection of thoracic aortic calcifications in chest computed tomography (CT) with a focus on the aortic clamping zone. METHODS We retrospectively included 100 chest CT scans from 91 patients who were examined on second- or third-generation dual-source scanners. Subsamples comprised 47 scans with an electrocardiogram-gated aortic angiography and 53 unenhanced scans. A deep learning model performed aortic landmark detection and aorta segmentation to derive 8 vessel segments. Associated calcifications were detected and their volumes measured using a mean-based density thresholding. Algorithm parameters (calcium cluster size threshold, aortic mask dilatation) were varied to determine optimal performance for the upper ascending aorta that encompasses the aortic clamping zone. A binary visual rating served as a reference. Standard estimates of diagnostic accuracy and inter-rater agreement using Cohen’s Kappa were calculated. RESULTS Thoracic aortic calcifications were observed in 74% of patients with a prevalence of 27–70% by aorta segment. Using different parameter combinations, the algorithm provided binary ratings for all scans and segments. The best performing parameter combination for the presence of calcifications in the aortic clamping zone yielded a sensitivity of 93% and a specificity of 82%, with an area under the receiver operating characteristic curve of 0.874. Using these parameters, the inter-rater agreement ranged from κ 0.66 to 0.92 per segment. CONCLUSIONS Fully automated segmental detection of thoracic aortic calcifications in chest CT performs with high accuracy. This includes the critical preoperative assessment of the aortic clamping zone.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAorta, ThoracicVascular CalcificationTomography, X-Ray ComputedAortic DiseasesHumansRetrospective StudiesFemaleMaleAgedMiddle AgedAlgorithmsAged, 80 and over

Stichwörter der Autor:innen

Artificial intelligenceCardiothoracic imagingCerebral protectionChest CTThoracic aortaThoracic aortic calcifications

Autor:innen und Institutionen

  • Department of Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
  • Siemens Healthineers, Erlangen, Germany.
  • Department of Cardiovascular Surgery, University Heart Center Freiburg-Bad Krozingen, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
  • Siemens Healthineers, Bratislava, Slovakia.

ORCID-Profile: Ruben Saffar, Jonathan I Sperl, Tim Berger, Maximilian Kreibich, Muhammad Taha Hagar, Jakob B Weiss, Martin Soschynski, Fabian Bamberg, Martin Czerny, Christopher Schuppert, Christopher L Schlett

Zitieren

APA

Saffar, R., Sperl, J. I., Berger, T., Vojtekova, J., Kreibich, M., Hagar, M. T., Weiss, J. B., Soschynski, M., Bamberg, F., Czerny, M., Schuppert, C., & Schlett, C. L. (2024). Accuracy of a deep learning-based algorithm for the detection of thoracic aortic calcifications in chest computed tomography and cardiovascular surgery planning. European Journal of Cardio-Thoracic Surgery. https://doi.org/10.1093/ejcts/ezae219

Vancouver

Saffar R, Sperl JI, Berger T, Vojtekova J, Kreibich M, Hagar MT, et al. Accuracy of a deep learning-based algorithm for the detection of thoracic aortic calcifications in chest computed tomography and cardiovascular surgery planning. European Journal of Cardio-Thoracic Surgery. 2024. doi:10.1093/ejcts/ezae219

BibTeX
@article{Saffar2024,
  author = {Saffar, Ruben and Sperl, Jonathan I and Berger, Tim and Vojtekova, Jana and Kreibich, Maximilian and Hagar, Muhammad Taha and Weiss, Jakob B and Soschynski, Martin and Bamberg, Fabian and Czerny, Martin and Schuppert, Christopher and Schlett, Christopher L},
  title = {Accuracy of a deep learning-based algorithm for the detection of thoracic aortic calcifications in chest computed tomography and cardiovascular surgery planning},
  journal = {European Journal of Cardio-Thoracic Surgery},
  year = {2024},
  doi = {10.1093/ejcts/ezae219}
}
Kostenlos starten →