Synopsis

Keywords: Image acquisition: Machine learning

This presentation delves into the innovative utilization of deep learning methodologies in crafting MRI sequences. Firstly, the talk addresses the automation of designing specific elements within MRI sequences, such as RF pulse design and gradient waveform design. Then, we will continue to explore how deep learning facilitates the timing of MRI sequence blocks and k-space acquisition order. Related to these topics, the presentation will cover the co-design paradigms of acquisition and reconstruction to achieve optimal performance in final outcomes. Lastly, development of novel MRI sequences targets for specific or even unknown contrasts will be explained.

This presentation delves into the innovative utilization of deep learning methodologies in crafting MRI sequences. Firstly, the talk addresses the automation of designing specific elements within MRI sequences, such as RF pulse design and gradient waveform design. Then, we will continue to explore how deep learning facilitates the timing of MRI sequence blocks and k-space acquisition order. Related to these topics, the presentation will cover the co-design paradigms of acquisition and reconstruction to achieve optimal performance in final outcomes. Lastly, development of novel MRI sequences targets for specific or even unknown contrasts. Attendees will gain insights into the principles, methodologies, and future directions of this burgeoning field, fostering interdisciplinary collaboration and catalyzing further innovation in MRI imaging.

Acknowledgements

No acknowledgement found.

References

· P. K. Lee, L. E. Watkins, T. I. Anderson et al., "Flexible and efficient optimization of quantitative sequences using automatic differentiation of Bloch simulations," Magn. Reson. Med., vol. 82, no. 4, pp. 1438-1451, 2018. · B. Zhu, J. Liu, N. Koonjoo et al., "AUTOmated pulse SEQuence generation (AUTOSEQ) using Bayesian reinforcement learning in an MRI physics simulation environment," in Proceedings of the International Society for Magnetic Resonance in Medicine 26. · D. Shin, S. Ji, D. Lee et al., “Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse Using Root-Flipping: DeepRFSLR,” IEEE Trans. Med. Imaging, vol. 39, no. 12, pp. 4391-4400, 2020. · S. P. Jordan, S. Hu, I. Rozada et al., “Automated design of pulse sequences for magnetic resonance fingerprinting using physics-inspired optimization,” Proc. Natl. Acad. Sci. U. S. A., vol. 118, no. 40, pp. e2020516118, 2021. · D. Shin, Y. Kim, C. Oh et al., “Deep reinforcement learning-designed radiofrequency waveform in MRI,” Nat. Mach. Intell., vol. 3, no. 11, pp. 985-994, 2021. · M. S. Vinding, C. S. Aigner, S. Schmitter, and T. E. Lund, “DeepControl: 2DRF pulses facilitating B1+ inhomogeneity and B0 off-resonance compensation in vivo at 7 T,” Magn. Reson. Med., vol. 85, no. 6, pp. 3308-3317, 2021. · T. Luo, D. C. Noll, J. A. Fessler, and J.-F. Nielsen, “Joint Design of RF and Gradient Waveforms via Auto-differentiation for 3D Tailored Excitation in MRI,” IEEE Trans. Med. Imaging, vol. 40, no. 12, pp. 3305-3314, 2021. · A. Loktyushin, K. Herz, N. Dang et al., “MRzero - Automated discovery of MRI sequences using supervised learning,” Magn. Reson. Med., vol. 86, no. 2, pp. 709-724, 2021. · W. Peng, L. Feng, G. Zhao, and F. Liu, "Learning optimal k-space acquisition and reconstruction using physics-informed neural networks." in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022, pp. 20794-20803. · G. Wang, T. Luo, J.-F. Nielsen et al., “B-Spline Parameterized Joint Optimization of Reconstruction and K-Space Trajectories (BJORK) for Accelerated 2D MRI,” IEEE Trans. Med. Imaging, vol. 41, no. 9, pp. 2318-2330, 2022. · O. Perlman, B. Zhu, M. Zaiss et al., “An end-to-end AI-based framework for automated discovery of rapid CEST/MT MRI acquisition protocols and molecular parameter quantification (AutoCEST),” Magn. Reson. Med., vol. 87, no. 6, pp. 2792-2810, 2022. · S. Walker-Samuel, "Using deep reinforcement learning to actively, adaptively and autonomously control a simulated MRI scanner," in Proceedings of the International Society for Magnetic Resonance in Medicine 27. · F. Glang, S. Mueller, K. Herz et al., "MR-double-zero – Proof-of-concept for a framework to autonomously discover MRI contrasts," J. Magn. Reson., vol. 341, p. 107237, 2022. · V. Somai, F. Kreis, A. Gaunt et al., "Genetic algorithm-based optimization of pulse sequences," Magn. Reson. Med., vol. 87, no. 5, pp. 2130-2144, 2022.