Improvement of megavoltage computed tomography image quality for adaptive helical tomotherapy using cycleGAN-based image synthesis with small datasets
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, D.[Lee, D.] | - |
dc.contributor.author | Jeong, S.W.[Jeong, S.W.] | - |
dc.contributor.author | Kim, S.J.[Kim, S.J.] | - |
dc.contributor.author | Cho, H.[Cho, H.] | - |
dc.contributor.author | Park, W.[Park, W.] | - |
dc.contributor.author | Han, Y.[Han, Y.] | - |
dc.date.accessioned | 2021-12-28T11:55:30Z | - |
dc.date.available | 2021-12-28T11:55:30Z | - |
dc.date.created | 2021-10-27 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.issn | 0094-2405 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/91049 | - |
dc.description.abstract | Purpose: Megavoltage computed tomography (MVCT) offers an opportunity for adaptive helical tomotherapy. However, high noise and reduced contrast in the MVCT images due to a decrease in the imaging dose to patients limits its usability. Therefore, we propose an algorithm to improve the image quality of MVCT. Methods: The proposed algorithm generates kilovoltage CT (kVCT)-like images from MVCT images using a cycle-consistency generative adversarial network (cycleGAN)-based image synthesis model. Data augmentation using an affine transformation was applied to the training data to overcome the lack of data diversity in the network training. The mean absolute error (MAE), root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) were used to quantify the correction accuracy of the images generated by the proposed algorithm. The proposed method was validated by comparing the images generated with those obtained from conventional and deep learning-based image processing method through non-augmented datasets. Results: The average MAE, RMSE, PSNR, and SSIM values were 18.91 HU, 69.35 HU, 32.73 dB, and 95.48 using the proposed method, respectively, whereas cycleGAN with non-augmented data showed inferior results (19.88 HU, 70.55 HU, 32.62 dB, 95.19, respectively). The voxel values of the image obtained by the proposed method also indicated similar distributions to those of the kVCT image. The dose-volume histogram of the proposed method was also similar to that of electron density corrected MVCT. Conclusions: The proposed algorithm generates synthetic kVCT images from MVCT images using cycleGAN with small patient datasets. The image quality achieved by the proposed method was correspondingly improved to the level of a kVCT image while maintaining the anatomical structure of an MVCT image. The evaluation of dosimetric effectiveness of the proposed method indicates the applicability of accurate treatment planning in adaptive radiation therapy. © 2021 American Association of Physicists in Medicine | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | John Wiley and Sons Ltd | - |
dc.subject | Deep learning | - |
dc.subject | Image enhancement | - |
dc.subject | Image quality | - |
dc.subject | Mean square error | - |
dc.subject | Metadata | - |
dc.subject | Radiotherapy | - |
dc.subject | Signal to noise ratio | - |
dc.subject | Adaptive radiation therapies | - |
dc.subject | Affine transformations | - |
dc.subject | Computed tomography images | - |
dc.subject | Dose-volume histograms | - |
dc.subject | Image processing - methods | - |
dc.subject | Peak signal to noise ratio | - |
dc.subject | Root mean square errors | - |
dc.subject | Structural similarity index measures (SSIM) | - |
dc.subject | Computerized tomography | - |
dc.subject | adaptive radiation | - |
dc.subject | adult | - |
dc.subject | affine transform | - |
dc.subject | anatomical concepts | - |
dc.subject | article | - |
dc.subject | comparative effectiveness | - |
dc.subject | computer assisted tomography | - |
dc.subject | deep learning | - |
dc.subject | dose volume histogram | - |
dc.subject | human | - |
dc.subject | image processing | - |
dc.subject | image quality | - |
dc.subject | quantitative analysis | - |
dc.subject | radiotherapy | - |
dc.subject | signal noise ratio | - |
dc.subject | synthesis | - |
dc.subject | tomotherapy | - |
dc.subject | treatment planning | - |
dc.title | Improvement of megavoltage computed tomography image quality for adaptive helical tomotherapy using cycleGAN-based image synthesis with small datasets | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, D.[Lee, D.] | - |
dc.contributor.affiliatedAuthor | Park, W.[Park, W.] | - |
dc.contributor.affiliatedAuthor | Han, Y.[Han, Y.] | - |
dc.identifier.doi | 10.1002/mp.15182 | - |
dc.identifier.scopusid | 2-s2.0-85113765554 | - |
dc.identifier.wosid | 000690865300001 | - |
dc.identifier.bibliographicCitation | Medical Physics, v.48, no.10, pp.5593 - 5610 | - |
dc.relation.isPartOf | Medical Physics | - |
dc.citation.title | Medical Physics | - |
dc.citation.volume | 48 | - |
dc.citation.number | 10 | - |
dc.citation.startPage | 5593 | - |
dc.citation.endPage | 5610 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Radiology, Nuclear Medicine & Medical Imaging | - |
dc.relation.journalWebOfScienceCategory | Radiology, Nuclear Medicine & Medical Imaging | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Image enhancement | - |
dc.subject.keywordPlus | Image quality | - |
dc.subject.keywordPlus | Mean square error | - |
dc.subject.keywordPlus | Metadata | - |
dc.subject.keywordPlus | Radiotherapy | - |
dc.subject.keywordPlus | Signal to noise ratio | - |
dc.subject.keywordPlus | Adaptive radiation therapies | - |
dc.subject.keywordPlus | Affine transformations | - |
dc.subject.keywordPlus | Computed tomography images | - |
dc.subject.keywordPlus | Dose-volume histograms | - |
dc.subject.keywordPlus | Image processing - methods | - |
dc.subject.keywordPlus | Peak signal to noise ratio | - |
dc.subject.keywordPlus | Root mean square errors | - |
dc.subject.keywordPlus | Structural similarity index measures (SSIM) | - |
dc.subject.keywordPlus | Computerized tomography | - |
dc.subject.keywordPlus | adaptive radiation | - |
dc.subject.keywordPlus | adult | - |
dc.subject.keywordPlus | affine transform | - |
dc.subject.keywordPlus | anatomical concepts | - |
dc.subject.keywordPlus | article | - |
dc.subject.keywordPlus | comparative effectiveness | - |
dc.subject.keywordPlus | computer assisted tomography | - |
dc.subject.keywordPlus | deep learning | - |
dc.subject.keywordPlus | dose volume histogram | - |
dc.subject.keywordPlus | human | - |
dc.subject.keywordPlus | image processing | - |
dc.subject.keywordPlus | image quality | - |
dc.subject.keywordPlus | quantitative analysis | - |
dc.subject.keywordPlus | radiotherapy | - |
dc.subject.keywordPlus | signal noise ratio | - |
dc.subject.keywordPlus | synthesis | - |
dc.subject.keywordPlus | tomotherapy | - |
dc.subject.keywordPlus | treatment planning | - |
dc.subject.keywordAuthor | adaptive radiation therapy | - |
dc.subject.keywordAuthor | cycleGAN | - |
dc.subject.keywordAuthor | data augmentation | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | image synthesis | - |
dc.subject.keywordAuthor | megavoltage computed tomography | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(03063) 25-2, SUNGKYUNKWAN-RO, JONGNO-GU, SEOUL, KOREAsamsunglib@skku.edu
COPYRIGHT © 2021 SUNGKYUNKWAN UNIVERSITY ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.