Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network. Haji-Valizadeh, H., Shen, D., Avery, R. J., Serhal, A. M., Schiffers, F. A., Katsaggelos, A. K., Cossairt, O. S., & Kim, D. Radiology: Cardiothoracic Imaging, 2(3):e190205, jun, 2020. Paper doi abstract bibtex Purpose: To implement an integrated reconstruction pipeline including a graphics processing unit (GPU)–based convolutional neural network (CNN) architecture and test whether it reconstructs four-dimensional non-Cartesian, non–contrast material–enhanced MR angiographic k-space data faster than a central processing unit (CPU)–based compressed sensing (CS) reconstruction pipeline, without significant losses in data fidelity, summed visual score (SVS), or arterial vessel–diameter measurements. Materials and Methods: Raw k-space data of 24 patients (18 men and six women; mean age, 56.8 years 6 11.8 [standard deviation]) suspected of having thoracic aortic disease were used to evaluate the proposed reconstruction pipeline derived from an open-source threedimensional CNN. For training, 4800 zero-filled images and the corresponding CS-reconstructed images from 10 patients were used as input-output pairs. For testing, 6720 zero-filled images from 14 different patients were used as inputs to a trained CNN. Metrics for evaluating the agreement between the CNN and CS images included reconstruction times, structural similarity index (SSIM) and normalized root-mean-square error (NRMSE), SVS (3 = nondiagnostic, 9 = clinically acceptable, 15 = excellent), and vessel diameters. Results: The mean reconstruction time was 65 times and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds 6 40.5 and 204.9 seconds 6 40.5), respectively, than for CS (14 152.3 seconds 6 1708.6) (P, .001). Compared with CS as practical ground truth, CNNs produced high data fidelity (SSIM = 0.94 6 0.02, NRMSE = 2.8% 6 0.4) and not significantly different (P = .25) SVS and aortic diameters, except at one out of seven locations, where the percentage difference was only 3% (ie, clinically irrelevant). Conclusion: The proposed integrated reconstruction pipeline including a CNN architecture is capable of rapidly reconstructing timeresolved volumetric cardiovascular MRI k-space data, without a significant loss in data quality, thereby supporting clinical translation of said non–contrast-enhanced MR angiograms.
@article{Hassan2020,
abstract = {Purpose: To implement an integrated reconstruction pipeline including a graphics processing unit (GPU)–based convolutional neural network (CNN) architecture and test whether it reconstructs four-dimensional non-Cartesian, non–contrast material–enhanced MR angiographic k-space data faster than a central processing unit (CPU)–based compressed sensing (CS) reconstruction pipeline, without significant losses in data fidelity, summed visual score (SVS), or arterial vessel–diameter measurements. Materials and Methods: Raw k-space data of 24 patients (18 men and six women; mean age, 56.8 years 6 11.8 [standard deviation]) suspected of having thoracic aortic disease were used to evaluate the proposed reconstruction pipeline derived from an open-source threedimensional CNN. For training, 4800 zero-filled images and the corresponding CS-reconstructed images from 10 patients were used as input-output pairs. For testing, 6720 zero-filled images from 14 different patients were used as inputs to a trained CNN. Metrics for evaluating the agreement between the CNN and CS images included reconstruction times, structural similarity index (SSIM) and normalized root-mean-square error (NRMSE), SVS (3 = nondiagnostic, 9 = clinically acceptable, 15 = excellent), and vessel diameters. Results: The mean reconstruction time was 65 times and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds 6 40.5 and 204.9 seconds 6 40.5), respectively, than for CS (14 152.3 seconds 6 1708.6) (P, .001). Compared with CS as practical ground truth, CNNs produced high data fidelity (SSIM = 0.94 6 0.02, NRMSE = 2.8% 6 0.4) and not significantly different (P = .25) SVS and aortic diameters, except at one out of seven locations, where the percentage difference was only 3% (ie, clinically irrelevant). Conclusion: The proposed integrated reconstruction pipeline including a CNN architecture is capable of rapidly reconstructing timeresolved volumetric cardiovascular MRI k-space data, without a significant loss in data quality, thereby supporting clinical translation of said non–contrast-enhanced MR angiograms.},
