MR‐based synthetic CT generation using a deep convolutional neural network method

Purpose Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR‐only radiotherapy also simplifies clinical workflow and avoids unc...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Medical physics (Lancaster) Ročník 44; číslo 4; s. 1408 - 1419
Hlavný autor: Han, Xiao
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States 01.04.2017
Predmet:
ISSN:0094-2405, 2473-4209, 2473-4209
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Purpose Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR‐only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT‐equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR‐based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET‐MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images. Methods The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end‐to‐end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1‐weighted MR images are used as experimental data and a sixfold cross‐validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel‐by‐voxel basis. Comparison is also made with respect to an atlas‐based approach that involves deformable atlas registration and patch‐based atlas fusion. Results The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas‐based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas‐based approach. Conclusions A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single‐sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas‐based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi‐sequence MR images.
AbstractList Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR-only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT-equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR-based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET-MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images. The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end-to-end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1-weighted MR images are used as experimental data and a sixfold cross-validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel-by-voxel basis. Comparison is also made with respect to an atlas-based approach that involves deformable atlas registration and patch-based atlas fusion. The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas-based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas-based approach. A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single-sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas-based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi-sequence MR images.
Purpose Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR‐only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT‐equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR‐based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET‐MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images. Methods The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end‐to‐end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1‐weighted MR images are used as experimental data and a sixfold cross‐validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel‐by‐voxel basis. Comparison is also made with respect to an atlas‐based approach that involves deformable atlas registration and patch‐based atlas fusion. Results The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas‐based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas‐based approach. Conclusions A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single‐sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas‐based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi‐sequence MR images.
Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR-only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT-equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR-based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET-MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images.PURPOSEInterests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR-only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT-equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR-based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET-MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images.The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end-to-end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1-weighted MR images are used as experimental data and a sixfold cross-validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel-by-voxel basis. Comparison is also made with respect to an atlas-based approach that involves deformable atlas registration and patch-based atlas fusion.METHODSThe proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end-to-end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1-weighted MR images are used as experimental data and a sixfold cross-validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel-by-voxel basis. Comparison is also made with respect to an atlas-based approach that involves deformable atlas registration and patch-based atlas fusion.The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas-based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas-based approach.RESULTSThe proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas-based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas-based approach.A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single-sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas-based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi-sequence MR images.CONCLUSIONSA DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single-sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas-based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi-sequence MR images.
Author Han, Xiao
Author_xml – sequence: 1
  givenname: Xiao
  surname: Han
  fullname: Han, Xiao
  email: xiao.han@elekta.com
  organization: Elekta Inc
BackLink https://www.ncbi.nlm.nih.gov/pubmed/28192624$$D View this record in MEDLINE/PubMed
BookMark eNp1kElOwzAYhS1URFtA4gTISzYpHjMsUcUkFYEY1pHj_GkDiR3shKo7jsAZOQmlLSAhWL3F-95bfEPUM9YAQgeUjCgh7LhuRpRRKbfQgImIB4KRpIcGhCQiYILIPhp6_0gICbkkO6jPYpqwkIkBuru6fX99y5SHHPuFaWfQlhqP7_EUDDjVltbgzpdmihXOARqsrXmxVfdZqAob6Nwq2rl1T7iGdmbzPbRdqMrD_iZ30cPZ6f34Iphcn1-OTyaB5nEkg4KLmEAhIh0TrcJCK8lpSDMJtABFKKUZ51xxwqiKuNY5lRFVIgp5BrFIcr6Ljta_jbPPHfg2rUuvoaqUAdv5lMZhzBMpuFiihxu0y2rI08aVtXKL9EvEz5d21nsHxTdCSfrpOK2bdOV4iY5-obpsV6Zap8rqr0GwHszLChb_HqdXN2v-A6V0i-0
CitedBy_id crossref_primary_10_1016_j_meddos_2018_06_008
crossref_primary_10_1088_1361_6560_ab0dc0
crossref_primary_10_1002_acm2_13775
crossref_primary_10_1016_j_compbiomed_2022_105948
crossref_primary_10_1016_j_ejmp_2017_09_132
crossref_primary_10_1016_j_engappai_2023_107334
crossref_primary_10_1088_1757_899X_914_1_012030
crossref_primary_10_1007_s40042_021_00291_z
crossref_primary_10_1186_s41747_019_0143_0
crossref_primary_10_14338_IJPT_D_20_00020_1
crossref_primary_10_1097_HP_0000000000002027
crossref_primary_10_1016_j_media_2019_101546
crossref_primary_10_1088_2057_1976_acea27
crossref_primary_10_1016_j_neuroimage_2020_117221
crossref_primary_10_1093_jrr_rrz030
crossref_primary_10_1155_2020_8279342
crossref_primary_10_1002_mp_15174
crossref_primary_10_1002_hbm_24210
crossref_primary_10_1007_s12149_021_01697_2
crossref_primary_10_1016_j_compmedimag_2024_102344
crossref_primary_10_1055_s_0045_1802660
crossref_primary_10_1088_1361_6560_ab8bf2
crossref_primary_10_1016_j_phro_2021_05_001
crossref_primary_10_1038_s41598_020_64842_3
crossref_primary_10_1186_s12880_024_01242_3
crossref_primary_10_1007_s13246_020_00933_9
crossref_primary_10_1016_j_phro_2021_05_007
crossref_primary_10_1038_s41598_025_05323_3
crossref_primary_10_1155_2021_2254594
crossref_primary_10_1016_j_ejrad_2024_111587
crossref_primary_10_1148_ryai_2021200276
crossref_primary_10_1007_s11042_024_18759_y
crossref_primary_10_1007_s13139_017_0504_7
crossref_primary_10_1016_j_media_2018_03_011
