Artificial intelligence for analyzing orthopedic trauma radiographs Deep learning algorithms-are they on par with humans for diagnosing fractures?

Background and purpose - Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this stud...

Full description

Saved in:

Bibliographic Details
Published in:	Acta orthopaedica Vol. 88; no. 6; pp. 581 - 586
Main Authors:	Olczak, Jakub, Fahlberg, Niklas, Maki, Atsuto, Razavian, Ali Sharif, Jilert, Anthony, Stark, André, Sköldenberg, Olof, Gordon, Max
Format:	Journal Article
Language:	English
Published:	Sweden Taylor & Francis 02.11.2017 Medical Journals Sweden
Subjects:	Artificial Intelligence Fractures, Bone - diagnosis Humans Radiographic Image Enhancement Radiography - methods Reproducibility of Results
ISSN:	1745-3674, 1745-3682, 1745-3682
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Background and purpose - Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs. Methods - We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd's Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network's performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network. Results - All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen's kappa under these conditions was 0.76. Interpretation - This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics.
AbstractList	Background and purpose — Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs. Methods — We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd’s Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network’s performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network. Results — All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen’s kappa under these conditions was 0.76. Interpretation — This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics. Background and purpose - Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs. Methods - We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd's Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network's performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network. Results - All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen's kappa under these conditions was 0.76. Interpretation - This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics.
Author	Olczak, Jakub Razavian, Ali Sharif Fahlberg, Niklas Stark, André Jilert, Anthony Gordon, Max Maki, Atsuto Sköldenberg, Olof
AuthorAffiliation	2 Radiology clinic, Danderyd Hospital, Danderyd Hospital AB 1 Department of Clinical Sciences, Karolinska Institutet, Danderyd Hospital 3 Department of Robotics, Perception and Learning (RPL), School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden
AuthorAffiliation_xml	– name: 2 Radiology clinic, Danderyd Hospital, Danderyd Hospital AB – name: 1 Department of Clinical Sciences, Karolinska Institutet, Danderyd Hospital – name: 3 Department of Robotics, Perception and Learning (RPL), School of Computer Science and Communication, KTH Royal Institute of Technology, Stockholm, Sweden
