A cycle generative adversarial network for improving the quality of four-dimensional cone-beam computed tomography images.

Cone-Beam Computed Tomography / methods Four-Dimensional Computed Tomography Humans Image Processing, Computer-Assisted / methods Lung Neoplasms / diagnostic imaging Phantoms, Imaging Radiotherapy Planning, Computer-Assisted / methods
4D-CBCT ART CycleGAN Image quality correction Lung cancer

Journal

Radiation oncology (London, England)
ISSN: 1748-717X
Titre abrégé: Radiat Oncol
Pays: England
ID NLM: 101265111

Informations de publication

Date de publication:
07 Apr 2022
Historique:
received: 08 12 2021
accepted: 23 03 2022
entrez: 8 4 2022
pubmed: 9 4 2022
medline: 12 4 2022
Statut: epublish

Résumé

Four-dimensional cone-beam computed tomography (4D-CBCT) can visualize moving tumors, thus adaptive radiation therapy (ART) could be improved if 4D-CBCT were used. However, 4D-CBCT images suffer from severe imaging artifacts. The aim of this study is to investigate the use of synthetic 4D-CBCT (sCT) images created by a cycle generative adversarial network (CycleGAN) for ART for lung cancer. Unpaired thoracic 4D-CBCT images and four-dimensional multislice computed tomography (4D-MSCT) images of 20 lung-cancer patients were used for training. High-quality sCT lung images generated by the CycleGAN model were tested on another 10 cases. The mean and mean absolute errors were calculated to assess changes in the computed tomography number. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) were used to compare the sCT and original 4D-CBCT images. Moreover, a volumetric modulation arc therapy plan with a dose of 48 Gy in four fractions was recalculated using the sCT images and compared with ideal dose distributions observed in 4D-MSCT images. The generated sCT images had fewer artifacts, and lung tumor regions were clearly observed in the sCT images. The mean and mean absolute errors were near 0 Hounsfield units in all organ regions. The SSIM and PSNR results were significantly improved in the sCT images by approximately 51% and 18%, respectively. Moreover, the results of gamma analysis were significantly improved; the pass rate reached over 90% in the doses recalculated using the sCT images. Moreover, each organ dose index of the sCT images agreed well with those of the 4D-MSCT images and were within approximately 5%. The proposed CycleGAN enhances the quality of 4D-CBCT images, making them comparable to 4D-MSCT images. Thus, clinical implementation of sCT-based ART for lung cancer is feasible.

Sections du résumé

BACKGROUND BACKGROUND
Four-dimensional cone-beam computed tomography (4D-CBCT) can visualize moving tumors, thus adaptive radiation therapy (ART) could be improved if 4D-CBCT were used. However, 4D-CBCT images suffer from severe imaging artifacts. The aim of this study is to investigate the use of synthetic 4D-CBCT (sCT) images created by a cycle generative adversarial network (CycleGAN) for ART for lung cancer.
METHODS METHODS
Unpaired thoracic 4D-CBCT images and four-dimensional multislice computed tomography (4D-MSCT) images of 20 lung-cancer patients were used for training. High-quality sCT lung images generated by the CycleGAN model were tested on another 10 cases. The mean and mean absolute errors were calculated to assess changes in the computed tomography number. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) were used to compare the sCT and original 4D-CBCT images. Moreover, a volumetric modulation arc therapy plan with a dose of 48 Gy in four fractions was recalculated using the sCT images and compared with ideal dose distributions observed in 4D-MSCT images.
RESULTS RESULTS
The generated sCT images had fewer artifacts, and lung tumor regions were clearly observed in the sCT images. The mean and mean absolute errors were near 0 Hounsfield units in all organ regions. The SSIM and PSNR results were significantly improved in the sCT images by approximately 51% and 18%, respectively. Moreover, the results of gamma analysis were significantly improved; the pass rate reached over 90% in the doses recalculated using the sCT images. Moreover, each organ dose index of the sCT images agreed well with those of the 4D-MSCT images and were within approximately 5%.
CONCLUSIONS CONCLUSIONS
The proposed CycleGAN enhances the quality of 4D-CBCT images, making them comparable to 4D-MSCT images. Thus, clinical implementation of sCT-based ART for lung cancer is feasible.

Identifiants

DOI: 10.1186/s13014-022-02042-1 PMID: 35392947 PMC: PMC8991563
pubmed: 35392947
doi: 10.1186/s13014-022-02042-1
pii: 10.1186/s13014-022-02042-1
pmc: PMC8991563
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

69

Informations de copyright

© 2022. The Author(s).