crossref_primary_10_3389_fphy_2018_00051
crossref_primary_10_3389_fonc_2020_01715
crossref_primary_10_1109_ACCESS_2024_3377428
crossref_primary_10_1109_TRPMS_2023_3241102
crossref_primary_10_1038_s41598_019_52262_x
crossref_primary_10_3389_fgene_2019_01110
crossref_primary_10_1016_j_ejmp_2020_10_023
crossref_primary_10_1016_j_phro_2020_12_007
crossref_primary_10_1007_s13534_024_00430_y
crossref_primary_10_1016_j_radonc_2020_09_008
crossref_primary_10_1007_s11060_022_04068_7
crossref_primary_10_3390_rs15071906
crossref_primary_10_3389_fneur_2024_1383773
crossref_primary_10_3390_diagnostics12040816
crossref_primary_10_1088_1361_6560_ab436a
crossref_primary_10_1145_3625227
crossref_primary_10_1016_j_phro_2020_04_002
crossref_primary_10_1088_1361_6560_ad611a
crossref_primary_10_1002_mp_15073
crossref_primary_10_1109_TUFFC_2020_2983099
crossref_primary_10_1016_j_ijrobp_2020_05_006
crossref_primary_10_1002_mp_16048
crossref_primary_10_1016_j_radonc_2020_11_027
crossref_primary_10_3389_fonc_2017_00315
crossref_primary_10_1007_s13246_024_01457_2
crossref_primary_10_1002_acm2_13327
crossref_primary_10_1016_j_media_2025_103454
crossref_primary_10_1088_1361_6560_ab6f51
crossref_primary_10_1007_s11036_020_01678_1
crossref_primary_10_3389_fnins_2021_655019
crossref_primary_10_1109_JBHI_2019_2927368
crossref_primary_10_1109_TRPMS_2024_3397318
crossref_primary_10_1016_j_cmpb_2022_106932
crossref_primary_10_1016_j_ijrobp_2018_06_024
crossref_primary_10_1007_s10278_021_00551_1
crossref_primary_10_1088_1361_6560_abf1bb
crossref_primary_10_1007_s10278_020_00361_x
crossref_primary_10_1016_j_ymeth_2020_10_004
crossref_primary_10_1016_j_engappai_2023_106337
crossref_primary_10_1109_JSEN_2021_3050618
crossref_primary_10_1088_1361_6560_aca38a
crossref_primary_10_3389_frai_2022_780405
crossref_primary_10_3390_s25061814
crossref_primary_10_3233_JIFS_179575
crossref_primary_10_1016_j_sigpro_2025_110181
crossref_primary_10_1111_echo_14674
crossref_primary_10_1109_TUFFC_2022_3198522
crossref_primary_10_1016_j_phro_2025_100764
crossref_primary_10_1016_j_bspc_2024_106819
crossref_primary_10_1016_j_cmpb_2024_108578
crossref_primary_10_1007_s13246_019_00822_w
crossref_primary_10_1088_1361_6560_aaf5e0
crossref_primary_10_1016_j_neunet_2020_05_001
crossref_primary_10_1088_1361_6560_ab25bc
crossref_primary_10_1109_TRPMS_2018_2868946
crossref_primary_10_1155_2021_4463975
crossref_primary_10_1007_s00259_021_05198_2
crossref_primary_10_1088_1361_6560_ab5c5b
crossref_primary_10_3390_s22020523
crossref_primary_10_1002_mp_14075
crossref_primary_10_1088_1361_6560_ac8d45
crossref_primary_10_3390_cancers14123027
crossref_primary_10_1002_mp_16256
crossref_primary_10_1007_s00234_024_03282_6
crossref_primary_10_1016_j_bspc_2022_104258
crossref_primary_10_1016_j_canrad_2020_01_008
crossref_primary_10_1002_btm2_10494
crossref_primary_10_1002_acm2_70228
crossref_primary_10_1016_j_zemedi_2018_11_002
crossref_primary_10_1002_acm2_13121
crossref_primary_10_1007_s12350_021_02817_1
crossref_primary_10_3390_diagnostics11071194
crossref_primary_10_1016_j_ejmp_2021_03_035
crossref_primary_10_1007_s10278_018_0124_5
crossref_primary_10_3389_fonc_2024_1478148
crossref_primary_10_1002_mp_14180
crossref_primary_10_1002_mp_15150
crossref_primary_10_1002_mp_14062
crossref_primary_10_1109_TMI_2025_3559823
crossref_primary_10_1002_mp_16246
crossref_primary_10_1016_j_ijrobp_2019_08_049
crossref_primary_10_1088_1361_6560_ab23a6
crossref_primary_10_3390_bioengineering12060611
crossref_primary_10_1002_mp_17338
crossref_primary_10_1140_epjp_s13360_024_05660_8
crossref_primary_10_1186_s40658_023_00569_0
crossref_primary_10_1016_j_engappai_2018_11_013
crossref_primary_10_1002_mp_15460
crossref_primary_10_3389_fonc_2020_593381
crossref_primary_10_1016_j_bspc_2024_106294
crossref_primary_10_1007_s00066_024_02328_1
crossref_primary_10_1002_mrm_27134
crossref_primary_10_1002_mp_13047
crossref_primary_10_1002_mp_16556
crossref_primary_10_1002_acm2_13139
crossref_primary_10_1088_1361_6560_aac763
crossref_primary_10_1016_j_zemedi_2020_10_004
crossref_primary_10_1088_1361_6560_ab7d54
crossref_primary_10_1007_s11547_021_01351_x
crossref_primary_10_1097_MD_0000000000023138
crossref_primary_10_1088_1361_6560_ab5b70
crossref_primary_10_1016_j_compbiomed_2018_05_018
crossref_primary_10_1002_ird3_112
crossref_primary_10_1002_mp_15572
crossref_primary_10_1002_mp_16782
crossref_primary_10_1093_bib_bbaa310
crossref_primary_10_1002_mp_16666
crossref_primary_10_1088_2057_1976_ac0501
crossref_primary_10_3389_fneur_2019_00869
crossref_primary_10_3390_jimaging7040066
crossref_primary_10_1042_BSR20180289
crossref_primary_10_1007_s00259_020_05061_w
crossref_primary_10_1016_j_compmedimag_2021_101953
crossref_primary_10_1016_j_ejmp_2021_05_010
crossref_primary_10_1109_JPROC_2019_2936809
crossref_primary_10_1109_TMI_2024_3382043
crossref_primary_10_1038_s41598_018_27742_1
crossref_primary_10_1007_s00066_023_02090_w
crossref_primary_10_1007_s00259_020_04852_5
crossref_primary_10_1016_j_jvcir_2019_102578
crossref_primary_10_1002_mp_13187
crossref_primary_10_1109_TCSVT_2025_3528981
crossref_primary_10_1016_j_cmpb_2022_107001
crossref_primary_10_1002_mrm_28008
crossref_primary_10_3389_fonc_2022_920443
crossref_primary_10_1016_j_ejmp_2021_05_001
crossref_primary_10_1177_13524585211029860
crossref_primary_10_1007_s13246_023_01320_w
crossref_primary_10_1109_TRPMS_2020_3009269
crossref_primary_10_1002_jmri_26712
crossref_primary_10_1155_2020_5193707
crossref_primary_10_3390_app15052311
crossref_primary_10_4103_JCOT_JCOT_3_23
crossref_primary_10_1088_1361_6560_ade220
crossref_primary_10_1007_s00259_019_04380_x
crossref_primary_10_1088_1361_6560_ab1cee
crossref_primary_10_1002_mp_14387
crossref_primary_10_1002_mrm_29684
crossref_primary_10_1002_mp_15479
crossref_primary_10_3233_JIFS_211968
crossref_primary_10_3390_app12178650
crossref_primary_10_1088_1361_6560_abab57
crossref_primary_10_1186_s13014_023_02349_7
crossref_primary_10_3390_diagnostics13243661
crossref_primary_10_1016_j_radonc_2022_08_028
crossref_primary_10_1016_j_compbiomed_2022_105556
crossref_primary_10_1002_acm2_13176
crossref_primary_10_1186_s12880_021_00618_z
crossref_primary_10_1002_mp_15661
crossref_primary_10_1002_mrm_29356
crossref_primary_10_1002_mp_16752
crossref_primary_10_1016_j_ejmp_2021_04_016
crossref_primary_10_1053_j_semnuclmed_2025_01_006
crossref_primary_10_1002_mp_13247
crossref_primary_10_1186_s13014_023_02336_y
crossref_primary_10_1002_ima_70013
crossref_primary_10_1038_s41598_021_81044_7
crossref_primary_10_1088_2057_1976_ad6a62
crossref_primary_10_1007_s12072_021_10229_z
crossref_primary_10_3390_app11041691
crossref_primary_10_1088_1361_6560_aaf0bc
crossref_primary_10_1002_mp_15534
crossref_primary_10_1016_j_artmed_2023_102609
crossref_primary_10_3389_fnins_2022_920981
crossref_primary_10_3389_fonc_2023_1117874
crossref_primary_10_3390_app10113794
crossref_primary_10_3389_fonc_2024_1407016
crossref_primary_10_1016_j_knosys_2025_114491
crossref_primary_10_1016_j_radonc_2020_10_018
crossref_primary_10_1093_jrr_rrz063
crossref_primary_10_1109_JBHI_2019_2912659
crossref_primary_10_1186_s13014_024_02467_w
crossref_primary_10_1007_s11548_022_02732_x
crossref_primary_10_1088_1361_6560_ab857b
crossref_primary_10_1016_j_patrec_2022_04_019
crossref_primary_10_1088_1742_6596_1848_1_012006
crossref_primary_10_1002_mp_13262
crossref_primary_10_1088_2057_1976_ac21aa
crossref_primary_10_1002_mp_13264
crossref_primary_10_1016_j_meddos_2019_01_002
crossref_primary_10_3390_app122211600
crossref_primary_10_1016_j_compbiomed_2023_106738
crossref_primary_10_1016_j_neuroimage_2021_118606
crossref_primary_10_1016_j_ejrad_2020_109487
crossref_primary_10_1016_j_compmedimag_2021_101885
crossref_primary_10_1109_JBHI_2022_3143104
crossref_primary_10_1007_s11633_024_1528_y
crossref_primary_10_1016_j_crmeth_2025_101074
crossref_primary_10_1016_j_ejmp_2023_102544
crossref_primary_10_3389_fonc_2019_00977
crossref_primary_10_1371_journal_pone_0316642
crossref_primary_10_3390_bioengineering10091078
crossref_primary_10_1186_s13014_021_01794_6
