Validation of deep-learning image reconstruction for coronary computed tomography angiography: Impact on noise, image quality and diagnostic accuracy.

Aged Artifacts Computed Tomography Angiography Coronary Angiography Coronary Artery Disease / diagnostic imaging Coronary Vessels / diagnostic imaging Deep Learning Diagnosis, Computer-Assisted Female Humans Male Middle Aged Predictive Value of Tests Radiographic Image Interpretation, Computer-Assisted Registries Reproducibility of Results Retrospective Studies
ASiR-V Adaptive statistical iterative reconstruction-veo Coronary CT angiography DLIR Deep-learning image reconstruction Diagnostic accuracy Image quality

Journal

Journal of cardiovascular computed tomography
ISSN: 1876-861X
Titre abrégé: J Cardiovasc Comput Tomogr
Pays: United States
ID NLM: 101308347

Informations de publication

Date de publication:
Historique:
received: 23 08 2019
revised: 29 10 2019
accepted: 08 01 2020
pubmed: 25 1 2020
medline: 7 10 2020
entrez: 25 1 2020
Statut: ppublish

Résumé

Advances in image reconstruction are necessary to decrease radiation exposure from coronary CT angiography (CCTA) further, but iterative reconstruction has been shown to degrade image quality at high levels. Deep-learning image reconstruction (DLIR) offers unique opportunities to overcome these limitations. The present study compared the impact of DLIR and adaptive statistical iterative reconstruction-Veo (ASiR-V) on quantitative and qualitative image parameters and the diagnostic accuracy of CCTA using invasive coronary angiography (ICA) as the standard of reference. This retrospective study includes 43 patients who underwent clinically indicated CCTA and ICA. Datasets were reconstructed with ASiR-V 70% (using standard [SD] and high-definition [HD] kernels) and with DLIR at different levels (i.e., medium [M] and high [H]). Image noise, image quality, and coronary luminal narrowing were evaluated by three blinded readers. Diagnostic accuracy was compared against ICA. Noise did not significantly differ between ASiR-V SD and DLIR-M (37 vs. 37 HU, p = 1.000), but was significantly lower in DLIR-H (30 HU, p < 0.001) and higher in ASiR-V HD (53 HU, p < 0.001). Image quality was higher for DLIR-M and DLIR-H (3.4-3.8 and 4.2-4.6) compared to ASiR-V SD and HD (2.1-2.7 and 1.8-2.2; p < 0.001), with DLIR-H yielding the highest image quality. Consistently across readers, no significant differences in sensitivity (88% vs. 92%; p = 0.453), specificity (73% vs. 73%; p = 0.583) and diagnostic accuracy (80% vs. 82%; p = 0.366) were found between ASiR-V HD and DLIR-H. DLIR significantly reduces noise in CCTA compared to ASiR-V, while yielding superior image quality at equal diagnostic accuracy.

Sections du résumé

BACKGROUND BACKGROUND
Advances in image reconstruction are necessary to decrease radiation exposure from coronary CT angiography (CCTA) further, but iterative reconstruction has been shown to degrade image quality at high levels. Deep-learning image reconstruction (DLIR) offers unique opportunities to overcome these limitations. The present study compared the impact of DLIR and adaptive statistical iterative reconstruction-Veo (ASiR-V) on quantitative and qualitative image parameters and the diagnostic accuracy of CCTA using invasive coronary angiography (ICA) as the standard of reference.
METHODS METHODS
This retrospective study includes 43 patients who underwent clinically indicated CCTA and ICA. Datasets were reconstructed with ASiR-V 70% (using standard [SD] and high-definition [HD] kernels) and with DLIR at different levels (i.e., medium [M] and high [H]). Image noise, image quality, and coronary luminal narrowing were evaluated by three blinded readers. Diagnostic accuracy was compared against ICA.
RESULTS RESULTS
Noise did not significantly differ between ASiR-V SD and DLIR-M (37 vs. 37 HU, p = 1.000), but was significantly lower in DLIR-H (30 HU, p < 0.001) and higher in ASiR-V HD (53 HU, p < 0.001). Image quality was higher for DLIR-M and DLIR-H (3.4-3.8 and 4.2-4.6) compared to ASiR-V SD and HD (2.1-2.7 and 1.8-2.2; p < 0.001), with DLIR-H yielding the highest image quality. Consistently across readers, no significant differences in sensitivity (88% vs. 92%; p = 0.453), specificity (73% vs. 73%; p = 0.583) and diagnostic accuracy (80% vs. 82%; p = 0.366) were found between ASiR-V HD and DLIR-H.
CONCLUSION CONCLUSIONS
DLIR significantly reduces noise in CCTA compared to ASiR-V, while yielding superior image quality at equal diagnostic accuracy.

