Deep learning and particle filter-based aortic dissection vessel tree segmentation

Yuan Jin; Antonio Pepe; Jianning Li; Christina Gsaxner; Jan Egger

doi:10.1117/12.2588220

Deep learning and particle filter-based aortic dissection vessel tree segmentation

Yuan Jin^*, Antonio Pepe, Jianning Li, Christina Gsaxner, Jan Egger

^*Korrespondierende/r Autor/-in für diese Arbeit

Institut für Maschinelles Sehen und Darstellen (7100)

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

Aortic dissections (AD) are injuries of the inner vessel wall of the (human) aorta. As this disease poses a significant threat to a patient's life, it is crucial to observe and analyze the progression of the dissection over the course of the disease. The clinical examinations are usually performed with the application of Computed Tomography (CT) or Computed Tomography Angiography (CTA), based on which, automated post-processing procedures would be beneficial for the management of critical pathologies. One of the main tasks during post-processing is aorta segmentation. Different methods have been developed for the segmentation of aorta, including the tracking methods, the active contour/surface methods and the deep learning methods. In this study, a method for the automatic segmentation of aorta and its branches from original thorax CT and CTA images is introduced. The aorta is segmented based on deep learning algorithm and afterwards the branches are tracked based on particle filter algorithm.

Originalsprache	englisch
Titel	Medical Imaging 2021
Untertitel	Biomedical Applications in Molecular, Structural, and Functional Imaging
Redakteure/-innen	Barjor S. Gimi, Andrzej Krol
Herausgeber (Verlag)	SPIE
ISBN (elektronisch)	9781510640290
DOIs	https://doi.org/10.1117/12.2588220
Publikationsstatus	Veröffentlicht - 2021
Veranstaltung	Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging - Virtual, Online, USA / Vereinigte Staaten Dauer: 15 Feb. 2021 → 19 Feb. 2021

Publikationsreihe

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Band	11600
ISSN (Print)	1605-7422

Konferenz

Konferenz	Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging
Land/Gebiet	USA / Vereinigte Staaten
Ort	Virtual, Online
Zeitraum	15/02/21 → 19/02/21

ASJC Scopus subject areas

Elektronische, optische und magnetische Materialien
Biomaterialien
Atom- und Molekularphysik sowie Optik
Radiologie, Nuklearmedizin und Bildgebung

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Zugriff auf Dokument

10.1117/12.2588220

Andere Dateien und Links

Verknüpfung zur Publikation in Scopus

Dieses zitieren

Jin, Y., Pepe, A., Li, J., Gsaxner, C., & Egger, J. (2021). Deep learning and particle filter-based aortic dissection vessel tree segmentation. in B. S. Gimi, & A. Krol (Hrsg.), Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging Artikel 116001W (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Band 11600). SPIE. https://doi.org/10.1117/12.2588220

Deep learning and particle filter-based aortic dissection vessel tree segmentation. / Jin, Yuan; Pepe, Antonio; Li, Jianning et al.
Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging. Hrsg. / Barjor S. Gimi; Andrzej Krol. SPIE, 2021. 116001W (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Band 11600).

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Jin, Y, Pepe, A, Li, J, Gsaxner, C & Egger, J 2021, Deep learning and particle filter-based aortic dissection vessel tree segmentation. in BS Gimi & A Krol (Hrsg.), Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging., 116001W, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Bd. 11600, SPIE, Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging, Virtual, Online, USA / Vereinigte Staaten, 15/02/21. https://doi.org/10.1117/12.2588220