crossref_primary_10_1016_j_ijrobp_2019_06_2535
crossref_primary_10_1016_j_dib_2025_111768
crossref_primary_10_1007_s10278_024_01312_6
crossref_primary_10_1016_j_jrras_2022_03_003
crossref_primary_10_1016_j_cmpb_2022_107032
crossref_primary_10_1148_radiol_2020202861
crossref_primary_10_3389_fonc_2022_1086258
crossref_primary_10_1007_s00138_023_01410_5
crossref_primary_10_1109_JBHI_2024_3393870
crossref_primary_10_1007_s11517_024_03035_w
crossref_primary_10_1016_j_ejrad_2025_112310
crossref_primary_10_1148_radiol_2020202747
crossref_primary_10_3390_app12073223
crossref_primary_10_3389_fonc_2019_00964
crossref_primary_10_1088_1361_6560_aba5e9
crossref_primary_10_3389_fnins_2022_1053783
crossref_primary_10_1016_j_radonc_2019_03_026
crossref_primary_10_1002_mp_14534
crossref_primary_10_1002_mp_15986
crossref_primary_10_1007_s00259_020_04746_6
crossref_primary_10_1088_1361_6560_ac0e79
crossref_primary_10_3389_fonc_2021_617681
crossref_primary_10_1016_j_compbiomed_2023_107842
crossref_primary_10_1016_j_jacr_2020_06_033
crossref_primary_10_1038_s41571_020_0417_8
crossref_primary_10_3390_bioengineering10020250
crossref_primary_10_1088_1361_6560_ab41af
crossref_primary_10_1109_TMI_2022_3167808
crossref_primary_10_1016_j_ijrobp_2024_09_046
crossref_primary_10_1016_j_compmedimag_2018_09_004
crossref_primary_10_3389_fphy_2019_00243
crossref_primary_10_1002_jmri_26534
crossref_primary_10_1093_rpd_ncaf043
crossref_primary_10_3390_cancers14246123
crossref_primary_10_1109_RBME_2023_3269776
crossref_primary_10_3390_s22072452
crossref_primary_10_1002_mp_13672
crossref_primary_10_1016_j_bspc_2022_103994
crossref_primary_10_1002_mp_16702
crossref_primary_10_1177_02841851241300616
crossref_primary_10_1002_mp_14758
crossref_primary_10_1038_s41598_024_59014_6
crossref_primary_10_1016_j_phro_2021_10_001
crossref_primary_10_1109_TMI_2019_2935916
crossref_primary_10_3171_2020_4_PEDS20131
crossref_primary_10_1109_JBHI_2023_3308529
crossref_primary_10_1016_j_ijrobp_2021_11_007
crossref_primary_10_1186_s12885_020_6694_x
crossref_primary_10_1186_s40658_021_00426_y
crossref_primary_10_1007_s13534_022_00227_x
crossref_primary_10_1109_TBME_2018_2814538
crossref_primary_10_1016_j_eswa_2021_115008
crossref_primary_10_1002_mp_13583
crossref_primary_10_1002_ima_23169
crossref_primary_10_1016_j_phro_2023_100425
crossref_primary_10_1002_mp_16976
crossref_primary_10_1038_s41598_022_06546_4
crossref_primary_10_1088_1361_6560_ac08b2
crossref_primary_10_1109_TAI_2022_3187388
crossref_primary_10_1016_j_mri_2019_04_002
crossref_primary_10_1016_j_neucom_2021_07_066
crossref_primary_10_1088_2057_1976_ab6e1f
crossref_primary_10_1016_j_semradonc_2023_10_003
crossref_primary_10_1007_s13534_024_00402_2
crossref_primary_10_1109_TCBB_2020_2979841
crossref_primary_10_1002_mp_13574
crossref_primary_10_3390_jpm13091338
crossref_primary_10_1007_s13534_021_00195_8
crossref_primary_10_1002_mp_15876
crossref_primary_10_1002_mp_14418
crossref_primary_10_1109_ACCESS_2019_2912226
crossref_primary_10_1016_j_ctro_2022_100564
crossref_primary_10_1016_j_compbiomed_2022_105277
crossref_primary_10_1016_j_radonc_2023_110056
crossref_primary_10_1109_ACCESS_2025_3570728
crossref_primary_10_3390_cancers16213670
crossref_primary_10_3390_su13031224
crossref_primary_10_1088_2057_1976_abe3a7
crossref_primary_10_1016_j_ejro_2022_100448
crossref_primary_10_3390_diagnostics11010011
crossref_primary_10_1148_ryai_2020190027
crossref_primary_10_1002_mp_15936
crossref_primary_10_1016_j_radonc_2025_110782
crossref_primary_10_3389_fonc_2022_968689
crossref_primary_10_1016_j_radonc_2020_06_049
crossref_primary_10_1016_j_radonc_2024_110387
crossref_primary_10_1088_1361_6560_ac279e
crossref_primary_10_1259_bjr_20180505
crossref_primary_10_1016_j_phro_2022_11_011
crossref_primary_10_1016_j_jksuci_2019_06_002
crossref_primary_10_1016_j_knosys_2024_111799
crossref_primary_10_1016_j_ijrobp_2018_12_008
crossref_primary_10_1088_2057_1976_ab27a6
crossref_primary_10_1016_j_semradonc_2022_06_001
crossref_primary_10_3390_s22114043
crossref_primary_10_1002_jmri_27308
crossref_primary_10_1097_RMR_0000000000000279
crossref_primary_10_1007_s00066_024_02277_9
crossref_primary_10_1177_0271678X19888123
crossref_primary_10_4274_mirt_galenos_2024_86422
crossref_primary_10_1016_j_semradonc_2022_06_007
crossref_primary_10_1177_15330338231199286
crossref_primary_10_3390_bioengineering9090467
crossref_primary_10_1016_j_compbiomed_2021_104917
crossref_primary_10_1109_JBHI_2021_3103387
crossref_primary_10_1088_2516_1091_ac5b13
crossref_primary_10_1016_j_procs_2023_01_171
crossref_primary_10_1007_s00330_019_06229_1
crossref_primary_10_1038_s41598_021_01681_w
crossref_primary_10_3389_fonc_2021_660284
crossref_primary_10_1002_mp_13663
crossref_primary_10_1002_mp_14987
crossref_primary_10_1109_TIM_2025_3544370
crossref_primary_10_1088_1361_6560_aaaca4
crossref_primary_10_3390_app12031358
crossref_primary_10_3390_s23239532
crossref_primary_10_1002_mrm_28689
crossref_primary_10_1016_j_neuroimage_2021_118697
crossref_primary_10_1109_ACCESS_2020_3047861
crossref_primary_10_1088_1361_6560_abc5cb
crossref_primary_10_1186_s13014_020_01524_4
crossref_primary_10_1002_ima_23113
crossref_primary_10_1177_15330338211046433
crossref_primary_10_1016_j_ejmp_2019_08_008
crossref_primary_10_1007_s00259_019_04374_9
crossref_primary_10_1016_j_phro_2022_10_002
crossref_primary_10_1007_s11227_021_03901_6
crossref_primary_10_1007_s11604_023_01449_4
crossref_primary_10_1002_mrm_29766
crossref_primary_10_1177_17562848251359141
crossref_primary_10_1007_s11042_021_11411_z
crossref_primary_10_1088_1361_6560_ac3d16
crossref_primary_10_1016_j_ejmp_2021_07_027
crossref_primary_10_3389_fonc_2020_01107
crossref_primary_10_1016_j_compbiomed_2025_110635
crossref_primary_10_1016_j_cmpb_2021_106575
crossref_primary_10_3233_JIFS_213367
crossref_primary_10_1177_0271678X211029178
crossref_primary_10_1007_s00330_023_10534_1
crossref_primary_10_1155_2021_2033806
crossref_primary_10_1259_bjr_20190001
crossref_primary_10_1002_mp_13716
crossref_primary_10_3390_cancers15020330
crossref_primary_10_1038_s41598_024_61869_8
crossref_primary_10_1002_mp_14929
crossref_primary_10_1016_j_ejmp_2018_05_006
crossref_primary_10_1038_s41598_021_85671_y
crossref_primary_10_1148_rg_220029
crossref_primary_10_1148_radiol_2018180547
crossref_primary_10_1016_j_neucom_2021_08_138
crossref_primary_10_1016_j_compbiomed_2024_107983
crossref_primary_10_1016_j_cmpb_2019_105065
crossref_primary_10_1016_j_media_2020_101718
crossref_primary_10_1016_j_hoc_2019_08_005
crossref_primary_10_1007_s13246_021_01031_0
crossref_primary_10_1016_j_compmedimag_2023_102249
crossref_primary_10_1016_j_zemedi_2018_12_003
crossref_primary_10_1007_s13369_019_03735_8
crossref_primary_10_1080_00207454_2024_2352784
crossref_primary_10_14338_IJPT_20_00099_1
crossref_primary_10_1016_j_breast_2019_11_011
crossref_primary_10_1088_2516_1091_adc85e
crossref_primary_10_3389_fonc_2021_686875
crossref_primary_10_1016_j_ijrobp_2019_06_009
crossref_primary_10_1088_1361_6560_aada6d
crossref_primary_10_1088_1361_6560_aaf496
crossref_primary_10_1016_j_jatmed_2025_06_003
crossref_primary_10_1088_1361_6560_abb1d6
crossref_primary_10_3390_a14050144
crossref_primary_10_1002_mp_13617
crossref_primary_10_3389_fonc_2021_713617
crossref_primary_10_1007_s10723_020_09513_3
crossref_primary_10_1038_s41598_019_43656_y
crossref_primary_10_1016_j_patrec_2020_06_017
crossref_primary_10_1016_j_media_2021_102079
crossref_primary_10_1016_j_ejrad_2021_109915
crossref_primary_10_1155_2021_1348922
crossref_primary_10_1016_j_clon_2018_08_009
crossref_primary_10_1038_s41598_023_33288_8
crossref_primary_10_1088_1361_6560_ab0b66
crossref_primary_10_1186_s12885_024_11844_3
crossref_primary_10_3390_app11083508
crossref_primary_10_1016_j_eswa_2022_117421
crossref_primary_10_1088_2399_6528_ac24d8
crossref_primary_10_3389_fphy_2023_1088899
crossref_primary_10_1007_s13042_023_01871_0
crossref_primary_10_3389_fonc_2019_01333
crossref_primary_10_1002_jmri_28573
crossref_primary_10_1016_j_ejca_2023_113504