Références

IEEE Trans Radiat Plasma Med Sci. 2021 Mar;5(2):185-192
pubmed: 33778235
J Digit Imaging. 2013 Dec;26(6):1045-57
pubmed: 23884657
Front Oncol. 2021 Mar 12;11:603844
pubmed: 33777746
Med Image Anal. 1998 Sep;2(3):243-60
pubmed: 9873902
Semin Radiat Oncol. 2015 Apr;25(2):78-86
pubmed: 25771411
Med Phys. 2019 Jan;46(1):e1-e36
pubmed: 30367497
Comput Biol Med. 2015 May;60:117-31
pubmed: 25817533
Int J Radiat Oncol Biol Phys. 2011 May 1;80(1):301-5
pubmed: 20864274
Phys Med Biol. 2019 Jun 10;64(12):125002
pubmed: 31108465
IEEE Trans Med Imaging. 2019 Nov;38(11):2705-2715
pubmed: 31021791
Acta Oncol. 2006;45(7):915-22
pubmed: 16982558
Phys Med. 2020 Dec;80:308-316
pubmed: 33246190
Int J Radiat Oncol Biol Phys. 2015 Apr 1;91(5):1026-33
pubmed: 25832693
Med Phys. 2019 Sep;46(9):3998-4009
pubmed: 31206709
Med Phys. 2021 Dec;48(12):7673-7684
pubmed: 34725829
Phys Med Biol. 2018 Apr 19;63(8):085014
pubmed: 29537385
Med Phys. 2005 Apr;32(4):1176-86
pubmed: 15895601
Int J Radiat Oncol Biol Phys. 2006 Dec 1;66(5):1553-61
pubmed: 17056197
Int J Radiat Oncol Biol Phys. 2005 Mar 1;61(3):779-88
pubmed: 15708257
Radiat Oncol. 2021 Oct 14;16(1):202
pubmed: 34649572
Dentomaxillofac Radiol. 2011 Jul;40(5):265-73
pubmed: 21697151
Vis Comput Ind Biomed Art. 2019;2(1):23
pubmed: 32190409
Phys Med. 2020 Aug;76:243-276
pubmed: 32736286
J Med Imaging (Bellingham). 2017 Jul;4(3):035501
pubmed: 28924574
Quant Imaging Med Surg. 2013 Jun;3(3):147-61
pubmed: 23833728
Int J Radiat Oncol Biol Phys. 2016 Feb 1;94(2):394-403
pubmed: 26678659
Phys Med. 2019 Sep;65:67-75
pubmed: 31430590
Phys Med Biol. 2019 Jan 24;64(3):035011
pubmed: 30523998

Auteurs

Keisuke Usui (K)

Department of Radiological Technology, Faculty of Health Science, Juntendo University, 2-1-1, Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan. k-usui@juntendo.ac.jp.

Koichi Ogawa (K)

Department of Applied Informatics, Faculty of Science and Engineering, Hosei University, 3-7-3, Kajino, Koganei, Tokyo, 184-8584, Japan.

Masami Goto (M)

Department of Radiological Technology, Faculty of Health Science, Juntendo University, 2-1-1, Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.

Yasuaki Sakano (Y)

Department of Radiological Technology, Faculty of Health Science, Juntendo University, 2-1-1, Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.

Shinsuke Kyougoku (S)

Department of Radiological Technology, Faculty of Health Science, Juntendo University, 2-1-1, Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.

Hiroyuki Daida (H)

Department of Radiological Technology, Faculty of Health Science, Juntendo University, 2-1-1, Hongo, Bunkyo-ku, Tokyo, 113-8421, Japan.

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 › Diagnostic › Techniques et procédures diagnostiques › Imagerie diagnostique › Tomographie › Tomographie à rayons X › Tomodensitométrie › Tomodensitométrie à faisceau conique › A cycle generative adversarial network for...
questionsmedicales.fr › Diagnostic › Techniques et procédures diagnostiques › Imagerie diagnostique › Tomographie › Tomographie à rayons X › Tomodensitométrie › Tomodensitométrie 4D › A cycle generative adversarial network for...
questionsmedicales.fr › Eucaryotes › Animaux › Chordés › Vertébrés › Mammifères › Eutheria › Primates › Haplorhini › Catarrhini › Hominidae › Humains › A cycle generative adversarial network for...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Traitement d'image par ordinateur › A cycle generative adversarial network for...
questionsmedicales.fr › Maladies de l'appareil respiratoire › Tumeurs de l'appareil respiratoire › Tumeurs du poumon › A cycle generative adversarial network for...
questionsmedicales.fr › Équipement et fournitures › Fantômes en imagerie › A cycle generative adversarial network for...
questionsmedicales.fr › Sciences de l'information › Informatique › Informatique médicale › Applications de l'informatique médicale › Prise de décision assistée par ordinateur › Thérapie assistée par ordinateur › Radiothérapie assistée par ordinateur › Planification de radiothérapie assistée par ordinateur › A cycle generative adversarial network for...