Deep Variational Networks with Exponential Weighting for Learning Computed Tomography
Tomographic image reconstruction is relevant for many medical imaging modalities including X-ray, ultrasound (US) computed tomography (CT) and photoacoustics, for which the access to full angular range tomographic projections might be not available in clinical practice due to physical or time constraints. Reconstruction from incomplete data in low signal-to-noise ratio regime is a challenging and ill-posed inverse problem that usually leads to unsatisfactory image quality. While informative image priors may be learned using generic deep neural network architectures, the artefacts caused by an ill-conditioned design matrix often have global spatial support and cannot be efficiently filtered out by means of convolutions. In this paper we propose to learn an inverse mapping in an end-to-end fashion via unrolling optimization iterations of a prototypical reconstruction algorithm. We herein introduce a network architecture that performs filtering jointly in both sinogram and spatial domains. To efficiently train such deep network we propose a novel regularization approach based on deep exponential weighting. Experiments on US and X-ray CT data show that our proposed method is qualitatively and quantitatively superior to conventional non-linear reconstruction methods as well as state-of-the-art deep networks for image reconstruction. Fast inference time of the proposed algorithm allows for sophisticated reconstructions in real-time critical settings, demonstrated with US SoS imaging of an ex vivo bovine phantom.
It was provided by the Swiss National Science Foundation (SNSF).
- 3.Cheng, A., et al.: Deep learning image reconstruction method for limited-angle ultrasound tomography in prostate cancer. In: Proceedings of SPIE Medical Imaging, p. 1095516 (2019)Google Scholar
- 8.Lin, H., Azuma, T., Unlu, M.B., Takagi, S.: Evaluation of adjoint methods in photoacoustic tomography with under-sampled sensors. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 73–81. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_9CrossRefGoogle Scholar
- 9.Liu, Y., Lew, M.S.: Learning relaxed deep supervision for better edge detection. In: CVPR, pp. 231–240 (2016)Google Scholar
- 12.Rau, R., Unal, O., Schweizer, D., Vishnevskiy, V., Goksel, O.: Attenuation imaging with pulse-echo ultrasound based on an acoustic reflector. In: MICCAI (2016, accepted). arXiv:1906.11615
- 13.Sanabria, S.J., Goksel, O.: Hand-held sound-speed imaging based on ultrasound reflector delineation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9900, pp. 568–576. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46720-7_66CrossRefGoogle Scholar
- 16.Schwab, J., Antholzer, S., Haltmeier, M.: Learned backprojection for sparse and limited view photoacoustic tomography. In: Proceedings of SPIE Photons Plus Ultrasound: Imaging and Sensing, p. 1087837 (2019)Google Scholar
- 17.Siewerdsen, J., et al.: Multimode C-arm fluoroscopy, tomosynthesis, and cone-beam CT for image-guided interventions: from proof of principle to patient protocols. In: Proceedings of SPIE Medical Imaging, p. 65101A (2007)Google Scholar
- 18.Soler, L., et al.: 3D image reconstruction for comparison of algorithm database: a patient specific anatomical and medical image database. Technical report. IRCAD, Strasbourg, France (2010)Google Scholar
- 19.Vishnevskiy, V., Sanabria, S.J., Goksel, O.: Image reconstruction via variational network for real-time hand-held sound-speed imaging. In: Knoll, F., Maier, A., Rueckert, D. (eds.) MLMIR 2018. LNCS, vol. 11074, pp. 120–128. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00129-2_14CrossRefGoogle Scholar