crossref_primary_10_56809_icujtas_1562430
crossref_primary_10_1007_s12194_019_00520_y
crossref_primary_10_2478_pjmpe_2025_0003
crossref_primary_10_1002_hbm_25039
crossref_primary_10_3390_app131810521
crossref_primary_10_1186_s13244_024_01627_6
crossref_primary_10_1002_jmri_26271
crossref_primary_10_1002_mrm_27948
crossref_primary_10_3389_fonc_2024_1429837
crossref_primary_10_1016_j_rpor_2019_02_001
crossref_primary_10_1186_s13244_024_01820_7
crossref_primary_10_3389_fonc_2022_822687
crossref_primary_10_3390_app9122521
crossref_primary_10_1016_j_ijrobp_2018_10_002
crossref_primary_10_1016_j_radonc_2020_09_029
crossref_primary_10_1186_s40658_022_00486_8
crossref_primary_10_1109_TRPMS_2020_3006844
crossref_primary_10_3390_s19102361
crossref_primary_10_1016_j_compmedimag_2022_102150
crossref_primary_10_1186_s13014_023_02384_4
crossref_primary_10_1016_j_canrad_2018_09_005
crossref_primary_10_1002_mrm_28826
crossref_primary_10_1109_TMI_2020_2987026
crossref_primary_10_1007_s42835_023_01602_z
crossref_primary_10_1016_j_compbiomed_2024_108870
crossref_primary_10_1007_s11548_019_02040_x
crossref_primary_10_1002_acm2_12654
crossref_primary_10_1016_j_ymeth_2020_06_008
crossref_primary_10_1088_1361_6560_ab8cd2
crossref_primary_10_1007_s11263_020_01321_2
crossref_primary_10_1088_1361_6560_ab28a1
crossref_primary_10_1093_noajnl_vdaf001
crossref_primary_10_1016_j_phro_2025_100806
crossref_primary_10_2478_pjmpe_2025_0025
crossref_primary_10_1016_j_ijrobp_2018_05_058
crossref_primary_10_1088_1361_6560_ab0095
crossref_primary_10_1080_0284186X_2019_1684558
crossref_primary_10_3390_diagnostics11111964
crossref_primary_10_1002_mp_18038
crossref_primary_10_1109_ACCESS_2024_3460077
crossref_primary_10_1002_mp_12602
crossref_primary_10_1016_j_phro_2023_100464
crossref_primary_10_1002_mp_12600
crossref_primary_10_1088_1361_6560_abb0f8
crossref_primary_10_1109_TMI_2021_3059265
crossref_primary_10_1259_bjro_20230030
crossref_primary_10_3390_app14125144
crossref_primary_10_1109_ACCESS_2020_3048315
crossref_primary_10_1259_bjr_20190067
crossref_primary_10_1053_j_semnuclmed_2025_05_005
crossref_primary_10_1080_0284186X_2022_2140017
crossref_primary_10_3389_fnins_2018_01005
crossref_primary_10_1038_s41598_022_18256_y
crossref_primary_10_3390_app132011283
crossref_primary_10_1109_TAP_2019_2948565
crossref_primary_10_7555_JBR_36_20220037
crossref_primary_10_1016_j_ejmp_2021_09_006
crossref_primary_10_1016_j_ins_2020_06_072
crossref_primary_10_14338_IJPT_19_00062_1
crossref_primary_10_1002_mp_16087
crossref_primary_10_1007_s11604_018_0793_5
crossref_primary_10_1016_j_ynirp_2024_100195
crossref_primary_10_1016_j_compmedimag_2023_102300
crossref_primary_10_1097_RCT_0000000000001247
crossref_primary_10_3390_bioengineering9080368
crossref_primary_10_1002_acm2_13644
crossref_primary_10_1016_j_phro_2024_100658
crossref_primary_10_3389_fbioe_2024_1297675
crossref_primary_10_1002_acm2_12554
crossref_primary_10_1186_s41824_020_00086_8
crossref_primary_10_1002_acm2_13530
crossref_primary_10_1002_mp_13925
crossref_primary_10_1016_j_compbiomed_2021_104763
crossref_primary_10_1002_mp_13927
crossref_primary_10_1109_TVCG_2022_3219248
crossref_primary_10_1038_s41598_022_12646_y
crossref_primary_10_1016_j_phro_2025_100708
crossref_primary_10_1080_0284186X_2019_1630754
Cites_doi 10.1109/TSMC.1979.4310076
10.1118/1.4957412
10.1118/1.4842575
10.1088/0031-9155/59/23/7501
10.1016/j.ijrobp.2015.08.045
10.1088/0031-9155/61/17/6531
10.1088/0031-9155/59/21/6595
10.1145/2647868.2654889
10.1088/0031-9155/60/2/825
10.1118/1.4758068
10.1088/0031-9155/60/22/R323
10.1016/j.radonc.2013.10.034
10.1118/1.4914158
10.1118/1.4873315
10.1118/1.4926756
10.1118/1.3377774
10.1118/1.4931417
10.1118/1.1569270
10.1016/j.neuroimage.2014.12.061
10.1109/TMI.2015.2482920
10.2967/jnumed.111.092577
10.3109/0284186X.2012.692883
10.2967/jnumed.107.049353
10.1016/j.ijrobp.2015.07.001
10.1186/1748-717X-8-51
10.1109/42.668698
10.1118/1.3578928
10.1120/jacmp.v17i3.6065
10.2967/jnumed.109.065425
10.2967/jnumed.115.156299
10.1118/1.4958676
10.1148/radiol.14140810
10.1109/5.726791
10.1007/s00259-008-1007-7
10.2967/jnumed.108.054726
10.1016/j.ijrobp.2011.11.056
10.1038/nature14539
10.2967/jnumed.109.069112
10.3109/0284186X.2013.819119
10.1016/j.media.2016.07.007
10.1088/0031-9155/58/23/8419
10.1097/RLI.0b013e318283292f
ContentType Journal Article
Copyright 2017 American Association of Physicists in Medicine
2017 American Association of Physicists in Medicine.
Copyright_xml – notice: 2017 American Association of Physicists in Medicine
– notice: 2017 American Association of Physicists in Medicine.
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1002/mp.12155
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 2473-4209
EndPage 1419
ExternalDocumentID 28192624
10_1002_mp_12155
MP12155
Genre article
Journal Article
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
53G
5GY
5RE
5VS
AAHQN
AAIPD
AAMMB
AAMNL
AANLZ
AAQQT
AASGY
AAXRX
AAYCA
AAZKR
ABCUV
ABDPE
ABEFU
ABJNI
ABLJU
ABQWH
ABUFD
ABXGK
ACAHQ
ACBEA
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADMLS
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AENEX
AEUYR
AEYWJ
AFBPY
AFFPM
AFWVQ
AGHNM
AGXDD
AGYGG
AHBTC
AIACR
AIAGR
AIDQK
AIDYY
AIQQE
AITYG
AIURR
ALMA_UNASSIGNED_HOLDINGS
ALVPJ
AMYDB
ASPBG
BFHJK
C45
CS3
DCZOG
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMB
EMOBN
F5P
HDBZQ
HGLYW
I-F
KBYEO
LATKE
LEEKS
LH4
LOXES
LUTES
LYRES
MEWTI
O9-
OVD
P2P
P2W
PALCI
PHY
RJQFR
RNS
ROL
SAMSI
SUPJJ
SV3
TEORI
TN5
TWZ
USG
WOHZO
WXSBR
ZGI
ZVN
ZXP
ZY4
ZZTAW
AAYXX
CITATION
AAHHS
ABFTF
ABTAH
ACCFJ
AEEZP
AEQDE
AIWBW
AJBDE
ALUQN
CGR
CUY
CVF
ECM
EIF
NPM
XJT
7X8
ID FETCH-LOGICAL-c3875-f3480ef47c80ca6fca53161b5e1fea0111b333a3021a73ccd1571a4763be849d3
IEDL.DBID DRFUL
ISICitedReferencesCount 553
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000400572700020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0094-2405
2473-4209
IngestDate Sun Nov 09 10:11:59 EST 2025
Thu Apr 03 07:01:20 EDT 2025
Sat Nov 29 06:02:31 EST 2025
Tue Nov 18 22:03:38 EST 2025
Tue Nov 11 03:10:30 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords deep learning
synthetic CT
MRI
convolutional neural network
radiation therapy
Language English
License http://onlinelibrary.wiley.com/termsAndConditions
http://doi.wiley.com/10.1002/tdm_license_1
2017 American Association of Physicists in Medicine.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3875-f3480ef47c80ca6fca53161b5e1fea0111b333a3021a73ccd1571a4763be849d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 28192624
PQID 1868395434
PQPubID 23479
PageCount 12
ParticipantIDs proquest_miscellaneous_1868395434
pubmed_primary_28192624
crossref_primary_10_1002_mp_12155
crossref_citationtrail_10_1002_mp_12155
wiley_primary_10_1002_mp_12155_MP12155
PublicationCentury 2000
PublicationDate April 2017
PublicationDateYYYYMMDD 2017-04-01
PublicationDate_xml – month: 04
  year: 2017
  text: April 2017
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2017
References 2012; 83
2015; 57
2014; 1409
2013; 48
2010; 37
2015; 93
2013; 109
2015; 521
2015; 1511
2015; 108
2012; 39
2014; 41
1995; 2
2011; 38
2013; 8
2016; 17
2003; 30
1998; 86
2012; 53
2016; 35
2015; 9350
2015; 9351
1998; 1524
2009; 36
1998; 17
2013; 58
2015; 60
2009; 50
2015; 42
2015; 275
2008; 49
2017; 35
2013; 52
2016; 43
2014; 8689
2014; 59
2016; 61
2015
2014
2012; 25
2014; 1412
2015; 9349
2010; 51
1979; 9
Johansson (10.1002/mp.12155-BIB0016|mp12155-cit-0016) 2011; 38
Arabi (10.1002/mp.12155-BIB0022|mp12155-cit-0022) 2016; 61
Chen (10.1002/mp.12155-BIB0024|mp12155-cit-0024) 2016; 17
Martinez-Möller (10.1002/mp.12155-BIB0007|mp12155-cit-0007) 2009; 50
Dowling (10.1002/mp.12155-BIB0026|mp12155-cit-0026) 2015; 93
Krizhevsky (10.1002/mp.12155-BIB0036|mp12155-cit-0036) 2012; 25
Zeiler (10.1002/mp.12155-BIB0050|mp12155-cit-0050) 2014; 8689
LeCun (10.1002/mp.12155-BIB0052|mp12155-cit-0052) 1998; 1524
Hsu (10.1002/mp.12155-BIB0008|mp12155-cit-0008) 2013; 58
Burgos (10.1002/mp.12155-BIB0023|mp12155-cit-0023) 2015; 9350
