Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta

To evaluate the impact of a novel, deep-learning-based image reconstruction (DLIR) algorithm on image quality in CT angiography of the aorta, we retrospectively analyzed 51 consecutive patients who underwent ECG-gated chest CT angiography and non-gated acquisition for the abdomen on a 256-dectector-...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Andra Heinrich, Felix Streckenbach, Ebba Beller, Justus Groß, Marc-André Weber, Felix G. Meinel
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/abdf5f268faf4604bbc062a8cdd069f8
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:abdf5f268faf4604bbc062a8cdd069f8
record_format dspace
spelling oai:doaj.org-article:abdf5f268faf4604bbc062a8cdd069f82021-11-25T17:21:00ZDeep Learning-Based Image Reconstruction for CT Angiography of the Aorta10.3390/diagnostics111120372075-4418https://doaj.org/article/abdf5f268faf4604bbc062a8cdd069f82021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/2037https://doaj.org/toc/2075-4418To evaluate the impact of a novel, deep-learning-based image reconstruction (DLIR) algorithm on image quality in CT angiography of the aorta, we retrospectively analyzed 51 consecutive patients who underwent ECG-gated chest CT angiography and non-gated acquisition for the abdomen on a 256-dectector-row CT. Images were reconstructed with adaptive statistical iterative reconstruction (ASIR-V) and DLIR. Intravascular image noise, the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were quantified for the ascending aorta, the descending thoracic aorta, the abdominal aorta and the iliac arteries. Two readers scored subjective image quality on a five-point scale. Compared to ASIR-V, DLIR reduced the median image noise by 51–54% for the ascending aorta and the descending thoracic aorta. Correspondingly, median CNR roughly doubled for the ascending aorta and descending thoracic aorta. There was a 38% reduction in image noise for the abdominal aorta and the iliac arteries, with a corresponding improvement in CNR. Median subjective image quality improved from good to excellent at all anatomical levels. In CT angiography of the aorta, DLIR substantially improved objective and subjective image quality beyond what can be achieved by state-of-the-art iterative reconstruction. This can pave the way for further radiation or contrast dose reductions.Andra HeinrichFelix StreckenbachEbba BellerJustus GroßMarc-André WeberFelix G. MeinelMDPI AGarticledeep learningimage processingangiographycomputed tomographyaortaMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 2037, p 2037 (2021)
institution DOAJ
collection DOAJ
language EN
topic deep learning
image processing
angiography
computed tomography
aorta
Medicine (General)
R5-920
spellingShingle deep learning
image processing
angiography
computed tomography
aorta
Medicine (General)
R5-920
Andra Heinrich
Felix Streckenbach
Ebba Beller
Justus Groß
Marc-André Weber
Felix G. Meinel
Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta
description To evaluate the impact of a novel, deep-learning-based image reconstruction (DLIR) algorithm on image quality in CT angiography of the aorta, we retrospectively analyzed 51 consecutive patients who underwent ECG-gated chest CT angiography and non-gated acquisition for the abdomen on a 256-dectector-row CT. Images were reconstructed with adaptive statistical iterative reconstruction (ASIR-V) and DLIR. Intravascular image noise, the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were quantified for the ascending aorta, the descending thoracic aorta, the abdominal aorta and the iliac arteries. Two readers scored subjective image quality on a five-point scale. Compared to ASIR-V, DLIR reduced the median image noise by 51–54% for the ascending aorta and the descending thoracic aorta. Correspondingly, median CNR roughly doubled for the ascending aorta and descending thoracic aorta. There was a 38% reduction in image noise for the abdominal aorta and the iliac arteries, with a corresponding improvement in CNR. Median subjective image quality improved from good to excellent at all anatomical levels. In CT angiography of the aorta, DLIR substantially improved objective and subjective image quality beyond what can be achieved by state-of-the-art iterative reconstruction. This can pave the way for further radiation or contrast dose reductions.
format article
author Andra Heinrich
Felix Streckenbach
Ebba Beller
Justus Groß
Marc-André Weber
Felix G. Meinel
author_facet Andra Heinrich
Felix Streckenbach
Ebba Beller
Justus Groß
Marc-André Weber
Felix G. Meinel
author_sort Andra Heinrich
title Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta
title_short Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta
title_full Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta
title_fullStr Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta
title_full_unstemmed Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta
title_sort deep learning-based image reconstruction for ct angiography of the aorta
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/abdf5f268faf4604bbc062a8cdd069f8
work_keys_str_mv AT andraheinrich deeplearningbasedimagereconstructionforctangiographyoftheaorta
AT felixstreckenbach deeplearningbasedimagereconstructionforctangiographyoftheaorta
AT ebbabeller deeplearningbasedimagereconstructionforctangiographyoftheaorta
AT justusgroß deeplearningbasedimagereconstructionforctangiographyoftheaorta
AT marcandreweber deeplearningbasedimagereconstructionforctangiographyoftheaorta
AT felixgmeinel deeplearningbasedimagereconstructionforctangiographyoftheaorta
_version_ 1718412489839869952