Inter-Scanner Harmonization of High Angular Resolution DW-MRI Using Null Space Deep Learning
Diffusion-weighted magnetic resonance imaging (DW-MRI) allows for non-invasive imaging of the local fiber architecture of the human brain at a millimetric scale. Multiple classical approaches have been proposed to detect both single (e.g., tensors) and multiple (e.g., constrained spherical deconvolution, CSD) fiber population orientations per voxel. However, existing techniques generally exhibit low reproducibility across MRI scanners. Herein, we propose a data-driven technique using a neural network design which exploits two categories of data. First, training data were acquired on three squirrel monkey brains using ex-vivo DW-MRI and histology of the brain. Second, repeated scans of human subjects were acquired on two different scanners to augment the learning of the network proposed. To use these data, we propose a new network architecture, the null space deep network (NSDN), to simultaneously learn on traditional observed/truth pairs (e.g., MRI-histology voxels) along with repeated observations without a known truth (e.g., scan-rescan MRI). The NSDN was tested on twenty percent of the histology voxels that were kept completely blind to the network. NSDN significantly improved absolute performance relative to histology by 3.87% over CSD and 1.42% over a recently proposed deep neural network approach. More-over, it improved reproducibility on the paired data by 21.19% over CSD and 10.09% over a recently proposed deep approach. Finally, NSDN improved generalizability of the model to a third in-vivo human scanner (which was not used in training) by 16.08% over CSD and 10.41% over a recently proposed deep learning approach. This work suggests that data-driven approaches for local fiber reconstruction are more reproducible, informative, precise and offer a novel, practical method for determining these models.
KeywordsDiffusion HARDI DW-MRI Null space CSD Harmonization Inter-scanner Deep learning Histology
This work was supported by R01EB017230 (Landman), RO1NS058639 (Anderson), S10RR17799 (Gore) and T32EB001628. This work was conducted in part using the resources of the Advanced Computing Center for Research and Education at Vanderbilt University, Nashville, TN. This project was supported in part by the National Center for Research Resources, Grant UL1 RR024975-01, and is now at the National Center for Advancing Translational Sciences, Grant 2 UL1 TR000445-06. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. This work has been supported by Nvidia with supplement of hardware resources (GPUs). Glyph visualizations were supported using .
- 3.Tournier, J., Calamante, F., Connelly, A.: How many diffusion gradient directions are required for HARDI. In: Proceedings of the International Society Magnetic Resonance in Medicine (2009)Google Scholar
- 9.Nath, V., et al.: Comparison of multi-fiber reproducibility of PAS-MRI and Q-ball with empirical multiple b-value HARDI. In: Medical Imaging 2017: Image Processing (2017). (International Society for Optics and Photonics)Google Scholar
- 10.Helmer, K., et al.: Multi-site study of diffusion metric variability: effects of site, vendor, field strength, and echo time on regions-of-interest and histogram-bin analyses. In: Medical Imaging 2016: Biomedical Applications in Molecular, Structural, and Functional Imaging. International Society for Optics and Photonics (2016)Google Scholar
- 13.Mirzaalian, H., et al.: Harmonizing diffusion MRI data across multiple sites and scanners. In: International Conference on Medical Image Computing and Computer Assisted Intervention. Springer (2015)Google Scholar
- 16.Nath, Vishwesh, et al.: Deep learning captures more accurate diffusion fiber orientations distributions than constrained spherical deconvolution. In: ISMRM 2018, Paris, FranceGoogle Scholar
- 18.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems (2012)Google Scholar
- 22.Nath, Vishwesh, et al.,: SHARD: spherical harmonic-based robust outlier detection for HARDI methods. In: Medical Imaging 2018: Image Processing. Vol. 10574. International Society for Optics and Photonics (2018)Google Scholar
- 24.Li, S., et al.: A discriminative null space based deep learning approach for person re-identification. In: 2016 4th International Conference on Cloud Computing and Intelligence Systems (CCIS). IEEE (2016)Google Scholar
- 26.Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning-lecture 6a-overview of mini-batch gradient descent. Coursera Lecture slides (2012)Google Scholar
- 27.Blaber, J., Schilling, K., Landman, B.: (2018, March 6). justinblaberdwmri visualizer: First release of dwmri\(\_\)visualizer (Version v1.0.0). Zenodo. https://doi.org/10.5281/zenodo.1191107