Abstract
This study aimed to inpaint the truncated areas of CT images by using generative adversarial networks with gated convolution (GatedConv) and apply these images to dose calculations in radiotherapy. CT images were collected from 100 patients with esophageal cancer under thermoplastic membrane placement, and 85 cases were used for training based on randomly generated circle masks. In the prediction stage, 15 cases of data were used to evaluate the accuracy of the inpainted CT in anatomy and dosimetry based on the mask with a truncated volume covering 40% of the arm volume, and they were compared with the inpainted CT synthesized by U-Net, pix2pix, and PConv with partial convolution. The results showed that GatedConv could directly and effectively inpaint incomplete CT images in the image domain. For the results of U-Net, pix2pix, PConv, and GatedConv, the mean absolute errors for the truncated tissue were 195.54, 196.20, 190.40, and 158.45 HU, respectively. The mean dose of the planning target volume, heart, and lung in the truncated CT was statistically different (p < 0.05) from those of the ground truth CT (\({\mathrm{CT}}_{\mathrm{gt}}\)). The differences in dose distribution between the inpainted CT obtained by the four models and \({\mathrm{CT}}_{\mathrm{gt}}\) were minimal. The inpainting effect of clinical truncated CT images based on GatedConv showed better stability compared with the other models. GatedConv can effectively inpaint the truncated areas with high image quality, and it is closer to \({\mathrm{CT}}_{\mathrm{gt}}\) in terms of image visualization and dosimetry than other inpainting models.
Graphical Abstract
Similar content being viewed by others
References
Chen HH, Kuo MT (2017) Improving radiotherapy in cancer treatment: promises and challenges. Oncotarget 8(37):62742–62758
Molinelli S, Russo S, Magro G, Maestri D, Mairani A, Mastella E, Mirandola A, Vai A, Vischioni B, Valvo F (2019) Impact of TPS calculation algorithms on dose delivered to the patient in proton therapy treatments. Phys Med Biol 64(7):075016
van der Heyden B, Wohlfahrt P, Eekers DB, Richter C, Terhaag K, Troost EG, Verhaegen F (2019) Dual-energy CT for automatic organs-at-risk segmentation in brain-tumor patients using a multi-atlas and deep-learning approach. Sci Rep 9(1):4126
Swinnen AC, Öllers MC, Loon Ong C, Verhaegen F (2020) The potential of an optical surface tracking system in non-coplanar single isocenter treatments of multiple brain metastases. J Appl Clin Med Phys 21(6):63–72
Podesta M, Nijsten SMJJG, Persoon LCGG, Scheib SG, Baltes C, Verhaegen F (2014) Time dependent pre-treatment EPID dosimetry for standard and FFF VMAT. Phys Med Biol 59(16):4749
Fonseca GP, Baer-Beck M, Fournie E, Hofmann C, Rinaldi I, Ollers MC, van Elmpt WJ, Verhaegen F (2021) Evaluation of novel AI-based extended field-of-view CT reconstructions. Med Phys 48(7):3583–3594
Wu V, Podgorsak MB, Tran TA, Malhotra HK, Wang IZ (2011) Dosimetric impact of image artifact from a wide-bore CT scanner in radiotherapy treatment planning. Med Phys 38(7):4451–4463
Murrell DH, Karnas SJ, Corkum MT, Hipwell S, Louie AV (2019) Radical radiotherapy for locally advanced non-small cell lung cancer—what’s up with arm positioning? J Thorac Dis 11(5):2099–2104
Hui Z, Wang Q, Han W, Sun S, Wang M, Dai J, Wang L (2014) Comparation of set-up errors between two different body positions in precision radiotherapy for esophageal cancer. Chin J Radiat Oncol 23(4):336–339
Cheung JP, Shugard E, Mistry N, Pouliot J, Chen J (2019) Evaluating the impact of extended field-of-view CT reconstructions on CT values and dosimetric accuracy for radiation therapy. Med Phys 46(2):892–901
Hsieh J, Chao E, Thibault J, Grekowicz B, Horst A, Mcolash S, Myers TJ (2004) A novel reconstruction algorithm to extend the CT scan field-of-view. Med Phys 31(9):2385–2391
Sourbelle K, Kachelrieß M, Kalender WA (2005) Reconstruction from truncated projections in CT using adaptive detruncation. Eur Radiol 15(5):1008–1014
Xia Y, Berger M, Bauer S, Hu S, Aichert A, Maier A (2017) An improved extrapolation scheme for truncated CT data using 2D Fourier-based Helgason-Ludwig consistency conditions. Int J Biomed Imaging 2017:1867025
