Synthesizing Dynamic MRI Using Long-Term Recurrent Convolutional Networks
A method is proposed for converting raw ultrasound signals of respiratory organ motion into high frame rate dynamic MRI using a long-term recurrent convolutional neural network. Ultrasound signals were acquired using a single-element transducer, referred to here as ‘organ-configuration motion’ (OCM) sensor, while sagittal MR images were simultaneously acquired. Both streams of data were used for training a cascade of convolutional layers, to extract relevant features from raw ultrasound, followed by a recurrent neural network, to learn its temporal dynamics. The network was trained with MR images on the output, and was employed to predict MR images at a temporal resolution of 100 frames per second, based on ultrasound input alone, without any further MR scanner input. The method was validated on 7 subjects.
Support from grants NIH P41EB015898, R03EB025546, R01CA149342, and R21EB019500 is duly acknowledged. GPU hardware was generously donated by NVIDIA Corporation.
- 3.Preiswerk, F., et al.: Hybrid MRI-ultrasound acquisitions, and scannerless real-time imaging. Magn. Reson. Med. (2016)Google Scholar
- 4.Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. CoRR abs/1411.4389 (2014)Google Scholar
- 8.Preiswerk, F., et al.: Hybrid Utrasound and MRI Acquisitions for High-Speed Imaging of Respiratory Organ Motion. In: Navab, Nassir, Hornegger, Joachim, Wells, William M., Frangi, Alejandro F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 315–322. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24553-9_39CrossRefGoogle Scholar