Hao Song1, Dan Ruan2, Wenyang Liu2, V Andrew Stenger3, Rolf Pohmann4, Maria A Fernández-Seara5, Tejas Nair6, Sungkyu Jung7, Jingqin Luo8, Yuichi Motai9, Jingfei Ma1, John D Hazle1, H Michael Gach10. 1. Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, 77030, USA. 2. Departments of Radiation Oncology, Biomedical Physics and Bioengineering, UCLA, Los Angeles, CA, 90095, USA. 3. Department of Medicine, University of Hawai'i at Manoa, Honolulu, HI, 96813, USA. 4. High-Field Magnetic Resonance Center, Max Planck Institute for Biological Cybernetics, 72076, Tubingen, Germany. 5. Department of Radiology, University of Navarra Hospital, 31008, Pamplona, Spain. 6. DMC R&D Center, Samsung Electronics Inc., Seocho-gu, 06765, Seoul, Korea. 7. Department of Statistics, University of Pittsburgh, Pittsburgh, PA, 15213, USA. 8. Department of Surgery, Washington University in St. Louis, St. Louis, MO, 63110, USA. 9. Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA, 23284, USA. 10. Departments of Radiation Oncology and Radiology, Washington University, St. Louis, MO, 63110, USA.
Abstract
PURPOSE: Respiratory motion prediction using an artificial neural network (ANN) was integrated with pseudocontinuous arterial spin labeling (pCASL) MRI to allow free-breathing perfusion measurements in the kidney. In this study, we evaluated the performance of the ANN to accurately predict the location of the kidneys during image acquisition. METHODS: A pencil-beam navigator was integrated with a pCASL sequence to measure lung/diaphragm motion during ANN training and the pCASL transit delay. The ANN algorithm ran concurrently in the background to predict organ location during the 0.7-s 15-slice acquisition based on the navigator data. The predictions were supplied to the pulse sequence to prospectively adjust the axial slice acquisition to match the predicted organ location. Additional navigators were acquired immediately after the multislice acquisition to assess the performance and accuracy of the ANN. The technique was tested in eight healthy volunteers. RESULTS: The root-mean-square error (RMSE) and mean absolute error (MAE) for the eight volunteers were 1.91 ± 0.17 mm and 1.43 ± 0.17 mm, respectively, for the ANN. The RMSE increased with transit delay. The MAE typically increased from the first to last prediction in the image acquisition. The overshoot was 23.58% ± 3.05% using the target prediction accuracy of ± 1 mm. CONCLUSION: Respiratory motion prediction with prospective motion correction was successfully demonstrated for free-breathing perfusion MRI of the kidney. The method serves as an alternative to multiple breathholds and requires minimal effort from the patient.
PURPOSE: Respiratory motion prediction using an artificial neural network (ANN) was integrated with pseudocontinuous arterial spin labeling (pCASL) MRI to allow free-breathing perfusion measurements in the kidney. In this study, we evaluated the performance of the ANN to accurately predict the location of the kidneys during image acquisition. METHODS: A pencil-beam navigator was integrated with a pCASL sequence to measure lung/diaphragm motion during ANN training and the pCASL transit delay. The ANN algorithm ran concurrently in the background to predict organ location during the 0.7-s 15-slice acquisition based on the navigator data. The predictions were supplied to the pulse sequence to prospectively adjust the axial slice acquisition to match the predicted organ location. Additional navigators were acquired immediately after the multislice acquisition to assess the performance and accuracy of the ANN. The technique was tested in eight healthy volunteers. RESULTS: The root-mean-square error (RMSE) and mean absolute error (MAE) for the eight volunteers were 1.91 ± 0.17 mm and 1.43 ± 0.17 mm, respectively, for the ANN. The RMSE increased with transit delay. The MAE typically increased from the first to last prediction in the image acquisition. The overshoot was 23.58% ± 3.05% using the target prediction accuracy of ± 1 mm. CONCLUSION: Respiratory motion prediction with prospective motion correction was successfully demonstrated for free-breathing perfusion MRI of the kidney. The method serves as an alternative to multiple breathholds and requires minimal effort from the patient.
Authors: Marica Cutajar; David L Thomas; Tina Banks; Christopher A Clark; Xavier Golay; Isky Gordon Journal: MAGMA Date: 2012-01-13 Impact factor: 2.310
Authors: Philip M Robson; Ananth J Madhuranthakam; Weiying Dai; Ivan Pedrosa; Neil M Rofsky; David C Alsop Journal: Magn Reson Med Date: 2009-06 Impact factor: 4.668
Authors: Isabell K Bones; Anita A Harteveld; Suzanne L Franklin; Matthias J P van Osch; Jeroen Hendrikse; Chrit T W Moonen; Clemens Bos; Marijn van Stralen Journal: Magn Reson Med Date: 2019-03-18 Impact factor: 4.668
Authors: Markus Reischl; Mazin Jouda; Neil MacKinnon; Erwin Fuhrer; Natalia Bakhtina; Andreas Bartschat; Ralf Mikut; Jan G Korvink Journal: PLoS Comput Biol Date: 2019-12-19 Impact factor: 4.475
Authors: Fabio Nery; Charlotte E Buchanan; Anita A Harteveld; Aghogho Odudu; Octavia Bane; Eleanor F Cox; Katja Derlin; H Michael Gach; Xavier Golay; Marcel Gutberlet; Christoffer Laustsen; Alexandra Ljimani; Ananth J Madhuranthakam; Ivan Pedrosa; Pottumarthi V Prasad; Philip M Robson; Kanishka Sharma; Steven Sourbron; Manuel Taso; David L Thomas; Danny J J Wang; Jeff L Zhang; David C Alsop; Sean B Fain; Susan T Francis; María A Fernández-Seara Journal: MAGMA Date: 2019-12-12 Impact factor: 2.533