Du Y, Zhu L, Xi X, Han Y, Li L, Yan B (2020) CT local reconstruction method based on truncated data extrapolation network. Appl Opt Photon China (AOPC 2020) 11565:221–226
Li B, Deng J, Lonn AH, Jiang H (2012) An enhanced reconstruction algorithm to extend CT scan field-of-view with z-axis consistency constraint. Med Phys 39(10):6028–6034
Bruder H, Sedlmair MU, Stierstorfer K, Flohr TG (2011) High definition extended field of view (HD FOV) reconstruction in CT. In: Radiological Society of North America 2011 Scientific Assembly and Annual Meeting. Chicago, IL, p 1. http://archive.rsna.org/2011/11015308.html. Accessed 8 Mar 2023
Bhosale YH, Patnaik KS (2022) Application of deep learning techniques in diagnosis of covid-19 (coronavirus): a systematic review. Neural Process Lett 1–53. https://doi.org/10.1007/s11063-022-11023-0
Bhosale YH, Patnaik KS (2023) PulDi-COVID: Chronic obstructive pulmonary (lung) diseases with COVID-19 classification using ensemble deep convolutional neural network from chest X-ray images to minimize severity and mortality rates. Biomed Sig Process Control 81:104445
Fournié É, Baer-Beck M, Stierstorfer K (2019) CT field of view extension using combined channels extension and deep learning methods, arXiv preprint arXiv:1908.09529. https://doi.org/10.48550/arXiv.1908.09529
Huang Y, Gao L, Preuhs A, Maier A (2020) Field of view extension in computed tomography using deep learning prior. In: Tolxdorff T, Deserno T, Handels H, Maier A, Maier-Hein K, Palm C (eds) Bildverarbeitung für die Medizin 2020. Informatik aktuell. Springer Vieweg, Wiesbaden, pp 186–191. https://doi.org/10.1007/978-3-658-29267-6_40
Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. In: Proceedings of the 27th annual conference on computer graphics and interactive techniques. ACM Press/Addison-Wesley Publishing Co, New York, NY, pp 417–424
Pathak D, Krahenbuhl P, Donahue J, Darrell T, Efros A A (2016) Context encoders: feature learning by inpainting. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, pp 2536–2544. https://doi.org/10.1109/CVPR.2016.278
Goodfellow IJ, Pougetabadie J, Mirza M, Xu B, Wardefarley D, Ozair S, Courville AC, Bengio Y (2014) Generative adversarial nets. Neural Inf Process Syst 2:2672–2680
Iizuka S, Simo-Serra E, Ishikawa H (2017) Globally and locally consistent image completion. ACM Trans Graph (ToG) 36(4):107.101–107.114
Yu J, Lin Z, Yang J, Shen X, Lu X, Huang TS (2018) Generative image inpainting with contextual attention. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, pp 5505–5514. https://doi.org/10.1109/CVPR.2018.00577
Liu G, Reda FA, Shih KJ, Wang T-C, Tao A, Catanzaro B (2018) Image inpainting for irregular holes using partial convolutions. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol 11215. Springer, Cham, pp 85–100. https://doi.org/10.1007/978-3-030-01252-6_6
Yu J, Lin Z, Yang J, Shen X, Lu X, Huang TS (2019) Free-form image inpainting with gated convolution. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Seoul, Korea, pp 4471–4480
Suvorov R, Logacheva E, Mashikhin A, Remizova A, Ashukha A, Silvestrov A, Kong N, Goka H, Park K, Lempitsky V (2022) Resolution-robust large mask inpainting with fourier convolutions. In: Proceedings of 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, pp 2149–2159. https://doi.org/10.48550/arXiv.2109.07161
Yu Y, Zhan F, Wu R, Pan J, Cui K, Lu S, Ma F, Xie X, Miao C (2021) Diverse image inpainting with bidirectional and autoregressive transformers. In: Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery, New York, NY, pp 69–78
Li W, Yu X, Zhou K, Song Y, Lin Z, Jia J (2022) SDM: spatial diffusion model for large hole image inpainting. arXiv preprint arXiv:2212.02963. https://doi.org/10.48550/arXiv.2212.02963
Armanious K, Mecky Y, Gatidis S, Yang B (2019) Adversarial inpainting of medical image modalities. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Brighton, UK, pp 3267–3271
Armanious K, Kumar V, Abdulatif S, Hepp T, Yang B (2020) ipA-MedGAN: inpainting of arbitrarily regions in medical modalities. In: 2020 IEEE International Conference on Image Processing (ICIP). IEEE, Abu Dhabi, United Arab Emirates, pp 3005–3009
Wang Q, Chen Y, Zhang N, Gu Y (2021) Medical image inpainting with edge and structure priors. Measurement 185:110027