Author_xml	– sequence: 1 givenname: Jakub surname: Olczak fullname: Olczak, Jakub organization: Department of Clinical Sciences, Karolinska Institutet – sequence: 2 givenname: Niklas surname: Fahlberg fullname: Fahlberg, Niklas organization: Radiology clinic, Danderyd Hospital, Danderyd Hospital AB – sequence: 3 givenname: Atsuto surname: Maki fullname: Maki, Atsuto organization: Department of Robotics, Perception and Learning (RPL), School of Computer Science and Communication, KTH Royal Institute of Technology – sequence: 4 givenname: Ali Sharif surname: Razavian fullname: Razavian, Ali Sharif organization: Department of Robotics, Perception and Learning (RPL), School of Computer Science and Communication, KTH Royal Institute of Technology – sequence: 5 givenname: Anthony surname: Jilert fullname: Jilert, Anthony organization: Radiology clinic, Danderyd Hospital, Danderyd Hospital AB – sequence: 6 givenname: André surname: Stark fullname: Stark, André organization: Department of Clinical Sciences, Karolinska Institutet – sequence: 7 givenname: Olof surname: Sköldenberg fullname: Sköldenberg, Olof organization: Department of Clinical Sciences, Karolinska Institutet – sequence: 8 givenname: Max surname: Gordon fullname: Gordon, Max email: max.gordon@ki.se organization: Department of Clinical Sciences, Karolinska Institutet
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/28681679$$D View this record in MEDLINE/PubMed https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-220304$$DView record from Swedish Publication Index (Kungliga Tekniska Högskolan) http://kipublications.ki.se/Default.aspx?queryparsed=id:137148607$$DView record from Swedish Publication Index (Karolinska Institutet)
BookMark	eNqFUl1v0zAUtdAQ2wo_AZQ_kGLHdmwLCVGVr0mTeAFerRt_pN7cuHIypvLrSZauojyMJ18fn3N87Xsu0VmXOofQa4KXBEv8lgjGaS3YssJELAlljHH1DF1MeElrWZ0da8HO0WXf32BMJVP4BTqvZC1JLdQFWq_yEHwwAWIRusHFGFrXGVf4lAvoIO5_h64tUh42aedsMMWQ4W4LRQYbUptht-lfouceYu9eHdYF-vH50_f11_L625er9eq6NJzioRTG-UpWjXAKO0yA11x5GDeE8oYoSY03jnkhlbEWc-yosIJ5xQ1g7i2jC3Q1-9oEN3qXwxbyXicI-gFIudUwvsZEpznlILmnRvKKMVBSNLTBThjujXUNGb3K2au_d7u75sTtAN2OldNM8ZqIJ_kfw8_Vw-23w0ZXFaZ46vX9zB_JW2eN68Z_iyey05MubHSbfmleKybHSS3Qm78NjsrH0Y0EPhNMTn2fnT9SCNZTRPRjRPQUEX2IyKh794_OhAGGkKY-Qvyv-sOsDt2YkC3cpxytHmAfU_YZOhN6TZ-2-AP6ONcg
CitedBy_id	crossref_primary_10_1038_s42256_019_0126_0 crossref_primary_10_1016_j_redii_2023_100029 crossref_primary_10_1007_s00117_023_01181_0 crossref_primary_10_3390_diagnostics13182927 crossref_primary_10_3390_diagnostics15050550 crossref_primary_10_1016_j_eswa_2024_125916 crossref_primary_10_1109_ACCESS_2021_3082952 crossref_primary_10_3390_biomedicines11113100 crossref_primary_10_23736_S0022_4707_24_15759_3 crossref_primary_10_1155_2021_2728388 crossref_primary_10_1049_cit2_12072 crossref_primary_10_1177_15589447241238372 crossref_primary_10_1371_journal_pone_0257361 crossref_primary_10_1007_s00068_020_01468_0 crossref_primary_10_1016_j_rcot_2021_01_025 crossref_primary_10_1053_j_ro_2020_07_015 crossref_primary_10_1002_jmri_26534 crossref_primary_10_1007_s00521_022_07510_z crossref_primary_10_1007_s00256_019_03284_z crossref_primary_10_1177_15563316251340303 crossref_primary_10_1016_j_jcrc_2024_154794 crossref_primary_10_1186_s12891_021_04714_7 crossref_primary_10_1002_jor_25538 crossref_primary_10_1002_jsp2_1327 crossref_primary_10_32604_cmc_2022_024965 crossref_primary_10_1136_jramc_2018_001055 crossref_primary_10_3390_cancers15154007 crossref_primary_10_1016_j_otsr_2021_102837 crossref_primary_10_1007_s11701_025_02561_5 