EUVIMEDEUVIMED entdecken
Vergleichsstudie

Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm – a single centre retrospective study

Florian Hagen, Linda Vorberg, Florian Thamm, Hendrik Ditt, Andreas Maier, Jan Michael Brendel, Patrick Ghibes, Malte Niklas Bongers, Patrick Krumm, Konstantin Nikolaou, Marius Horger

The International Journal of Cardiovascular Imaging · 28.08.2024 · 40 (11) · 2293-2304

DOI: 10.1007/s10554-024-03222-8 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift The International Journal of Cardiovascular Imaging, erschienen am 28.08.2024. Verfasst von Florian Hagen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str. 3, 72076, Tübingen, Germany. Hauptthemen laut MEDLINE: Pulmonary Embolism, Predictive Value of Tests, Computed Tomography Angiography, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To preliminarily verify the feasibility of a deep-learning (DL) artificial intelligence (AI) model to localize pulmonary embolism (PE) on unenhanced chest-CT by comparison with pulmonary artery (PA) CT angiography (CTA). In a monocentric study, we retrospectively reviewed 99 oncological patients (median age in years: 64 (range: 28-92 years); percentage of female: 39.4%) who received unenhanced and contrast-enhanced chest CT examinations in one session between January 2020 and October 2022 and who were diagnosed incidentally with PE. Findings in the unenhanced images were correlated with the contrast-enhanced images, which were considered the gold standard for central, segmental and subsegmental PE. The new algorithm was trained and tested based on the 99 unenhanced chest-CT image data sets. Based on them, candidate boxes, which were output by the model, were post-processed by evaluating whether the predicted box intersects with the patient's lung segmentation at any position. The AI-based algorithm proved to have an overall sensitivity of 54.5% for central, of 81.9% for segmental and 80.0% for subsegmental PE if taking n = 20 candidate boxes into account. Depending on the localization of the pulmonary embolism, the detection rate for only one box was: 18.1% central, 34.7% segmental and 0.0% subsegmental. The median volume of the clots differed significantly between the three subgroups and was 846.5 mm3 (IQR:591.1-964.8) in central, 201.3 mm3 (IQR:98.3-390.9) in segmental and 110.6 mm3 (IQR:94.3-128.0) in subsegmental PA (p < 0.05). The new algorithm proved to have high sensitivity in detecting PE in particular in segmental/subsegmental localization and may guide to decide whether a second contrast enhanced CT is necessary.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pulmonary EmbolismPredictive Value of TestsComputed Tomography AngiographyRadiographic Image Interpretation, Computer-AssistedDeep LearningFeasibility StudiesHumansFemaleRetrospective StudiesAgedMaleMiddle AgedAged, 80 and overAdultReproducibility of ResultsPulmonary ArteryAlgorithmsIncidental Findings

Stichwörter der Autor:innen

Artificial intelligencePhoton counting CTPulmonary embolismUnenhanced chest CT

Autor:innen und Institutionen

  • Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str. 3, 72076, Tübingen, Germany.
  • Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen-Nürnberg, Germany.
  • Computed Tomography, Siemens Healthineers AG, Forchheim, Germany.
  • Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str. 3, 72076, Tübingen, Germany. marius.horger@med.uni-tuebingen.de.

Zitieren

APA

Hagen, F., Vorberg, L., Thamm, F., Ditt, H., Maier, A., Brendel, J. M., Ghibes, P., Bongers, M. N., Krumm, P., Nikolaou, K., & Horger, M. (2024). Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm – a single centre retrospective study. The International Journal of Cardiovascular Imaging. https://doi.org/10.1007/s10554-024-03222-8

Vancouver

Hagen F, Vorberg L, Thamm F, Ditt H, Maier A, Brendel JM, et al. Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm – a single centre retrospective study. The International Journal of Cardiovascular Imaging. 2024. doi:10.1007/s10554-024-03222-8

BibTeX
@article{Hagen2024,
  author = {Hagen, Florian and Vorberg, Linda and Thamm, Florian and Ditt, Hendrik and Maier, Andreas and Brendel, Jan Michael and Ghibes, Patrick and Bongers, Malte Niklas and Krumm, Patrick and Nikolaou, Konstantin and Horger, Marius},
  title = {Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm – a single centre retrospective study},
  journal = {The International Journal of Cardiovascular Imaging},
  year = {2024},
  doi = {10.1007/s10554-024-03222-8}
}
Kostenlos starten →