Hofmann (10.1002/mp.12155-BIB0003|mp12155-cit-0003) 2009; 36
Kooi (10.1002/mp.12155-BIB0041|mp12155-cit-0041) 2017; 35
Zheng (10.1002/mp.12155-BIB0011|mp12155-cit-0011) 2015; 93
Sjölund (10.1002/mp.12155-BIB0029|mp12155-cit-0029) 2015; 60
LeCun (10.1002/mp.12155-BIB0037|mp12155-cit-0037) 1998; 86
Schmidt (10.1002/mp.12155-BIB0001|mp12155-cit-0001) 2015; 60
Schreibmann (10.1002/mp.12155-BIB0027|mp12155-cit-0027) 2010; 37
Torrado-Carvajal (10.1002/mp.12155-BIB0030|mp12155-cit-0030) 2015; 57
Ronneberger (10.1002/mp.12155-BIB0039|mp12155-cit-0039) 2015; 9351
Kingma (10.1002/mp.12155-BIB0053|mp12155-cit-0053) 2014
Andreasen (10.1002/mp.12155-BIB0021|mp12155-cit-0021) 2015; 42
Sled (10.1002/mp.12155-BIB0043|mp12155-cit-0043) 1998; 17
Zaidi (10.1002/mp.12155-BIB0010|mp12155-cit-0010) 2003; 30
Otsu (10.1002/mp.12155-BIB0045|mp12155-cit-0045) 1979; 9
Edmund (10.1002/mp.12155-BIB0012|mp12155-cit-0012) 2014; 59
Gudur (10.1002/mp.12155-BIB0034|mp12155-cit-0034) 2014; 59
Su (10.1002/mp.12155-BIB0009|mp12155-cit-0009) 2015; 42
Navalpakkam (10.1002/mp.12155-BIB0017|mp12155-cit-0017) 2013; 48
Siversson (10.1002/mp.12155-BIB0028|mp12155-cit-0028) 2015; 42
Jia (10.1002/mp.12155-BIB0051|mp12155-cit-0051) 2014
10.1002/mp.12155-BIB0054|mp12155-cit-0054
Devic (10.1002/mp.12155-BIB0002|mp12155-cit-0002) 2012; 39
Catana (10.1002/mp.12155-BIB0005|mp12155-cit-0005) 2010; 51
Noh (10.1002/mp.12155-BIB0047|mp12155-cit-0047) 2015
Nguyen (10.1002/mp.12155-BIB0042|mp12155-cit-0042) 2015; 9349
Lecun (10.1002/mp.12155-BIB0035|mp12155-cit-0035) 2015; 521
Hofmann (10.1002/mp.12155-BIB0033|mp12155-cit-0033) 2008; 49
Uh (10.1002/mp.12155-BIB0031|mp12155-cit-0031) 2014; 41
Rank (10.1002/mp.12155-BIB0018|mp12155-cit-0018) 2013; 109
Johansson (10.1002/mp.12155-BIB0015|mp12155-cit-0015) 2013; 52
Roth (10.1002/mp.12155-BIB0040|mp12155-cit-0040) 2016; 35
Chen (10.1002/mp.12155-BIB0032|mp12155-cit-0032) 2015; 275
Zhang (10.1002/mp.12155-BIB0038|mp12155-cit-0038) 2015; 108
Berker (10.1002/mp.12155-BIB0004|mp12155-cit-0004) 2012; 53
Kapanen (10.1002/mp.12155-BIB0013|mp12155-cit-0013) 2013; 52
Dowling (10.1002/mp.12155-BIB0025|mp12155-cit-0025) 2012; 83
Andreasen (10.1002/mp.12155-BIB0020|mp12155-cit-0020) 2016; 43
Keereman (10.1002/mp.12155-BIB0006|mp12155-cit-0006) 2010; 51
Korhonen (10.1002/mp.12155-BIB0014|mp12155-cit-0014) 2014; 41
Rank (10.1002/mp.12155-BIB0019|mp12155-cit-0019) 2013; 8
Simonyan (10.1002/mp.12155-BIB0049|mp12155-cit-0049) 2014; 1409
Han (10.1002/mp.12155-BIB0055|mp12155-cit-0055) 2016; 43
Chen (10.1002/mp.12155-BIB0046|mp12155-cit-0046) 2014; 1412
Cox (10.1002/mp.12155-BIB0044|mp12155-cit-0044) 1995; 2
Badrinarayanan (10.1002/mp.12155-BIB0048|mp12155-cit-0048) 2015; 1511
References_xml – volume: 59
  start-page: 7501
  year: 2014
  end-page: 7519
  article-title: A voxel‐based investigation for MRI‐only radiotherapy of the brain using ultra short echo times
  publication-title: Phys Med Biol
– start-page: 1520
  year: 2015
  end-page: 1528
  article-title: Learning deconvolution network for semantic segmentation
  publication-title: Proc. Int. Conf. Comp. Vis
– volume: 52
  start-page: 612
  year: 2013
  end-page: 618
  article-title: T1/T2*‐weighted MRI provides clinically relevant pseudo‐CT density data for the pelvic bones in MRI‐only based radiotherapy treatment planning
  publication-title: Acta Oncol
– volume: 60
  start-page: 825
  year: 2015
  end-page: 839
  article-title: Generating patient specific pseudo‐CT of the head from MR using atlas‐based regression
  publication-title: Phys Med Biol
– volume: 9349
  start-page: 677
  year: 2015
  end-page: 684
  article-title: “Cross‐domain synthesis of medical images using efficient location‐sensitive deep network”, MICCAI 2015
  publication-title: Part I, LNCS
– volume: 1524
  start-page: 9
  year: 1998
  end-page: 48
  article-title: Efficient backprop
  publication-title: Neural Networks: tricks of the trade Springer
– volume: 36
  start-page: 93
  year: 2009
  end-page: 104
  article-title: Towards quantitative PET/MRI: a review of MR‐based attenuation correction techniques
  publication-title: Eur J Nucl Med Mol Imaging
– volume: 9351
  start-page: 234
  year: 2015
  end-page: 241
  article-title: “U‐Net: convolutional networks for biomedical image segmentation”, MICCAI 2015
  publication-title: Part III, LNCS
– volume: 61
  start-page: 6531
  year: 2016
  end-page: 6552
  article-title: Atlas‐guided generation of pseudo‐CT images for MRI‐only and hybrid PET–MRI‐guided radiotherapy treatment planning
  publication-title: Phys Med Biol
– volume: 17
  start-page: 1
  year: 2016
  end-page: 10
  article-title: MR image‐based synthetic CT for IMRT prostate treatment planning and CBCT image‐guided localization
  publication-title: J Appl Clin Med Phys
– volume: 57
  start-page: 136
  year: 2015
  end-page: 144
  article-title: Fast patch‐based pseudo‐CT synthesis from T1‐weighted MR images for PET/MR attenuation correction in brain studies
  publication-title: J Nucl Med
– volume: 52
  start-page: 1369
  year: 2013
  end-page: 1373
  article-title: Improved quality of computed tomography substitute derived from magnetic resonance (MR) data by incorporation of spatial information–potential application for MR‐only radiotherapy and attenuation correction in positron emission tomography
  publication-title: Acta Oncol
– volume: 1409
  start-page: 1
  year: 2014
  end-page: 14
  article-title: “Very deep convolutional networks for large‐scale image recognition”, arXiv
  publication-title: preprint
– volume: 1412
  start-page: 1
  year: 2014
  end-page: 14
  article-title: “Semantic image segmentation with deep convolutional nets and fully connected CRFs”, arXiv
  publication-title: preprint
– volume: 42
  start-page: 1596
  year: 2015
  end-page: 1605
  article-title: J.a.L. Andersen, J.M. Edmund, “Patch‐based generation of a pseudo CT from conventional MRI sequences for MRI‐only radiotherapy of the brain”
  publication-title: Med Phys
– volume: 60
  start-page: 323
  year: 2015
  end-page: 361
  article-title: Radiotherapy planning using MRI
  publication-title: Phys Med Biol
– volume: 49
  start-page: 1875
  year: 2008
  end-page: 1883
  article-title: MRI‐based attenuation correction for PET/MRI: a novel approach combining pattern recognition and atlas registration
  publication-title: J Nucl Med
– volume: 58
  start-page: 8419
  year: 2013
  end-page: 8435
  article-title: Investigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapy
  publication-title: Phys Med Biol
– volume: 53
  start-page: 796
  year: 2012
  end-page: 804
  article-title: MRI‐based attenuation correction for hybrid PET/MRI systems: a 4‐class tissue segmentation technique using a combined ultrashort‐echo‐time/Dixon MRI sequence
  publication-title: J Nucl Med
– volume: 109
  start-page: 414
  year: 2013
  end-page: 418
  article-title: MRI‐based simulation of treatment plans for ion radiotherapy in the brain region
  publication-title: Radiother Oncol
– volume: 42
  start-page: 4974
  year: 2015
  end-page: 4986
  article-title: Generation of brain pseudo‐CTs using an undersampled, single‐acquisition UTE‐mDixon pulse sequence and unsupervised clustering
  publication-title: Med Phys
– volume: 8
  start-page: 51
  year: 2013
  article-title: MRI‐based treatment plan simulation and adaptation for ion radiotherapy using a classification‐based approach
  publication-title: Radiat Oncol
– volume: 51
  start-page: 812
  year: 2010
  end-page: 818
  article-title: MRI‐based attenuation correction for PET/MRI using ultrashort echo time sequences
  publication-title: J Nucl Med
– volume: 43
  start-page: 4742
  year: 2016
  end-page: 4752
  article-title: A patch‐based pseudo‐CT approach for MRI‐only radiotherapy in the pelvis
  publication-title: Med Phys
– volume: 108
  start-page: 214
  year: 2015
  end-page: 224
  article-title: Deep convolutional neural networks for multi‐modality isointense infant brain image segmentation
  publication-title: NeuroImage