author = {Haji-Valizadeh, Hassan and Shen, Daming and Avery, Ryan J. and Serhal, Ali M. and Schiffers, Florian A. and Katsaggelos, Aggelos K. and Cossairt, Oliver S. and Kim, Daniel},
doi = {10.1148/ryct.2020190205},
issn = {2638-6135},
journal = {Radiology: Cardiothoracic Imaging},
month = {jun},
number = {3},
pages = {e190205},
title = {{Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network}},
url = {http://pubs.rsna.org/doi/10.1148/ryct.2020190205},
volume = {2},
year = {2020}
}
Downloads: 0
{"_id":"fvkYXrHfsCj3zkmey","bibbaseid":"hajivalizadeh-shen-avery-serhal-schiffers-katsaggelos-cossairt-kim-rapidreconstructionoffourdimensionalmrangiographyofthethoracicaortausingaconvolutionalneuralnetwork-2020","author_short":["Haji-Valizadeh, H.","Shen, D.","Avery, R. J.","Serhal, A. M.","Schiffers, F. A.","Katsaggelos, A. K.","Cossairt, O. S.","Kim, D."],"bibdata":{"bibtype":"article","type":"article","abstract":"Purpose: To implement an integrated reconstruction pipeline including a graphics processing unit (GPU)–based convolutional neural network (CNN) architecture and test whether it reconstructs four-dimensional non-Cartesian, non–contrast material–enhanced MR angiographic k-space data faster than a central processing unit (CPU)–based compressed sensing (CS) reconstruction pipeline, without significant losses in data fidelity, summed visual score (SVS), or arterial vessel–diameter measurements. Materials and Methods: Raw k-space data of 24 patients (18 men and six women; mean age, 56.8 years 6 11.8 [standard deviation]) suspected of having thoracic aortic disease were used to evaluate the proposed reconstruction pipeline derived from an open-source threedimensional CNN. For training, 4800 zero-filled images and the corresponding CS-reconstructed images from 10 patients were used as input-output pairs. For testing, 6720 zero-filled images from 14 different patients were used as inputs to a trained CNN. Metrics for evaluating the agreement between the CNN and CS images included reconstruction times, structural similarity index (SSIM) and normalized root-mean-square error (NRMSE), SVS (3 = nondiagnostic, 9 = clinically acceptable, 15 = excellent), and vessel diameters. Results: The mean reconstruction time was 65 times and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds 6 40.5 and 204.9 seconds 6 40.5), respectively, than for CS (14 152.3 seconds 6 1708.6) (P, .001). Compared with CS as practical ground truth, CNNs produced high data fidelity (SSIM = 0.94 6 0.02, NRMSE = 2.8% 6 0.4) and not significantly different (P = .25) SVS and aortic diameters, except at one out of seven locations, where the percentage difference was only 3% (ie, clinically irrelevant). Conclusion: The proposed integrated reconstruction pipeline including a CNN architecture is capable of rapidly reconstructing timeresolved volumetric cardiovascular MRI k-space data, without a significant loss in data quality, thereby supporting clinical translation of said non–contrast-enhanced MR angiograms.","author":[{"propositions":[],"lastnames":["Haji-Valizadeh"],"firstnames":["Hassan"],"suffixes":[]},{"propositions":[],"lastnames":["Shen"],"firstnames":["Daming"],"suffixes":[]},{"propositions":[],"lastnames":["Avery"],"firstnames":["Ryan","J."],"suffixes":[]},{"propositions":[],"lastnames":["Serhal"],"firstnames":["Ali","M."],"suffixes":[]},{"propositions":[],"lastnames":["Schiffers"],"firstnames":["Florian","A."],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]},{"propositions":[],"lastnames":["Cossairt"],"firstnames":["Oliver","S."],"suffixes":[]},{"propositions":[],"lastnames":["Kim"],"firstnames":["Daniel"],"suffixes":[]}],"doi":"10.1148/ryct.2020190205","issn":"2638-6135","journal":"Radiology: