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
PMID: 39196450

Abstract

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 mm (IQR:591.1-964.8) in central, 201.3 mm (IQR:98.3-390.9) in segmental and 110.6 mm (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.

Authors

  • Florian Hagen
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str.3, 72076 Tübingen, Germany.
  • Linda Vorberg
    Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen-Nürnberg, Germany.
  • Florian Thamm
    Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
  • Hendrik Ditt
    Siemens Healthineers, Forchheim, Germany.
  • Andreas Maier
    Pattern Recognition Lab, University Erlangen-Nürnberg, Erlangen, Germany.
  • Jan Michael Brendel
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str. 3, 72076, Tübingen, Germany.
  • Patrick Ghibes
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls University, Hoppe-Seyler-Str. 3, 72076 Tuebingen, Germany (A.S.B., R.D., B.S., J.M., P.G., G.G., S.A., C.A.).
  • Malte Niklas Bongers
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str. 3, 72076, Tübingen, Germany.
  • Patrick Krumm
    Department of Radiology, Diagnostic and Interventional Radiology, University of Tübingen, 72076 Germany. Electronic address: patrick.krumm@med.uni-tuebingen.de.
  • Konstantin Nikolaou
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str.3, 72076 Tübingen, Germany.
  • Marius Horger
    Department of Diagnostic and Interventional Radiology, Eberhard-Karls-University, Hoppe-Seyler-Str.3, 72076 Tübingen, Germany. Electronic address: marius.horger@med.uni-tuebingen.de.

Keywords

External Resources

Popular Topics
Recent Journals