Identifiants

DOI: 10.1016/j.jcct.2020.01.002 PMID: 31974008
pubmed: 31974008
pii: S1934-5925(19)30464-2
doi: 10.1016/j.jcct.2020.01.002
pii:
doi:

Types de publication

Comparative Study Journal Article Validation Study

Langues

eng

Sous-ensembles de citation

IM

Pagination

444-451

Informations de copyright

Copyright © 2020 Society of Cardiovascular Computed Tomography. Published by Elsevier Inc. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of competing interest The University Hospital Zurich holds a research agreement with GE Healthcare.

Auteurs

Dominik C Benz (DC)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: dominik.benz@usz.ch.

Georgios Benetos (G)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: Georgios.benetos@usz.ch.

Georgios Rampidis (G)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: grampidi@outlook.com.

Elia von Felten (E)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: e.v.f@hotmail.com.

Adam Bakula (A)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: adam.bakula@usz.ch.

Aleksandra Sustar (A)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: Aleksandra.sustar@usz.ch.

Ken Kudura (K)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: ken.kudura@usz.ch.

Michael Messerli (M)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: michael.messerli@usz.ch.

Tobias A Fuchs (TA)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: tobias.fuchs@usz.ch.

Catherine Gebhard (C)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: catherine.gebhard@usz.ch.

Aju P Pazhenkottil (AP)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: aju.pazhenkottil@usz.ch.

Philipp A Kaufmann (PA)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: pak@usz.ch.

Ronny R Buechel (RR)

Department of Nuclear Medicine, Cardiac Imaging, University and University Hospital Zurich, Ramistrasse 100, 8091, Zurich, Switzerland. Electronic address: ronny.buechel@usz.ch.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female

Evaluation of Low-Value Services Across Major Medicare Advantage Insurers and Traditional Medicare.

Ciara Duggan, Adam L Beckman, Ishani Ganguli et al.
1.00
Humans United States Aged Cross-Sectional Studies Medicare Part C

Effectiveness of Virtual Yoga for Chronic Low Back Pain: A Randomized Clinical Trial.

Hallie Tankha, Devyn Gaskins, Amanda Shallcross et al.
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH

questionsmedicales.fr › Personnes › Tranches d'âge › Adulte › Sujet âgé › Validation of deep-learning image...
questionsmedicales.fr › Techniques d'investigation › Artéfacts › Validation of deep-learning image...
questionsmedicales.fr › Diagnostic › Techniques et procédures diagnostiques › Imagerie diagnostique › Tomographie › Tomographie à rayons X › Tomodensitométrie › Angiographie par tomodensitométrie › Validation of deep-learning image...
questionsmedicales.fr › Diagnostic › Techniques et procédures diagnostiques › Techniques de diagnostic cardiovasculaire › Tests de la fonction cardiaque › Coronarographie › Validation of deep-learning image...
questionsmedicales.fr › Maladies cardiovasculaires › Maladies vasculaires › Ischémie myocardique › Maladie coronarienne › Maladie des artères coronaires › Validation of deep-learning image...
questionsmedicales.fr › Système cardiovasculaire › Vaisseaux sanguins › Veines › Vaisseaux coronaires › Validation of deep-learning image...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Réseaux neuronaux (ordinateur) › Apprentissage profond › Validation of deep-learning image...
questionsmedicales.fr › Sciences de l'information › Informatique › Informatique médicale › Applications de l'informatique médicale › Prise de décision assistée par ordinateur › Diagnostic assisté par ordinateur › Validation of deep-learning image...
questionsmedicales.fr › Eucaryotes › Animaux › Chordés › Vertébrés › Mammifères › Eutheria › Primates › Haplorhini › Catarrhini › Hominidae › Humains › Validation of deep-learning image...
questionsmedicales.fr › Personnes › Tranches d'âge › Adulte › Adulte d'âge moyen › Validation of deep-learning image...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Méthodologie en recherche épidémiologique › Valeur prédictive des tests › Validation of deep-learning image...
questionsmedicales.fr › Sciences de l'information › Informatique › Informatique médicale › Applications de l'informatique médicale › Prise de décision assistée par ordinateur › Diagnostic assisté par ordinateur › Interprétation d'images assistée par ordinateur › Interprétation d'images radiographiques assistée par ordinateur › Validation of deep-learning image...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Collecte de données › Enregistrements › Validation of deep-learning image...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Méthodologie en recherche épidémiologique › Reproductibilité des résultats › Validation of deep-learning image...
questionsmedicales.fr › Environnement et santé publique › Santé publique › Méthodes épidémiologiques › Caractéristiques des études épidémiologiques › Études épidémiologiques › Études de cohortes › Études rétrospectives › Validation of deep-learning image...