Daniel Polak1,2,3, Stephen Cauley2,4,5, Berkin Bilgic2,4,5, Enhao Gong6, Peter Bachert1,7, Elfar Adalsteinsson8, Kawin Setsompop2,4,5. 1. Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany. 2. Department of Radiology, A. A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, USA. 3. Siemens Healthcare GmbH, Erlangen, Germany. 4. Harvard Medical School, Boston, MA, USA. 5. Harvard-MIT Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, USA. 6. Subtle Medical Inc, Menlo Park, CA, USA. 7. Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany. 8. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA.
Abstract
PURPOSE: To improve the image quality of highly accelerated multi-channel MRI data by learning a joint variational network that reconstructs multiple clinical contrasts jointly. METHODS: Data from our multi-contrast acquisition were embedded into the variational network architecture where shared anatomical information is exchanged by mixing the input contrasts. Complementary k-space sampling across imaging contrasts and Bunch-Phase/Wave-Encoding were used for data acquisition to improve the reconstruction at high accelerations. At 3T, our joint variational network approach across T1w, T2w and T2-FLAIR-weighted brain scans was tested for retrospective under-sampling at R = 6 (2D) and R = 4 × 4 (3D) acceleration. Prospective acceleration was also performed for 3D data where the combined acquisition time for whole brain coverage at 1 mm isotropic resolution across three contrasts was less than 3 min. RESULTS: Across all test datasets, our joint multi-contrast network better preserved fine anatomical details with reduced image-blurring when compared to the corresponding single-contrast reconstructions. Improvement in image quality was also obtained through complementary k-space sampling and Bunch-Phase/Wave-Encoding where the synergistic combination yielded the overall best performance as evidenced by exemplary slices and quantitative error metrics. CONCLUSION: By leveraging shared anatomical structures across the jointly reconstructed scans, our joint multi-contrast approach learnt more efficient regularizers, which helped to retain natural image appearance and avoid over-smoothing. When synergistically combined with advanced encoding techniques, the performance was further improved, enabling up to R = 16-fold acceleration with good image quality. This should help pave the way to very rapid high-resolution brain exams.
PURPOSE: To improve the image quality of highly accelerated multi-channel MRI data by learning a joint variational network that reconstructs multiple clinical contrasts jointly. METHODS: Data from our multi-contrast acquisition were embedded into the variational network architecture where shared anatomical information is exchanged by mixing the input contrasts. Complementary k-space sampling across imaging contrasts and Bunch-Phase/Wave-Encoding were used for data acquisition to improve the reconstruction at high accelerations. At 3T, our joint variational network approach across T1w, T2w and T2-FLAIR-weighted brain scans was tested for retrospective under-sampling at R = 6 (2D) and R = 4 × 4 (3D) acceleration. Prospective acceleration was also performed for 3D data where the combined acquisition time for whole brain coverage at 1 mm isotropic resolution across three contrasts was less than 3 min. RESULTS: Across all test datasets, our joint multi-contrast network better preserved fine anatomical details with reduced image-blurring when compared to the corresponding single-contrast reconstructions. Improvement in image quality was also obtained through complementary k-space sampling and Bunch-Phase/Wave-Encoding where the synergistic combination yielded the overall best performance as evidenced by exemplary slices and quantitative error metrics. CONCLUSION: By leveraging shared anatomical structures across the jointly reconstructed scans, our joint multi-contrast approach learnt more efficient regularizers, which helped to retain natural image appearance and avoid over-smoothing. When synergistically combined with advanced encoding techniques, the performance was further improved, enabling up to R = 16-fold acceleration with good image quality. This should help pave the way to very rapid high-resolution brain exams.
Authors: Berkin Bilgic; Borjan A Gagoski; Stephen F Cauley; Audrey P Fan; Jonathan R Polimeni; P Ellen Grant; Lawrence L Wald; Kawin Setsompop Journal: Magn Reson Med Date: 2014-07-01 Impact factor: 4.668
Authors: Daniel Polak; Stephen Cauley; Susie Y Huang; Maria Gabriela Longo; John Conklin; Berkin Bilgic; Ned Ohringer; Esther Raithel; Peter Bachert; Lawrence L Wald; Kawin Setsompop Journal: J Magn Reson Imaging Date: 2019-02-08 Impact factor: 4.813
Authors: Martin Uecker; Peng Lai; Mark J Murphy; Patrick Virtue; Michael Elad; John M Pauly; Shreyas S Vasanawala; Michael Lustig Journal: Magn Reson Med Date: 2014-03 Impact factor: 4.668
Authors: Daniel Polak; Daniel Nicolas Splitthoff; Bryan Clifford; Wei-Ching Lo; Susie Y Huang; John Conklin; Lawrence L Wald; Kawin Setsompop; Stephen Cauley Journal: Magn Reson Med Date: 2021-08-13 Impact factor: 4.668
Authors: Harriet Hobday; James H Cole; Ryan A Stanyard; Richard E Daws; Vincent Giampietro; Owen O'Daly; Robert Leech; František Váša Journal: Sci Rep Date: 2022-07-14 Impact factor: 4.996
Authors: František Váša; Harriet Hobday; Ryan A Stanyard; Richard E Daws; Vincent Giampietro; Owen O'Daly; David J Lythgoe; Jakob Seidlitz; Stefan Skare; Steven C R Williams; Andre F Marquand; Robert Leech; James H Cole Journal: Hum Brain Mapp Date: 2021-12-24 Impact factor: 5.399