Tran M-T, Kim S-H, Yang H-J, Lee G-S (2021) Multi-task learning for medical image inpainting based on organ boundary awareness. Appl Sci 11(9):4247
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science, vol 9351. Springer, Cham, pp 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Isola P, Zhu J, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, pp 5967–5976
Miyato T, Kataoka T, Koyama M, Yoshida Y (2018) Spectral normalization for generative adversarial networks. In: International Conference on Learning Representations. ICLR, pp 1–26. https://openreview.net/forum?id=B1QRgziT-
Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition. IEEE, Istanbul, Turkey, pp 2366–2369
Sara U, Akter M, Uddin MS (2019) Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. J Comput Commun 7(3):8–18
Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302
Unkelbach J, Bortfeld T, Craft D, Alber M, Bangert M, Bokrantz R, Chen D, Li R, Xing L, Men C (2015) Optimization approaches to volumetric modulated arc therapy planning. Med Phys 42(3):1367–1377
Fiandra C, Filippi AR, Catuzzo P, Botticella A, Ciammella P, Franco P, Borca VC, Ragona R, Tofani S, Ricardi U (2012) Different IMRT solutions vs. 3D-conformal radiotherapy in early stage Hodgkin’s Lymphoma: dosimetric comparison and clinical considerations. Radiat Oncol 7(1):1–9
Ma P, Wang X, Xu Y, Dai J, Wang L (2014) Applying the technique of volume-modulated arc radiotherapy to upper esophageal carcinoma. J Appl Clin Med Phys 15(3):221–228
Zhang W-Z, Zhai T-T, Lu J-Y, Chen J-Z, Chen Z-J, Li D-R, Chen C-Z (2015) Volumetric modulated arc therapy vs. c-IMRT for the treatment of upper thoracic esophageal cancer. PLoS ONE 10(3):e0121385
Paddick I (2000) A simple scoring ratio to index the conformity of radiosurgical treatment plans. J Neurosurg 93(supplement_3):219–222
Semenenko VA, Reitz B, Day E, Qi XS, Miften M, Li XA (2008) Evaluation of a commercial biologically based IMRT treatment planning system. Med Phys 35(12):5851–5860
Aziz NAA, Mubin M, Ibrahim Z, Nawawi SW (2015) Statistical analysis for swarm intelligence—simplified. Int J Future Comput Commun 4(3):193–197
Huang Y, Preuhs A, Manhart M, Lauritsch G, Maier A (2021) Data extrapolation from learned prior images for truncation correction in computed tomography. IEEE Trans Med Imaging 99:1–12
Liu Y, Le Y, Wang T, Fu Y, Tang X, Curran W, Liu T, Patel P, Yang X (2020) CBCT-based synthetic CT generation using deep-attention cycleGAN for pancreatic adaptive radiotherapy. Med Phys 47(6):2472–2483
Funding
This work is supported by the Changzhou Sci&Tech Program (Nos. CJ20210128 and CJ20200099), Jiangsu Provincial Key Research and Development Program Social Development Project (No. BE2022720), General Program of Jiangsu Provincial Health Commission (No. M2020006), Changzhou Key Laboratory of Medical Physics (No. CM20193005), Young Talent Development Plan of Changzhou Health Commission (Nos. CZQM2020075 and CZQM2020067), and the Science and Technology Programs for Young Talents of Changzhou Health Commission (No. QN201932).
Author information
Authors and Affiliations
Contributions
Kai Xie and Liugang Gao contributed equally to this work. Kai Xie, Liugang Gao, and Xinye Ni collected the data and wrote the manuscript draft. Kai Xie, Liugang Gao, and Heng Zhang performed the training of different models. Jiawei Sun, Tao Lin, and Jianfeng Sui designed the VMAT plans. Sai Zhang, Qianyi Xi, and Fan analyzed the results. All authors discussed the results and have given approval to the final version of the manuscript.
Corresponding author
Ethics declarations
Ethics approval and consent to participate
The retrospective study was approved by the Clinical Ethics Committee of Second People’s Hospital of Changzhou of Nanjing Medical University (#2020KY154-01). Written informed consent to participate in this study was not required in accordance with national and institutional guidelines.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xie, K., Gao, L., Zhang, H. et al. Inpainting truncated areas of CT images based on generative adversarial networks with gated convolution for radiotherapy. Med Biol Eng Comput 61, 1757–1772 (2023). https://doi.org/10.1007/s11517-023-02809-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-023-02809-y