– volume: 37
  start-page: 2101
  year: 2010
  end-page: 2109
  article-title: J.a. Nye, D.M. Schuster, D.R. Martin, J. Votaw, T. Fox, “MR‐based attenuation correction for hybrid PET‐MR brain imaging systems using deformable image registration”
  publication-title: Med Phys
– year: 2015
– volume: 9
  start-page: 62
  year: 1979
  end-page: 66
  article-title: A threshold selection method from gray‐level histograms
  publication-title: IEEE Trans. Syst. Man Cybern
– volume: 83
  start-page: 5
  year: 2012
  end-page: 11
  article-title: An atlas‐based electron density mapping method for magnetic resonance imaging (MRI)‐alone treatment planning and adaptive MRI‐based prostate radiation therapy
  publication-title: Int J Radiat Oncol Biol Phys
– start-page: 675
  year: 2014
  end-page: 678
  article-title: Caffe: convolutional architecture for fast feature embedding
  publication-title: Proc. ACM Int. Conf. Multimedia
– volume: 35
  start-page: 1170
  year: 2016
  end-page: 1181
  article-title: Improving computer‐aided detection using convolutional neural networks and random view aggregation
  publication-title: IEEE Trans Med Imaging
– volume: 38
  start-page: 2708
  year: 2011
  end-page: 2714
  article-title: CT substitute derived from MRI sequences with ultrashort echo time
  publication-title: Med Phys
– volume: 48
  start-page: 323
  year: 2013
  article-title: Magnetic resonance‐based attenuation correction for PET/MR hybrid imaging using continuous valued attenuation maps
  publication-title: Invest Radiol
– volume: 51
  start-page: 1431
  year: 2010
  end-page: 1438
  article-title: Toward implementing an MRI‐based PET attenuation‐correction method for neurologic studies on the MR‐PET brain prototype
  publication-title: J Nucl Med
– volume: 43
  start-page: 3733
  year: 2016
  article-title: An efficient atlas‐based synthetic CT generation method
  publication-title: Med Phys
– volume: 93
  start-page: 1144
  year: 2015
  end-page: 1153
  article-title: Automatic substitute CT generation and contouring for MRI‐alone external beam radiation therapy from standard MRI sequences
  publication-title: Int J Radiat Oncol Biol Phys
– start-page: 1
  year: 2014
  end-page: 13
  article-title: Adam: a method for stochastic optimization
  publication-title: Proc. Int. Conf. Learning Representations
– volume: 41
  start-page: 051711
  year: 2014
  article-title: MRI‐based treatment planning with pseudo CT generated through atlas registration
  publication-title: Med Phys
– volume: 25
  start-page: 1097
  year: 2012
  end-page: 1105
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Advances In Neural Information Processing Systems
– volume: 42
  start-page: 6090
  year: 2015
  end-page: 6097
  article-title: Technical Note: MRI only prostate radiotherapy planning using the statistical decomposition algorithm
  publication-title: Med Phys
– volume: 9350
  start-page: 476
  year: 2015
  end-page: 484
  article-title: “Robust CT synthesis for radiotherapy planning: application to the head and neck region”, MICCAI 2015
  publication-title: Part II, LNCS
– volume: 275
  start-page: 562
  year: 2015
  end-page: 569
  article-title: Probabilistic air segmentation and sparse regression estimated pseudo CT for PET/MR attenuation correction
  publication-title: Radiology
– volume: 521
  start-page: 436
  year: 2015
  end-page: 444
  article-title: Deep learning
  publication-title: Nature
– volume: 50
  start-page: 520
  year: 2009
  end-page: 526
  article-title: Tissue classification as a potential approach for attenuation correction in whole‐body PET/MRI: evaluation with PET/CT data
  publication-title: J Nucl Med
– volume: 1511
  start-page: 1
  year: 2015
  end-page: 14
  article-title: “SegNet: a deep convolutional encoder‐decoder architecture for image segmentation”, arXiv
  publication-title: preprint
– volume: 30
  start-page: 937
  year: 2003
  end-page: 948
  article-title: Magnetic resonance imaging‐guided attenuation and scatter corrections in three‐dimensional brain positron emission tomography
  publication-title: Med Phys
– volume: 35
  start-page: 303
  year: 2017
  end-page: 312
  article-title: Large scale deep learning for computer aided detection of mammographic lesions
  publication-title: Med Image Anal
– volume: 93
  start-page: 497
  year: 2015
  end-page: 506
  article-title: Magnetic Resonance‐Based Automatic Air Segmentation for Generation of Synthetic Computed Tomography Scans in the Head Region
  publication-title: Int J Radiat Oncol Biol Phys
– volume: 86
  start-page: 2278
  year: 1998
  end-page: 2323
  article-title: L.o. Bottou, Y. Bengio, P. Haffner, “Gradient‐based learning applied to document recognition”
  publication-title: Proc IEEE
– volume: 8689
  start-page: 818
  year: 2014
  end-page: 833
  article-title: “Visualizing and understanding convolutional networks”, ECCV 2014
  publication-title: LNCS
– volume: 59
  start-page: 6595
  year: 2014
  end-page: 6606
  article-title: A unifying probabilistic Bayesian approach to derive electron density from MRI for radiation therapy treatment planning
  publication-title: Phys Med Biol
– volume: 17
  start-page: 87
  year: 1998
  end-page: 97
  article-title: A nonparametric method for automatic correction of intensity nonuniformity in MRI data
  publication-title: IEEE Trans Med Imaging
– volume: 39
  start-page: 6701
  year: 2012
  end-page: 6711
  article-title: MRI simulation for radiotherapy treatment planning
  publication-title: Med Phys
– volume: 41
  start-page: 011704
  year: 2014
  article-title: A dual model HU conversion from MRI intensity values within and outside of bone segment for MRI‐based radiotherapy treatment planning of prostate cancer
  publication-title: Med Phys
– volume: 2
  start-page: 366
  year: 1995
  end-page: 369
  article-title: Dynamic histogram warping of image pairs for constant image brightness
  publication-title: Proc. Int. Conf. Image Proc
– volume: 9
  start-page: 62
  year: 1979
  ident: 10.1002/mp.12155-BIB0045|mp12155-cit-0045
  article-title: A threshold selection method from gray-level histograms
  publication-title: IEEE Trans. Syst. Man Cybern
  doi: 10.1109/TSMC.1979.4310076
– volume: 43
  start-page: 3733
  year: 2016
  ident: 10.1002/mp.12155-BIB0055|mp12155-cit-0055
  article-title: An efficient atlas-based synthetic CT generation method
  publication-title: Med Phys
  doi: 10.1118/1.4957412
– volume: 41
  start-page: 011704
  year: 2014
  ident: 10.1002/mp.12155-BIB0014|mp12155-cit-0014
  article-title: A dual model HU conversion from MRI intensity values within and outside of bone segment for MRI-based radiotherapy treatment planning of prostate cancer
  publication-title: Med Phys
  doi: 10.1118/1.4842575
– volume: 59
  start-page: 7501
  year: 2014
  ident: 10.1002/mp.12155-BIB0012|mp12155-cit-0012
  article-title: A voxel-based investigation for MRI-only radiotherapy of the brain using ultra short echo times
  publication-title: Phys Med Biol
  doi: 10.1088/0031-9155/59/23/7501
– volume: 93
  start-page: 1144
  year: 2015
  ident: 10.1002/mp.12155-BIB0026|mp12155-cit-0026
  article-title: Automatic substitute CT generation and contouring for MRI-alone external beam radiation therapy from standard MRI sequences
  publication-title: Int J Radiat Oncol Biol Phys
  doi: 10.1016/j.ijrobp.2015.08.045
– ident: 10.1002/mp.12155-BIB0054|mp12155-cit-0054
– volume: 61
  start-page: 6531
  year: 2016
  ident: 10.1002/mp.12155-BIB0022|mp12155-cit-0022
  article-title: Atlas-guided generation of pseudo-CT images for MRI-only and hybrid PET-MRI-guided radiotherapy treatment planning
  publication-title: Phys Med Biol
  doi: 10.1088/0031-9155/61/17/6531
– volume: 59
  start-page: 6595
  year: 2014
  ident: 10.1002/mp.12155-BIB0034|mp12155-cit-0034
  article-title: A unifying probabilistic Bayesian approach to derive electron density from MRI for radiation therapy treatment planning
  publication-title: Phys Med Biol
  doi: 10.1088/0031-9155/59/21/6595
