Fully automated contrast selection of joint bright- and black-blood late gadolinium enhancement imaging for robust myocardial scar assessment
Magnetic Resonance Imaging · 2024-06 · 109 · 256-263
DOI: 10.1016/j.mri.2024.03.035 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2024-06. Verfasst von Victor de Villedon de Naide und 13 weiteren Autor:innen. Beteiligte Einrichtung: Université de Bordeaux, INSERM, CRCTB, U 1045, IHU Liryc, F-33000 Bordeaux, France. Hauptthemen laut MEDLINE: Contrast Media, Gadolinium. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: European Research Council, French National Research Agency.
Abstract (Originalsprache)
PURPOSE: Joint bright- and black-blood MRI techniques provide improved scar localization and contrast. Black-blood contrast is obtained after the visual selection of an optimal inversion time (TI) which often results in uncertainties, inter- and intra-observer variability and increased workload. In this work, we propose an artificial intelligence-based algorithm to enable fully automated TI selection and simplify myocardial scar imaging. METHODS: The proposed algorithm first localizes the left ventricle using a U-Net architecture. The localized left cavity centroid is extracted and a squared region of interest ("focus box") is created around the resulting pixel. The focus box is then propagated on each image and the sum of the pixel intensity inside is computed. The smallest sum corresponds to the image with the lowest intensity signal within the blood pool and healthy myocardium, which will provide an ideal scar-to-blood contrast. The image's corresponding TI is considered optimal. The U-Net was trained to segment the epicardium in 177 patients with binary cross-entropy loss. The algorithm was validated retrospectively in 152 patients, and the agreement between the algorithm and two magnetic resonance (MR) operators' prediction of TI values was calculated using the Fleiss' kappa coefficient. Thirty focus box sizes, ranging from 2.3mm2 to 20.3cm2, were tested. Processing times were measured. RESULTS: The U-Net's Dice score was 93.0 ± 0.1%. The proposed algorithm extracted TI values in 2.7 ± 0.1 s per patient (vs. 16.0 ± 8.5 s for the operator). An agreement between the algorithm's prediction and the MR operators' prediction was found in 137/152 patients (κ= 0.89), for an optimal focus box of size 2.3cm2. CONCLUSION: The proposed fully-automated algorithm has potential of reducing uncertainties, variability, and workload inherent to manual approaches with promise for future clinical implementation for joint bright- and black-blood MRI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Université de Bordeaux, INSERM, CRCTB, U 1045, IHU Liryc, F-33000 Bordeaux, France.
- CHU de Bordeaux, Department of Cardiovascular Imaging, INSERM, U 1045, F-33000 Bordeaux, France.
- Université de Bordeaux, INSERM, CRCTB, U 1045, IHU Liryc, F-33000 Bordeaux, France; Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
- Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University Hospital of Tübingen, 72076 Tübingen, Germany.
- Université de Bordeaux, INSERM, CRCTB, U 1045, IHU Liryc, F-33000 Bordeaux, France; Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland;…
- Université de Bordeaux, INSERM, CRCTB, U 1045, IHU Liryc, F-33000 Bordeaux, France; CHU de Bordeaux, Department of Cardiovascular Imaging, INSERM, U 1045, F-33000 Bordeaux, France.
Förderung
- European Research Council
- French National Research Agency
Zitieren
APA
de Villedon de Naide, V., Maes, J. D., Villegas-Martinez, M., Ribal, I., Maillot, A., Ozenne, V., Montier, G., Boullé, T., Sridi, S., Gut, P., Küstner, T., Stuber, M., Cochet, H., & Bustin, A. (2024). Fully automated contrast selection of joint bright- and black-blood late gadolinium enhancement imaging for robust myocardial scar assessment. Magnetic Resonance Imaging, 109, 256-263. https://doi.org/10.1016/j.mri.2024.03.035
Vancouver
de Villedon de Naide V, Maes JD, Villegas-Martinez M, Ribal I, Maillot A, Ozenne V, et al. Fully automated contrast selection of joint bright- and black-blood late gadolinium enhancement imaging for robust myocardial scar assessment. Magnetic Resonance Imaging. 2024;109:256-263. doi:10.1016/j.mri.2024.03.035
BibTeX
@article{deVilledondeNaide2024,
author = {de Villedon de Naide, Victor and Maes, Jean-David and Villegas-Martinez, Manuel and Ribal, Indra and Maillot, Aurélien and Ozenne, Valéry and Montier, Géraldine and Boullé, Thibaut and Sridi, Soumaya and Gut, Pauline and Küstner, Thomas and Stuber, Matthias and Cochet, Hubert and Bustin, Aurélien},
title = {Fully automated contrast selection of joint bright- and black-blood late gadolinium enhancement imaging for robust myocardial scar assessment},
journal = {Magnetic Resonance Imaging},
year = {2024},
volume = {109},
pages = {256--263},
doi = {10.1016/j.mri.2024.03.035}
}
EUVIMED