Sparse-view CT Reconstruction using Wasserstein GANs

Franz Thaler; Kerstin Hammernik; Christian Payer; Martin Urschler; Darko Štern

doi:10.1007/978-3-030-00129-2_9

Sparse-view CT Reconstruction using Wasserstein GANs

Franz Thaler^*, Kerstin Hammernik, Christian Payer, Martin Urschler, Darko Štern

^*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

We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an L₁ content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on L₁ and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on L₁, the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences.

Originalsprache	englisch
Titel	Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings
Herausgeber (Verlag)	Springer Verlag Heidelberg
Seiten	75-82
Seitenumfang	8
Band	11074 LNCS
ISBN (Print)	9783030001285
DOIs	https://doi.org/10.1007/978-3-030-00129-2_9
Publikationsstatus	Veröffentlicht - 16 Sep. 2018
Veranstaltung	1st Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2018 Held in Conjunction with 21st Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 - Granada, Spanien Dauer: 16 Sep. 2018 → 16 Sep. 2018

Publikationsreihe

Name	Lecture Notes in Computer Science
Band	11074
ISSN (Print)	0302-9743
ISSN (elektronisch)	1611-3349

Konferenz

Konferenz	1st Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2018 Held in Conjunction with 21st Medical Image Computing and Computer Assisted Intervention, MICCAI 2018
Land/Gebiet	Spanien
Ort	Granada
Zeitraum	16/09/18 → 16/09/18

ASJC Scopus subject areas

Theoretische Informatik
Informatik (insg.)

Fields of Expertise

Information, Communication & Computing

Kooperationen

BioTechMed-Graz

Zugriff auf Dokument

10.1007/978-3-030-00129-2_9

Andere Dateien und Links

http://www.scopus.com/inward/record.url?scp=85053906671&partnerID=8YFLogxK

FWF - FAME - Vollautomatische MRT-basierte Altersschätzung von Jugendlichen
Bischof, H. & Urschler, M.
1/07/15 → 31/12/18
Projekt: Foschungsprojekt

Dieses zitieren

Thaler, F., Hammernik, K., Payer, C., Urschler, M., & Štern, D. (2018). Sparse-view CT Reconstruction using Wasserstein GANs. in Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings (Band 11074 LNCS, S. 75-82). (Lecture Notes in Computer Science ; Band 11074). Springer Verlag Heidelberg. https://doi.org/10.1007/978-3-030-00129-2_9

Sparse-view CT Reconstruction using Wasserstein GANs. / Thaler, Franz; Hammernik, Kerstin; Payer, Christian et al.

Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings. Band 11074 LNCS Springer Verlag Heidelberg, 2018. S. 75-82 (Lecture Notes in Computer Science ; Band 11074).

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

Thaler, F, Hammernik, K, Payer, C, Urschler, M & Štern, D 2018, Sparse-view CT Reconstruction using Wasserstein GANs. in Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings. Bd. 11074 LNCS, Lecture Notes in Computer Science , Bd. 11074, Springer Verlag Heidelberg, S. 75-82, 1st Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2018 Held in Conjunction with 21st Medical Image Computing and Computer Assisted Intervention, MICCAI 2018, Granada, Spanien, 16/09/18. https://doi.org/10.1007/978-3-030-00129-2_9

Thaler F, Hammernik K, Payer C, Urschler M, Štern D. Sparse-view CT Reconstruction using Wasserstein GANs. in Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings. Band 11074 LNCS. Springer Verlag Heidelberg. 2018. S. 75-82. (Lecture Notes in Computer Science ). doi: 10.1007/978-3-030-00129-2_9

@inproceedings{089cfb30f6ef49fb9fa046c235ac5e5f,

title = "Sparse-view CT Reconstruction using Wasserstein GANs",

abstract = "We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an L1 content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on L1 and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on L1, the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences.",

keywords = "Computed tomography, Convolutional neural networks, Generative adversarial networks, L1 loss, Sparse-view reconstruction",

author = "Franz Thaler and Kerstin Hammernik and Christian Payer and Martin Urschler and Darko {\v S}tern",

year = "2018",

month = sep,

day = "16",

doi = "10.1007/978-3-030-00129-2_9",

language = "English",

isbn = "9783030001285",

volume = "11074 LNCS",

series = "Lecture Notes in Computer Science ",

publisher = "Springer Verlag Heidelberg",

pages = "75--82",

booktitle = "Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings",

note = "1st Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2018 Held in Conjunction with 21st Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 ; Conference date: 16-09-2018 Through 16-09-2018",

}

TY - GEN

T1 - Sparse-view CT Reconstruction using Wasserstein GANs

AU - Thaler, Franz

AU - Hammernik, Kerstin

AU - Payer, Christian

AU - Urschler, Martin

AU - Štern, Darko

PY - 2018/9/16

Y1 - 2018/9/16

N2 - We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an L1 content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on L1 and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on L1, the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences.

AB - We propose a 2D computed tomography (CT) slice image reconstruction method from a limited number of projection images using Wasserstein generative adversarial networks (wGAN). Our wGAN optimizes the 2D CT image reconstruction by utilizing an adversarial loss to improve the perceived image quality as well as an L1 content loss to enforce structural similarity to the target image. We evaluate our wGANs using different weight factors between the two loss functions and compare to a convolutional neural network (CNN) optimized on L1 and the Filtered Backprojection (FBP) method. The evaluation shows that the results generated by the machine learning based approaches are substantially better than those from the FBP method. In contrast to the blurrier looking images generated by the CNNs trained on L1, the wGANs results appear sharper and seem to contain more structural information. We show that a certain amount of projection data is needed to get a correct representation of the anatomical correspondences.

KW - Computed tomography

KW - Convolutional neural networks

KW - Generative adversarial networks

KW - L1 loss

KW - Sparse-view reconstruction

UR - http://www.scopus.com/inward/record.url?scp=85053906671&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-00129-2_9

DO - 10.1007/978-3-030-00129-2_9

M3 - Conference paper

AN - SCOPUS:85053906671

SN - 9783030001285

VL - 11074 LNCS

T3 - Lecture Notes in Computer Science

SP - 75

EP - 82

BT - Machine Learning for Medical Image Reconstruction - First International Workshop, MLMIR 2018, Held in Conjunction with MICCAI 2018, Proceedings

PB - Springer Verlag Heidelberg

T2 - 1st Workshop on Machine Learning for Medical Image Reconstruction, MLMIR 2018 Held in Conjunction with 21st Medical Image Computing and Computer Assisted Intervention, MICCAI 2018

Y2 - 16 September 2018 through 16 September 2018

ER -

Sparse-view CT Reconstruction using Wasserstein GANs

Abstract

Publikationsreihe

Konferenz

ASJC Scopus subject areas

Fields of Expertise

Kooperationen

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Projekte

FWF - FAME - Vollautomatische MRT-basierte Altersschätzung von Jugendlichen

Dieses zitieren