– start-page: 675
  year: 2014
  ident: 10.1002/mp.12155-BIB0051|mp12155-cit-0051
  article-title: Caffe: convolutional architecture for fast feature embedding
  publication-title: Proc. ACM Int. Conf. Multimedia
  doi: 10.1145/2647868.2654889
– volume: 60
  start-page: 825
  year: 2015
  ident: 10.1002/mp.12155-BIB0029|mp12155-cit-0029
  article-title: Generating patient specific pseudo-CT of the head from MR using atlas-based regression
  publication-title: Phys Med Biol
  doi: 10.1088/0031-9155/60/2/825
– volume: 9350
  start-page: 476
  year: 2015
  ident: 10.1002/mp.12155-BIB0023|mp12155-cit-0023
  article-title: “Robust CT synthesis for radiotherapy planning: application to the head and neck region”, MICCAI 2015
  publication-title: Part II, LNCS
– volume: 39
  start-page: 6701
  year: 2012
  ident: 10.1002/mp.12155-BIB0002|mp12155-cit-0002
  article-title: MRI simulation for radiotherapy treatment planning
  publication-title: Med Phys
  doi: 10.1118/1.4758068
– volume: 60
  start-page: 323
  year: 2015
  ident: 10.1002/mp.12155-BIB0001|mp12155-cit-0001
  article-title: Radiotherapy planning using MRI
  publication-title: Phys Med Biol
  doi: 10.1088/0031-9155/60/22/R323
– start-page: 1520
  year: 2015
  ident: 10.1002/mp.12155-BIB0047|mp12155-cit-0047
  article-title: Learning deconvolution network for semantic segmentation
  publication-title: Proc. Int. Conf. Comp. Vis
– volume: 109
  start-page: 414
  year: 2013
  ident: 10.1002/mp.12155-BIB0018|mp12155-cit-0018
  article-title: MRI-based simulation of treatment plans for ion radiotherapy in the brain region
  publication-title: Radiother Oncol
  doi: 10.1016/j.radonc.2013.10.034
– volume: 42
  start-page: 1596
  year: 2015
  ident: 10.1002/mp.12155-BIB0021|mp12155-cit-0021
  article-title: J.a.L. Andersen, J.M. Edmund, “Patch-based generation of a pseudo CT from conventional MRI sequences for MRI-only radiotherapy of the brain”
  publication-title: Med Phys
  doi: 10.1118/1.4914158
– volume: 1409
  start-page: 1
  year: 2014
  ident: 10.1002/mp.12155-BIB0049|mp12155-cit-0049
  article-title: “Very deep convolutional networks for large-scale image recognition”, arXiv
  publication-title: preprint
– volume: 41
  start-page: 051711
  year: 2014
  ident: 10.1002/mp.12155-BIB0031|mp12155-cit-0031
  article-title: MRI-based treatment planning with pseudo CT generated through atlas registration
  publication-title: Med Phys
  doi: 10.1118/1.4873315
– volume: 42
  start-page: 4974
  year: 2015
  ident: 10.1002/mp.12155-BIB0009|mp12155-cit-0009
  article-title: Generation of brain pseudo-CTs using an undersampled, single-acquisition UTE-mDixon pulse sequence and unsupervised clustering
  publication-title: Med Phys
  doi: 10.1118/1.4926756
– volume: 37
  start-page: 2101
  year: 2010
  ident: 10.1002/mp.12155-BIB0027|mp12155-cit-0027
  article-title: J.a. Nye, D.M. Schuster, D.R. Martin, J. Votaw, T. Fox, “MR-based attenuation correction for hybrid PET-MR brain imaging systems using deformable image registration”
  publication-title: Med Phys
  doi: 10.1118/1.3377774
– volume: 42
  start-page: 6090
  year: 2015
  ident: 10.1002/mp.12155-BIB0028|mp12155-cit-0028
  article-title: Technical Note: MRI only prostate radiotherapy planning using the statistical decomposition algorithm
  publication-title: Med Phys
  doi: 10.1118/1.4931417
– volume: 1412
  start-page: 1
  year: 2014
  ident: 10.1002/mp.12155-BIB0046|mp12155-cit-0046
  article-title: “Semantic image segmentation with deep convolutional nets and fully connected CRFs”, arXiv
  publication-title: preprint
– volume: 30
  start-page: 937
  year: 2003
  ident: 10.1002/mp.12155-BIB0010|mp12155-cit-0010
  article-title: Magnetic resonance imaging-guided attenuation and scatter corrections in three-dimensional brain positron emission tomography
  publication-title: Med Phys
  doi: 10.1118/1.1569270
– volume: 25
  start-page: 1097
  year: 2012
  ident: 10.1002/mp.12155-BIB0036|mp12155-cit-0036
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Advances In Neural Information Processing Systems
– volume: 108
  start-page: 214
  year: 2015
  ident: 10.1002/mp.12155-BIB0038|mp12155-cit-0038
  article-title: Deep convolutional neural networks for multi-modality isointense infant brain image segmentation
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2014.12.061
– volume: 9351
  start-page: 234
  year: 2015
  ident: 10.1002/mp.12155-BIB0039|mp12155-cit-0039
  article-title: “U-Net: convolutional networks for biomedical image segmentation”, MICCAI 2015
  publication-title: Part III, LNCS
– volume: 35
  start-page: 1170
  year: 2016
  ident: 10.1002/mp.12155-BIB0040|mp12155-cit-0040
  article-title: Improving computer-aided detection using convolutional neural networks and random view aggregation
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2015.2482920
– volume: 9349
  start-page: 677
  year: 2015
  ident: 10.1002/mp.12155-BIB0042|mp12155-cit-0042
  article-title: “Cross-domain synthesis of medical images using efficient location-sensitive deep network”, MICCAI 2015
  publication-title: Part I, LNCS
– volume: 53
  start-page: 796
  year: 2012
  ident: 10.1002/mp.12155-BIB0004|mp12155-cit-0004
  article-title: MRI-based attenuation correction for hybrid PET/MRI systems: a 4-class tissue segmentation technique using a combined ultrashort-echo-time/Dixon MRI sequence
  publication-title: J Nucl Med
  doi: 10.2967/jnumed.111.092577
– volume: 52
  start-page: 612
  year: 2013
  ident: 10.1002/mp.12155-BIB0013|mp12155-cit-0013
  article-title: T1/T2*-weighted MRI provides clinically relevant pseudo-CT density data for the pelvic bones in MRI-only based radiotherapy treatment planning
  publication-title: Acta Oncol
  doi: 10.3109/0284186X.2012.692883
– volume: 49
  start-page: 1875
  year: 2008
  ident: 10.1002/mp.12155-BIB0033|mp12155-cit-0033
  article-title: MRI-based attenuation correction for PET/MRI: a novel approach combining pattern recognition and atlas registration
  publication-title: J Nucl Med
  doi: 10.2967/jnumed.107.049353
– volume: 93
  start-page: 497
  year: 2015
  ident: 10.1002/mp.12155-BIB0011|mp12155-cit-0011
  article-title: Magnetic Resonance-Based Automatic Air Segmentation for Generation of Synthetic Computed Tomography Scans in the Head Region
  publication-title: Int J Radiat Oncol Biol Phys
  doi: 10.1016/j.ijrobp.2015.07.001
– volume: 8
  start-page: 51
  year: 2013
  ident: 10.1002/mp.12155-BIB0019|mp12155-cit-0019
  article-title: MRI-based treatment plan simulation and adaptation for ion radiotherapy using a classification-based approach
  publication-title: Radiat Oncol
  doi: 10.1186/1748-717X-8-51
– volume: 17
  start-page: 87
  year: 1998
  ident: 10.1002/mp.12155-BIB0043|mp12155-cit-0043
  article-title: A nonparametric method for automatic correction of intensity nonuniformity in MRI data
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/42.668698
– volume: 38
  start-page: 2708
  year: 2011
  ident: 10.1002/mp.12155-BIB0016|mp12155-cit-0016
  article-title: CT substitute derived from MRI sequences with ultrashort echo time
  publication-title: Med Phys
  doi: 10.1118/1.3578928
– volume: 17
  start-page: 1
  year: 2016
  ident: 10.1002/mp.12155-BIB0024|mp12155-cit-0024
  article-title: MR image-based synthetic CT for IMRT prostate treatment planning and CBCT image-guided localization
  publication-title: J Appl Clin Med Phys
  doi: 10.1120/jacmp.v17i3.6065
– volume: 51
  start-page: 812
  year: 2010
  ident: 10.1002/mp.12155-BIB0006|mp12155-cit-0006
  article-title: MRI-based attenuation correction for PET/MRI using ultrashort echo time sequences
  publication-title: J Nucl Med
  doi: 10.2967/jnumed.109.065425
– volume: 57
  start-page: 136
  year: 2015
  ident: 10.1002/mp.12155-BIB0030|mp12155-cit-0030
  article-title: Fast patch-based pseudo-CT synthesis from T1-weighted MR images for PET/MR attenuation correction in brain studies
  publication-title: J Nucl Med
  doi: 10.2967/jnumed.115.156299
