Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution
In this work, we investigate the value of uncertainty modelling in 3D super-resolution with convolutional neural networks (CNNs). Deep learning has shown success in a plethora of medical image transformation problems, such as super-resolution (SR) and image synthesis. However, the highly ill-posed nature of such problems results in inevitable ambiguity in the learning of networks. We propose to account for intrinsic uncertainty through a per-patch heteroscedastic noise model and for parameter uncertainty through approximate Bayesian inference in the form of variational dropout. We show that the combined benefits of both lead to the state-of-the-art performance SR of diffusion MR brain images in terms of errors compared to ground truth. We further show that the reduced error scores produce tangible benefits in downstream tractography. In addition, the probabilistic nature of the methods naturally confers a mechanism to quantify uncertainty over the super-resolved output. We demonstrate through experiments on both healthy and pathological brains the potential utility of such an uncertainty measure in the risk assessment of the super-resolved images for subsequent clinical use.
This work was supported by Microsoft scholarship. Data were provided in part by the HCP, WU-Minn Consortium (PIs: David Van Essen and Kamil Ugurbil) funded by NIH and Wash. U. The tumour data were acquired as part of a study lead by Alberto Bizzi, MD at his hospital in Milan, Italy.
- 2.Oktay, O., Bai, W., Lee, M., Guerrero, R., Kamnitsas, K., Caballero, J., Marvao, A., Cook, S., O’Regan, D., Rueckert, D.: Multi-input cardiac image super-resolution using convolutional neural networks. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 246–254. Springer, Cham (2016). doi: 10.1007/978-3-319-46726-9_29 CrossRefGoogle Scholar
- 3.Bahrami, K., Shi, F., Rekik, I., Shen, D.: Convolutional neural network for reconstruction of 7T-like images from 3T MRI using appearance and anatomical features. In: Carneiro, G., et al. (eds.) LABELS/DLMIA -2016. LNCS, vol. 10008, pp. 39–47. Springer, Cham (2016). doi: 10.1007/978-3-319-46976-8_5 Google Scholar
- 4.Tanno, R., Ghosh, A., Grussu, F., Kaden, E., Criminisi, A., Alexander, D.C.: Bayesian image quality transfer. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 265–273. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_31 CrossRefGoogle Scholar
- 5.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
- 7.Kingma, D.P., Salimans, T., Welling, M.: Variational dropout and the local reparameterization trick. In: NIPS, pp. 2575–2583 (2015)Google Scholar
- 12.Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs/1412.6980 (2014)Google Scholar
- 13.Tournier, J., Calamante, F., Connelly, A.: Improved probabilistic streamlines tractography by 2nd order integration over fiber orientation distributions. In: ISMRM, p. 1670 (2010)Google Scholar