Advertisement

Stereo-Correlation and Noise-Distribution Aware ResVoxGAN for Dense Slices Reconstruction and Noise Reduction in Thick Low-Dose CT

  • Rongjun Ge
  • Guanyu Yang
  • Chenchu Xu
  • Yang ChenEmail author
  • Limin Luo
  • Shuo LiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)

Abstract

The low-dose computed tomography (CT) scan with thick slice thickness (3 mm) dramatically improves the imaging efficiency and reduces the radiation risk in clinical. However, the low-dose CT acquisition inherently compromises the signal-to-noise ratio, and the sparse sampled thick slices poorly reproduce the coronal/sagittal anatomy. We propose a Residual Voxel Generative Adversarial Nets (ResVoxGAN), the first powerful work to densely reconstruct slices into the thin thickness (1 mm), and simultaneously denoise the CT image into the more readable pattern, directly from the widely accessible thick low-dose CT. The framework is achieved in a voxel-wise conditional GAN constituted by the following: (1) a generator is composed of consecutive 3D multi-scale residual blocks that richly extracts multi-scale stereo feature for fine-granted and latent spatial structure mining from the noisy volume, and a followed Subpixel Convnet further interpretively reconstructs dense slices from the features for high-resolution and denoising volume; (2) a stereo-correlation constraint elegantly penalizes gradient deviation in voxel adjacent region (i.e., 3D 26-neighborhoods) to guide structural detail, together with a image-expression constraint on perceptual feature representations transformed from a pretrained deep convolution autoencoder to keep scene content; and (3) a pair of coupled discriminators advantageously fuse the prior-knowledge from the thick low-dose CT with the generated image and residual noise via self-learning to drive the generation towards into both realistic anatomic structure distribution and valid noise-reduction distribution. The experiment validated on Mayo dataset shows that the ResVoxGAN successfully reconstruct the low-dose CT of 3 mm thickness into 1 mm, and meanwhile keeps the with peak signal to noise ratio of 40.80 for noise reduction, and structural similarity index of 0.918 for dense slices reconstruction. These advantages reveal our method a great potential in clinical CT imaging.

Notes

Acknowlegements

This study was supported by the Postgraduate Research & Practice Innovation Program of Jiangsu Province (No. KYCX17\(\_\)0104), the China Scholarship Council (No. 201706090248), the State’s Key Project of Research and Development Plan (No. 2017YFA0104302, No. 2017YFC0109202 and No. 2017YFC0107900), the National Natural Science Foundation (No. 81530060 and No. 61871117).

References

  1. 1.
    Coxson, H.O., Rogers, R.M., Whittall, K.P., D’yachkova, Y., Par, P.D., Sciurba, F.C.: A quantification of the lung surface area in emphysema using computed tomography. Am. J. Respir. Crit. Care Med. 159(3), 851–856 (1999)CrossRefGoogle Scholar
  2. 2.
    Rodrigues, J.C., Pierre, A.F., Hanneman, K., Cabanero, M., Kavanagh, J., et al.: CT-guided microcoil pulmonary nodule localization prior to video-assisted thoracoscopic surgery: diagnostic utility and recurrence-free survival. Radiology 291, 214–222 (2019). 181674CrossRefGoogle Scholar
  3. 3.
    Huynh, E., et al.: CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer. Radiother. Oncol. 120(2), 258–266 (2016)CrossRefGoogle Scholar
  4. 4.
    Kanal, K.M., Stewart, B.K., Kolokythas, O., Shuman, W.P.: Impact of operator-selected image noise index and reconstruction slice thickness on patient radiation dose in 64-MDCT. Am. J. Roentgenol. 189(1), 219–225 (2007)CrossRefGoogle Scholar
  5. 5.
    Bae, W., Lee, S., Park, G., Park, H., Jung, K.H.: Residual CNN-based image super-resolution for CT slice thickness reduction using paired CT scans: preliminary validation study. In: Medical Imaging with Deep Learning (2018)Google Scholar
  6. 6.
    National Lung Screening Trial Research Team: Reduced lung-cancer mortality with low-dose computed tomographic screening. N. Engl. J. Med. 365(5), 395–409 (2011)CrossRefGoogle Scholar
  7. 7.
    Wen, N., et al.: Dose delivered from Varian’s CBCT to patients receiving IMRT for prostate cancer. Phys. Med. Biol. 52(8), 2267 (2007)CrossRefGoogle Scholar
  8. 8.
    Liu, J., et al.: Discriminative feature representation to improve projection data inconsistency for low dose CT imaging. IEEE TMI 36(12), 2499–2509 (2017)Google Scholar
  9. 9.
    Chen, H., et al.: Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE TMI 36(12), 2524–2535 (2017)Google Scholar
  10. 10.
    Yang, Q., et al.: Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE TMI 37(6), 1348–1357 (2018)MathSciNetGoogle Scholar
  11. 11.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: NIPS, pp. 5767–5777 (2017)Google Scholar
  12. 12.
    Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR, pp. 1874–1883 (2016)Google Scholar
  13. 13.
    Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_43CrossRefGoogle Scholar
  14. 14.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)Google Scholar
  16. 16.
    Goldman, L.W.: Principles of CT: multislice CT. J. Nuclear Med. Technol. 36(2), 57–68 (2008)CrossRefGoogle Scholar
  17. 17.
    Ford, J.M., Decker, S.J.: Computed tomography slice thickness and its effects on three-dimensional reconstruction of anatomical structures. J. Forensic Radiol. Imaging 4, 43–46 (2016)CrossRefGoogle Scholar
  18. 18.
    Chadwick, J.W., Lam, E.W.: The effects of slice thickness and interslice interval on reconstructed cone beam computed tomographic images. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endodontol. 110(4), e37–e42 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Laboratory of Image Science and Technology, School of Computer Science and EngineeringSoutheast UniversityNanjingChina
  2. 2.Centre de Recherche en Information Biomedicale Sino-Francais (LIA CRIBs)RennesFrance
  3. 3.Key Laboratory of Computer Network and Information IntegrationSoutheast University, Ministry of EducationNanjingChina
  4. 4.School of Cyber Science and EngineeringSoutheast UniversityNanjingChina
  5. 5.Department of Medical Imaging and Medical BiophysicsWestern UniversityLondonCanada
  6. 6.Digital Imaging Group of LondonLondonCanada

Personalised recommendations