@inproceedings{d3ceb5fffb7b4cd3b2f62e92e61ea288,

title = "Deep learning and particle filter-based aortic dissection vessel tree segmentation",

abstract = "Aortic dissections (AD) are injuries of the inner vessel wall of the (human) aorta. As this disease poses a significant threat to a patient's life, it is crucial to observe and analyze the progression of the dissection over the course of the disease. The clinical examinations are usually performed with the application of Computed Tomography (CT) or Computed Tomography Angiography (CTA), based on which, automated post-processing procedures would be beneficial for the management of critical pathologies. One of the main tasks during post-processing is aorta segmentation. Different methods have been developed for the segmentation of aorta, including the tracking methods, the active contour/surface methods and the deep learning methods. In this study, a method for the automatic segmentation of aorta and its branches from original thorax CT and CTA images is introduced. The aorta is segmented based on deep learning algorithm and afterwards the branches are tracked based on particle filter algorithm. ",

keywords = "Aortic Dissection, Computed Tomography Angiography, Deep Learning, Particle Filter., Segmentation, V-Net",

author = "Yuan Jin and Antonio Pepe and Jianning Li and Christina Gsaxner and Jan Egger",

note = "Publisher Copyright: {\textcopyright} COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.; Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging ; Conference date: 15-02-2021 Through 19-02-2021",

year = "2021",

doi = "10.1117/12.2588220",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Gimi, {Barjor S.} and Andrzej Krol",

booktitle = "Medical Imaging 2021",

address = "United States",

}

TY - GEN

T1 - Deep learning and particle filter-based aortic dissection vessel tree segmentation

AU - Jin, Yuan

AU - Pepe, Antonio

AU - Li, Jianning

AU - Gsaxner, Christina

AU - Egger, Jan

N1 - Publisher Copyright: © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

PY - 2021

Y1 - 2021

N2 - Aortic dissections (AD) are injuries of the inner vessel wall of the (human) aorta. As this disease poses a significant threat to a patient's life, it is crucial to observe and analyze the progression of the dissection over the course of the disease. The clinical examinations are usually performed with the application of Computed Tomography (CT) or Computed Tomography Angiography (CTA), based on which, automated post-processing procedures would be beneficial for the management of critical pathologies. One of the main tasks during post-processing is aorta segmentation. Different methods have been developed for the segmentation of aorta, including the tracking methods, the active contour/surface methods and the deep learning methods. In this study, a method for the automatic segmentation of aorta and its branches from original thorax CT and CTA images is introduced. The aorta is segmented based on deep learning algorithm and afterwards the branches are tracked based on particle filter algorithm.

AB - Aortic dissections (AD) are injuries of the inner vessel wall of the (human) aorta. As this disease poses a significant threat to a patient's life, it is crucial to observe and analyze the progression of the dissection over the course of the disease. The clinical examinations are usually performed with the application of Computed Tomography (CT) or Computed Tomography Angiography (CTA), based on which, automated post-processing procedures would be beneficial for the management of critical pathologies. One of the main tasks during post-processing is aorta segmentation. Different methods have been developed for the segmentation of aorta, including the tracking methods, the active contour/surface methods and the deep learning methods. In this study, a method for the automatic segmentation of aorta and its branches from original thorax CT and CTA images is introduced. The aorta is segmented based on deep learning algorithm and afterwards the branches are tracked based on particle filter algorithm.

KW - Aortic Dissection

KW - Computed Tomography Angiography

KW - Deep Learning

KW - Particle Filter.

KW - Segmentation

KW - V-Net

UR - http://www.scopus.com/inward/record.url?scp=85103178601&partnerID=8YFLogxK

U2 - 10.1117/12.2588220

DO - 10.1117/12.2588220

M3 - Conference paper

AN - SCOPUS:85103178601

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2021

A2 - Gimi, Barjor S.

A2 - Krol, Andrzej

PB - SPIE

T2 - Medical Imaging 2021: Biomedical Applications in Molecular, Structural, and Functional Imaging

Y2 - 15 February 2021 through 19 February 2021

ER -

Deep learning and particle filter-based aortic dissection vessel tree segmentation

Abstract

Publikationsreihe

Konferenz

ASJC Scopus subject areas

UN SDGs

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Dieses zitieren