– start-page: 1
  year: 2014
  ident: 10.1002/mp.12155-BIB0053|mp12155-cit-0053
  article-title: Adam: a method for stochastic optimization
  publication-title: Proc. Int. Conf. Learning Representations
– volume: 43
  start-page: 4742
  year: 2016
  ident: 10.1002/mp.12155-BIB0020|mp12155-cit-0020
  article-title: A patch-based pseudo-CT approach for MRI-only radiotherapy in the pelvis
  publication-title: Med Phys
  doi: 10.1118/1.4958676
– volume: 1524
  start-page: 9
  year: 1998
  ident: 10.1002/mp.12155-BIB0052|mp12155-cit-0052
  article-title: Efficient backprop
  publication-title: Neural Networks: tricks of the trade Springer
– volume: 275
  start-page: 562
  year: 2015
  ident: 10.1002/mp.12155-BIB0032|mp12155-cit-0032
  article-title: Probabilistic air segmentation and sparse regression estimated pseudo CT for PET/MR attenuation correction
  publication-title: Radiology
  doi: 10.1148/radiol.14140810
– volume: 8689
  start-page: 818
  year: 2014
  ident: 10.1002/mp.12155-BIB0050|mp12155-cit-0050
  article-title: “Visualizing and understanding convolutional networks”, ECCV 2014
  publication-title: LNCS
– volume: 86
  start-page: 2278
  year: 1998
  ident: 10.1002/mp.12155-BIB0037|mp12155-cit-0037
  article-title: L.o. Bottou, Y. Bengio, P. Haffner, “Gradient-based learning applied to document recognition”
  publication-title: Proc IEEE
  doi: 10.1109/5.726791
– volume: 1511
  start-page: 1
  year: 2015
  ident: 10.1002/mp.12155-BIB0048|mp12155-cit-0048
  article-title: “SegNet: a deep convolutional encoder-decoder architecture for image segmentation”, arXiv
  publication-title: preprint
– volume: 36
  start-page: 93
  year: 2009
  ident: 10.1002/mp.12155-BIB0003|mp12155-cit-0003
  article-title: Towards quantitative PET/MRI: a review of MR-based attenuation correction techniques
  publication-title: Eur J Nucl Med Mol Imaging
  doi: 10.1007/s00259-008-1007-7
– volume: 50
  start-page: 520
  year: 2009
  ident: 10.1002/mp.12155-BIB0007|mp12155-cit-0007
  article-title: Tissue classification as a potential approach for attenuation correction in whole-body PET/MRI: evaluation with PET/CT data
  publication-title: J Nucl Med
  doi: 10.2967/jnumed.108.054726
– volume: 2
  start-page: 366
  year: 1995
  ident: 10.1002/mp.12155-BIB0044|mp12155-cit-0044
  article-title: Dynamic histogram warping of image pairs for constant image brightness
  publication-title: Proc. Int. Conf. Image Proc
– volume: 83
  start-page: 5
  year: 2012
  ident: 10.1002/mp.12155-BIB0025|mp12155-cit-0025
  article-title: An atlas-based electron density mapping method for magnetic resonance imaging (MRI)-alone treatment planning and adaptive MRI-based prostate radiation therapy
  publication-title: Int J Radiat Oncol Biol Phys
  doi: 10.1016/j.ijrobp.2011.11.056
– volume: 521
  start-page: 436
  year: 2015
  ident: 10.1002/mp.12155-BIB0035|mp12155-cit-0035
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 51
  start-page: 1431
  year: 2010
  ident: 10.1002/mp.12155-BIB0005|mp12155-cit-0005
  article-title: Toward implementing an MRI-based PET attenuation-correction method for neurologic studies on the MR-PET brain prototype
  publication-title: J Nucl Med
  doi: 10.2967/jnumed.109.069112
– volume: 52
  start-page: 1369
  year: 2013
  ident: 10.1002/mp.12155-BIB0015|mp12155-cit-0015
  article-title: Improved quality of computed tomography substitute derived from magnetic resonance (MR) data by incorporation of spatial information-potential application for MR-only radiotherapy and attenuation correction in positron emission tomography
  publication-title: Acta Oncol
  doi: 10.3109/0284186X.2013.819119
– volume: 35
  start-page: 303
  year: 2017
  ident: 10.1002/mp.12155-BIB0041|mp12155-cit-0041
  article-title: Large scale deep learning for computer aided detection of mammographic lesions
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2016.07.007
– volume: 58
  start-page: 8419
  year: 2013
  ident: 10.1002/mp.12155-BIB0008|mp12155-cit-0008
  article-title: Investigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapy
  publication-title: Phys Med Biol
  doi: 10.1088/0031-9155/58/23/8419
– volume: 48
  start-page: 323
  year: 2013
  ident: 10.1002/mp.12155-BIB0017|mp12155-cit-0017
  article-title: Magnetic resonance-based attenuation correction for PET/MR hybrid imaging using continuous valued attenuation maps
  publication-title: Invest Radiol
  doi: 10.1097/RLI.0b013e318283292f
SSID ssj0006350
Score 2.6769788
Snippet Purpose Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue...
Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast...
SourceID proquest
pubmed
crossref
wiley
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1408
SubjectTerms Breast Neoplasms - diagnostic imaging
convolutional neural network
deep learning
Humans
Image Processing, Computer-Assisted - methods
Imaging, Three-Dimensional
Magnetic Resonance Imaging
MRI
Neural Networks (Computer)
radiation therapy
synthetic CT
Time Factors
Tomography, X-Ray Computed
Title MR‐based synthetic CT generation using a deep convolutional neural network method
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.12155
https://www.ncbi.nlm.nih.gov/pubmed/28192624
https://www.proquest.com/docview/1868395434
Volume 44
WOSCitedRecordID wos000400572700020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 2473-4209
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006350
  issn: 0094-2405
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB5sq-LFR33VR4kgelpsHuvuHkUtHmwRtdDbkmSzRdBt6argzZ_gb_SXOMluK6KC4CmHTbJLZibzZWfyDcA-1SxVnPleIn3uCZGizRmpPJMaFlGhaaiVKzYRdLthvx9dlVmV9i5MwQ8x_eFmLcPt19bApcqPPklDH0aOGcGvQI2h2vpVqJ1dt3uX030YXWlxASUSNobgT6hnW-xoMvarM_qGML8CVudx2kv_-dZlWCxxJjkpFGMFZkxWh_lOGUmvw5xL_dT5Ktx0rt9f36w3S0j-kiEgxCHk9JYMHCO1FRyx2fEDIklizIjYRPVSYfENlhDTNS6dnBQVqdeg1z6_Pb3wylILnuZ4YvFSLsKWSUWgw5aWx6lGySEWVL6hqZG2Hr3inEuOiEAGXOuE-gGVAjcnZUIRJXwdqtkwM5tARIKnbSppqHBSIRFBMhlSiSfRSARBpBpwOFnzWJc85LYcxn1cMCiz-GEUu9VqwN6056jg3vipz0RsMRqGjXbIzAyf8tjWAeCRvTnbgI1CntNZbPSQHTN8cuDE9uv0cefKtVt_7bgNC8w6fpfbswPVx_GT2YVZ_fx4l4-bUAn6YbNU1A-LmekC
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB6q9XXx_ajPFURPod1HTIInUUvFtohW8BY2m40ImpZWBW_-BH-jv8TZTVIpKgiecsjuJuzM7Hy7M_sNwB5VLIk4c51YutwRIkGb0zJydKJZQIWivopssQmv3fZvb4PLEhwVd2EyfojhgZuxDLteGwM3B9LVL9bQx56lRnDHoCxQi1C9y6dX9ZvmcCFGX5rdQAmECSK4BfdsjVWLvqPe6BvEHEWs1uXU5_71s_MwmyNNcpypxgKUdLoIU608lr4Ikzb5Uw2W4Lp19fH2bvxZTAavKUJC7EJOOuTOclIb0RGTH39HJIm17hGTqp6rLH7BUGLah00oJ1lN6mW4qZ91ThpOXmzBURz3LE7ChV_TifCUX1PyMFEoO0SDkatpoqWpSB9xziVHTCA9rlRMXY9KgctTpH0RxHwFxtNuqteAiBj321RSP8JBhUQMyaRPJe5FA-F5QVSBg2LSQ5UzkZuCGA9hxqHMwsdeaGerArvDlr2MfeOnNoXcQjQNE--Qqe4-D0JTCYAH5u5sBVYzgQ5HMfFDdsjwzb6V26_Dh61L-1z_a8MdmG50Ws2wed6-2IAZZmCAzfTZhPGn_rPeggn18nQ_6G_n-voJB1vsCg
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFD7opuKL98u8RhB9KlsutS0-yXQobmPoBr6VNE2HoF3ZRfDNn-Bv9JeYpBcZKgg-5aFJWnJycr70nPMdgGMsSBRQYlsht6nFWKR0TvLAkpEkHmYCuyIwxSacdtt9ePA6M3Ce58Kk_BDFDzetGea81goukzCqfrGGPieGGsGehTLTNWRKUL68a_SaxUGsbGmageIx7USwc-7ZGqnmY6et0TeIOY1YjclpLP_rY1dgKUOa6CLdGqswI-M1WGhlvvQ1mDfBn2K0Dvetu4-3d23PQjR6jRUkVENQvYv6hpNaiw7p-Pg-4iiUMkE6VD3bsuoNmhLTNCagHKU1qTeg17jq1q-trNiCJai6s1gRZW5NRswRbk3ws0go2Sk0GNgSR5LrivQBpZRThQm4Q4UIse1gztTxFEiXeSHdhFI8iOU2IBaq-zbm2A3UpIwrDEm4i7m6i3rMcbygAqf5ovsiYyLXBTGe_JRDmfjPiW9WqwJHRc8kZd_4qU8uN1-phvZ38FgOJiNfVwKgns6drcBWKtBiFu0_JGdEPTkxcvt1er_VMe3OXzsewkLnsuE3b9q3u7BINAowgT57UBoPJ3If5sTL-HE0PMi26yevkuuF
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=MR-based+synthetic+CT+generation+using+a+deep+convolutional+neural+network+method&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Han%2C+Xiao&rft.date=2017-04-01&rft.eissn=2473-4209&rft.volume=44&rft.issue=4&rft.spage=1408&rft_id=info:doi/10.1002%2Fmp.12155&rft_id=info%3Apmid%2F28192624&rft.externalDocID=28192624
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0094-2405&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0094-2405&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0094-2405&client=summon