crossref_primary_10_1038_s41598_022_12453_5 crossref_primary_10_3390_app11198791 crossref_primary_10_3390_app10144703 crossref_primary_10_1097_MD_0000000000043716 crossref_primary_10_1016_j_compbiomed_2025_110683 crossref_primary_10_1016_j_bbe_2020_12_002 crossref_primary_10_1007_s44411_025_00170_0 crossref_primary_10_3390_medicina58080998 crossref_primary_10_1016_j_clinimag_2020_01_008 crossref_primary_10_1177_23202068211005611 crossref_primary_10_1007_s10462_025_11296_6 crossref_primary_10_2147_JMDH_S536633 crossref_primary_10_1007_s10140_020_01773_6 crossref_primary_10_1097_CORR_0000000000001360 crossref_primary_10_1097_BSD_0000000000001119 crossref_primary_10_3233_THC_220501 crossref_primary_10_3389_fmed_2020_573522 crossref_primary_10_1007_s00068_020_01444_8 crossref_primary_10_1055_a_1511_8595 crossref_primary_10_1007_s10278_022_00741_5 crossref_primary_10_1007_s12647_022_00541_w crossref_primary_10_1007_s00586_021_06799_z crossref_primary_10_1109_JBHI_2022_3152267 crossref_primary_10_1186_s40634_023_00642_8 crossref_primary_10_2196_36199 crossref_primary_10_1007_s00590_024_04032_3 crossref_primary_10_1097_CORR_0000000000000848 crossref_primary_10_12998_wjcc_v11_i18_4231 crossref_primary_10_1007_s00330_021_07811_2 crossref_primary_10_1016_j_annemergmed_2019_12_024 crossref_primary_10_1016_j_jestch_2024_101883 crossref_primary_10_1016_j_jcot_2019_06_012 crossref_primary_10_31893_multirev_2025218 crossref_primary_10_1016_j_ejrad_2020_109188 crossref_primary_10_1302_0301_620X_107B6_BJJ_2024_1567_R1 crossref_primary_10_1038_s41598_021_81236_1 crossref_primary_10_52560_2713_0118_2025_4_81_91 crossref_primary_10_3390_bioengineering10060735 crossref_primary_10_1016_j_crad_2019_10_022 crossref_primary_10_1002_jbmr_4146 crossref_primary_10_4103_digm_digm_10_21 crossref_primary_10_1007_s42979_024_03155_y crossref_primary_10_3390_jimaging10120322 crossref_primary_10_1007_s00330_021_08014_5 crossref_primary_10_1002_cpe_7307 crossref_primary_10_1080_20479700_2022_2097765 crossref_primary_10_1007_s11914_021_00701_y crossref_primary_10_1177_23259671211014206 crossref_primary_10_1016_j_jham_2025_100339 crossref_primary_10_1007_s00247_023_05621_w crossref_primary_10_1016_j_arth_2023_08_018 crossref_primary_10_1016_j_diii_2022_06_004 crossref_primary_10_1016_j_injury_2022_04_013 crossref_primary_10_3389_fimmu_2023_1278247 crossref_primary_10_1016_j_jbo_2024_100648 crossref_primary_10_1002_rmb2_12267 crossref_primary_10_3390_diagnostics14060596 crossref_primary_10_1002_rmb2_12266 crossref_primary_10_3389_fendo_2021_720728 crossref_primary_10_2196_19416 crossref_primary_10_13005_bpj_3169 crossref_primary_10_3390_app10041507 crossref_primary_10_3390_diagnostics12030632 crossref_primary_10_2106_JBJS_19_01128 crossref_primary_10_1155_2021_7006541 crossref_primary_10_3389_fpubh_2022_949366 crossref_primary_10_3390_medicina57040351 crossref_primary_10_1002_ima_22849 crossref_primary_10_1186_s12891_024_07798_z crossref_primary_10_1007_s00256_021_03709_8 crossref_primary_10_1186_s12891_021_04260_2 crossref_primary_10_1007_s00330_022_09349_3 crossref_primary_10_3390_diagnostics13091657 crossref_primary_10_1007_s00068_024_02557_0 crossref_primary_10_3233_IDA_240431 crossref_primary_10_1007_s00330_022_09289_y crossref_primary_10_1016_j_crad_2020_05_021 