EUVIMEDEUVIMED entdecken
Crossref

Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images

Federico N Guilenea iD, Mariano E Casciaro iD, Gilles Soulat iD, Elie Mousseaux iD, Damian Craiem iD

Biomedical Physics & Engineering Express · 2024

DOI: 10.1088/2057-1976/ad2ff2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, 2024. Verfasst von Federico N Guilenea und 4 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Medicina Traslacional, Trasplante y Bioingeniería (IMeTTyB), Universidad Favaloro-CONICET, Solís 453, Buenos Aires CP 1078, Argentina. Hauptthemen laut MEDLINE: Aorta, Thoracic, Deep Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: Fondo para la Investigación Científica y Tecnológica, Consejo Nacional de Investigaciones Científicas y Técnicas.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Thoracic aorta calcium (TAC) can be assessed from cardiac computed tomography (CT) studies to improve cardiovascular risk prediction. The aim of this study was to develop a fully automatic system to detect TAC and to evaluate its performance for classifying the patients into four TAC risk categories. The method started by segmenting the thoracic aorta, combining three UNets trained with axial, sagittal and coronal CT images. Afterwards, the surrounding lesion candidates were classified using three combined convolutional neural networks (CNNs) trained with orthogonal patches. Image datasets included 1190 non-enhanced ECG-gated cardiac CT studies from a cohort of cardiovascular patients (age 57 ± 9 years, 80% men, 65% TAC > 0). In the test set (N = 119), the combination of UNets was able to successfully segment the thoracic aorta with a mean volume difference of 0.3 ± 11.7 ml (

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Aorta, ThoracicDeep LearningMaleHumansMiddle AgedAgedFemaleCalciumTomography, X-Ray ComputedElectrocardiography

Stichwörter der Autor:innen

UNetaorta segmentationartery calciumconvolutional neuronal networkthoracic aorta calcification

Substanzen

Calcium

Autor:innen und Institutionen

  • Instituto de Medicina Traslacional, Trasplante y Bioingeniería (IMeTTyB), Universidad Favaloro-CONICET, Solís 453, Buenos Aires CP 1078, Argentina.
  • Cardiovascular Imaging Unit, Hôpital Européen Georges Pompidou, INSERM U970, 75015 Paris, France.

ORCID-Profile: Federico N Guilenea, Mariano E Casciaro, Gilles Soulat, Elie Mousseaux, Damian Craiem

Förderung

  • Fondo para la Investigación Científica y Tecnológica
  • Consejo Nacional de Investigaciones Científicas y Técnicas

Zitieren

APA

Guilenea, F. N., Casciaro, M. E., Soulat, G., Mousseaux, E., & Craiem, D. (2024). Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ad2ff2

Vancouver

Guilenea FN, Casciaro ME, Soulat G, Mousseaux E, Craiem D. Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images. Biomedical Physics & Engineering Express. 2024. doi:10.1088/2057-1976/ad2ff2

BibTeX
@article{Guilenea2024,
  author = {Guilenea, Federico N and Casciaro, Mariano E and Soulat, Gilles and Mousseaux, Elie and Craiem, Damian},
  title = {Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images},
  journal = {Biomedical Physics & Engineering Express},
  year = {2024},
  doi = {10.1088/2057-1976/ad2ff2}
}
Kostenlos starten →