Cardiothoracic Imaging","month":"jun","number":"3","pages":"e190205","title":"Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network","url":"http://pubs.rsna.org/doi/10.1148/ryct.2020190205","volume":"2","year":"2020","bibtex":"@article{Hassan2020,\nabstract = {Purpose: To implement an integrated reconstruction pipeline including a graphics processing unit (GPU)–based convolutional neural network (CNN) architecture and test whether it reconstructs four-dimensional non-Cartesian, non–contrast material–enhanced MR angiographic k-space data faster than a central processing unit (CPU)–based compressed sensing (CS) reconstruction pipeline, without significant losses in data fidelity, summed visual score (SVS), or arterial vessel–diameter measurements. Materials and Methods: Raw k-space data of 24 patients (18 men and six women; mean age, 56.8 years 6 11.8 [standard deviation]) suspected of having thoracic aortic disease were used to evaluate the proposed reconstruction pipeline derived from an open-source threedimensional CNN. For training, 4800 zero-filled images and the corresponding CS-reconstructed images from 10 patients were used as input-output pairs. For testing, 6720 zero-filled images from 14 different patients were used as inputs to a trained CNN. Metrics for evaluating the agreement between the CNN and CS images included reconstruction times, structural similarity index (SSIM) and normalized root-mean-square error (NRMSE), SVS (3 = nondiagnostic, 9 = clinically acceptable, 15 = excellent), and vessel diameters. Results: The mean reconstruction time was 65 times and 69 times shorter for the CPU-based and GPU-based CNN pipelines (216.6 seconds 6 40.5 and 204.9 seconds 6 40.5), respectively, than for CS (14 152.3 seconds 6 1708.6) (P, .001). Compared with CS as practical ground truth, CNNs produced high data fidelity (SSIM = 0.94 6 0.02, NRMSE = 2.8% 6 0.4) and not significantly different (P = .25) SVS and aortic diameters, except at one out of seven locations, where the percentage difference was only 3% (ie, clinically irrelevant). Conclusion: The proposed integrated reconstruction pipeline including a CNN architecture is capable of rapidly reconstructing timeresolved volumetric cardiovascular MRI k-space data, without a significant loss in data quality, thereby supporting clinical translation of said non–contrast-enhanced MR angiograms.},\nauthor = {Haji-Valizadeh, Hassan and Shen, Daming and Avery, Ryan J. and Serhal, Ali M. and Schiffers, Florian A. and Katsaggelos, Aggelos K. and Cossairt, Oliver S. and Kim, Daniel},\ndoi = {10.1148/ryct.2020190205},\nissn = {2638-6135},\njournal = {Radiology: Cardiothoracic Imaging},\nmonth = {jun},\nnumber = {3},\npages = {e190205},\ntitle = {{Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network}},\nurl = {http://pubs.rsna.org/doi/10.1148/ryct.2020190205},\nvolume = {2},\nyear = {2020}\n}\n","author_short":["Haji-Valizadeh, H.","Shen, D.","Avery, R. J.","Serhal, A. M.","Schiffers, F. A.","Katsaggelos, A. K.","Cossairt, O. S.","Kim, D."],"key":"Hassan2020","id":"Hassan2020","bibbaseid":"hajivalizadeh-shen-avery-serhal-schiffers-katsaggelos-cossairt-kim-rapidreconstructionoffourdimensionalmrangiographyofthethoracicaortausingaconvolutionalneuralnetwork-2020","role":"author","urls":{"Paper":"http://pubs.rsna.org/doi/10.1148/ryct.2020190205"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["rapid","reconstruction","four","dimensional","angiography","thoracic","aorta","using","convolutional","neural","network","haji-valizadeh","shen","avery","serhal","schiffers","katsaggelos","cossairt","kim"],"title":"Rapid Reconstruction of Four-dimensional MR Angiography of the Thoracic Aorta Using a Convolutional Neural Network","year":2020}