crossref_primary_10_1007_s11548_023_02831_3 crossref_primary_10_1186_s40798_024_00786_6 crossref_primary_10_1002_hcs2_72 crossref_primary_10_1111_edt_12965 crossref_primary_10_2106_JBJS_RVW_22_00086 crossref_primary_10_2106_JBJS_OA_22_00030 crossref_primary_10_1097_JS9_0000000000002187 crossref_primary_10_1016_j_cjtee_2024_10_006 crossref_primary_10_1007_s00068_022_02128_1 crossref_primary_10_1177_17504589231179302 crossref_primary_10_1007_s00068_024_02731_4 crossref_primary_10_1007_s12178_020_09600_8 crossref_primary_10_1155_2022_5841451 crossref_primary_10_4103_jfsm_jfsm_88_23 crossref_primary_10_1002_rse2_195 crossref_primary_10_1007_s12553_021_00543_9 crossref_primary_10_1097_CORR_0000000000002385 crossref_primary_10_1007_s00256_020_03463_3 crossref_primary_10_3892_mco_2019_1932 crossref_primary_10_1371_journal_pdig_0000560 crossref_primary_10_1016_j_compmedimag_2021_101937 crossref_primary_10_1001_jamanetworkopen_2021_6096 crossref_primary_10_1016_j_msksp_2018_11_012 crossref_primary_10_1038_s41746_019_0105_1 crossref_primary_10_1186_s13102_021_00243_x crossref_primary_10_1007_s10140_020_01767_4 crossref_primary_10_1371_journal_pone_0248809 crossref_primary_10_1016_j_rcot_2023_06_014 crossref_primary_10_1016_j_legalmed_2022_102048 crossref_primary_10_1016_j_semss_2021_100876 crossref_primary_10_1109_ACCESS_2020_3004766 crossref_primary_10_3390_jcm11071885 crossref_primary_10_1007_s00256_020_03410_2 crossref_primary_10_1186_s12891_024_07884_2 crossref_primary_10_1007_s00142_023_00657_4 crossref_primary_10_1186_s13244_020_00932_0 crossref_primary_10_1111_anae_16733 crossref_primary_10_3390_jimaging7060100 crossref_primary_10_3390_jpm11060482 crossref_primary_10_7759_cureus_51631 crossref_primary_10_1007_s00256_020_03433_9 crossref_primary_10_3389_fbioe_2018_00075 crossref_primary_10_4103_jfsm_jfsm_35_24 crossref_primary_10_1016_j_otsr_2023_103652 crossref_primary_10_1186_s12891_024_07244_0 crossref_primary_10_1148_radiol_2018180547 crossref_primary_10_3390_jimaging9090180 crossref_primary_10_1097_CORR_0000000000001318 crossref_primary_10_1007_s11282_020_00468_5 crossref_primary_10_1016_j_arth_2019_05_048 crossref_primary_10_1016_j_cmpb_2021_106229 crossref_primary_10_1007_s10278_021_00519_1 crossref_primary_10_1016_j_knee_2019_11_020 crossref_primary_10_3389_fbioe_2025_1502669 crossref_primary_10_3390_bioengineering11040338 crossref_primary_10_1002_jor_26109 crossref_primary_10_1109_MM_2018_112130030 crossref_primary_10_1016_j_fas_2022_05_005 crossref_primary_10_1016_j_jcot_2020_03_006 crossref_primary_10_3389_fendo_2023_1025749 crossref_primary_10_3390_app14083451 crossref_primary_10_1002_jbmr_4292 crossref_primary_10_1016_j_ocl_2022_11_004 crossref_primary_10_1080_20479700_2022_2161146 crossref_primary_10_1097_CORR_0000000000001679 crossref_primary_10_1016_j_rhum_2023_07_018 crossref_primary_10_1007_s10742_025_00340_1 crossref_primary_10_1038_s41598_023_34176_x crossref_primary_10_3390_diagnostics12102420 crossref_primary_10_1186_s12880_023_00975_x crossref_primary_10_1016_j_engappai_2024_108326 crossref_primary_10_1371_journal_pone_0289808 crossref_primary_10_1002_jcu_23321 crossref_primary_10_1007_s12647_023_00633_1 crossref_primary_10_1002_mp_14705 crossref_primary_10_1109_ACCESS_2020_3029039 crossref_primary_10_1007_s00521_025_11539_1 crossref_primary_10_1177_20552076241279238 crossref_primary_10_2478_mspe_2022_0014 crossref_primary_10_1007_s00330_020_06856_z crossref_primary_10_1007_s10278_019_00226_y crossref_primary_10_1016_j_arth_2020_04_059 crossref_primary_10_1007_s00167_022_07220_y crossref_primary_10_1109_TMI_2021_3134650 crossref_primary_10_1371_journal_pone_0322051 crossref_primary_10_1016_j_ejrad_2020_108925 crossref_primary_10_1097_BPO_0000000000002428 crossref_primary_10_3390_app11146293 crossref_primary_10_3390_app142411652 crossref_primary_10_1007_s11548_020_02150_x crossref_primary_10_32604_cmc_2024_047377 crossref_primary_10_1007_s00330_024_10625_7 crossref_primary_10_1259_bjr_20221031 crossref_primary_10_4103_jhrs_jhrs_53_21 crossref_primary_10_5312_wjo_v13_i6_603 crossref_primary_10_1097_PRS_0000000000007627 crossref_primary_10_21015_vtse_v12i4_1971 crossref_primary_10_1111_1754_9485_12828 crossref_primary_10_2196_29839 crossref_primary_10_1002_jor_24617 crossref_primary_10_3390_jimaging7070105 crossref_primary_10_1016_j_asmart_2025_01_001 crossref_primary_10_3390_healthcare11111524 crossref_primary_10_1109_JPROC_2023_3273520 crossref_primary_10_2106_JBJS_24_00938 crossref_primary_10_1007_s00068_025_02931_6 crossref_primary_10_3390_jimaging11080281 crossref_primary_10_5312_wjo_v12_i9_685 crossref_primary_10_1002_jmri_27001 crossref_primary_10_1097_BSD_0000000000001082 crossref_primary_10_1186_s12891_025_09161_2 crossref_primary_10_1002_vro2_55 crossref_primary_10_1186_s12880_024_01316_2 crossref_primary_10_3389_fmedt_2022_995526 crossref_primary_10_2106_JBJS_RVW_23_00232 crossref_primary_10_3390_math9243227 crossref_primary_10_1177_17531934231152592 crossref_primary_10_3390_app14010133 crossref_primary_10_1007_s10140_024_02300_7 crossref_primary_10_1038_s41746_020_00352_w crossref_primary_10_1007_s42417_023_01165_3 crossref_primary_10_1016_j_wneu_2024_04_025 crossref_primary_10_3390_math10162939 crossref_primary_10_1088_1742_6596_2637_1_012033 crossref_primary_10_1007_s00330_019_06167_y crossref_primary_10_1007_s10278_018_0167_7 crossref_primary_10_1007_s00132_023_04436_9 crossref_primary_10_1089_heat_2019_0006 crossref_primary_10_1007_s00784_022_04427_8 crossref_primary_10_1007_s00586_022_07309_5 crossref_primary_10_1007_s00256_021_03876_8 crossref_primary_10_1007_s11548_021_02552_5 crossref_primary_10_1038_s41598_024_71654_2 crossref_primary_10_12677_acm_2025_1592603 crossref_primary_10_1002_ca_23615 crossref_primary_10_1016_j_suc_2022_11_002 crossref_primary_10_1016_j_future_2018_10_050 crossref_primary_10_7759_cureus_58364 crossref_primary_10_1186_s13244_022_01234_3 crossref_primary_10_1007_s44326_025_00066_x crossref_primary_10_1097_CORR_0000000000001352 crossref_primary_10_1186_s13018_021_02845_0 crossref_primary_10_1007_s00259_019_04372_x crossref_primary_10_1016_j_jcot_2023_102312 crossref_primary_10_1016_j_bushor_2025_06_007 crossref_primary_10_1177_02841851221122424 crossref_primary_10_1007_s13755_024_00288_5 crossref_primary_10_1159_000542228 crossref_primary_10_1007_s10140_023_02154_5 crossref_primary_10_1038_s41598_022_10666_2 crossref_primary_10_1016_j_arthro_2022_03_037 crossref_primary_10_1007_s00256_021_03733_8 crossref_primary_10_1016_j_jbspin_2022_105493 crossref_primary_10_1007_s00264_024_06125_4 crossref_primary_10_3390_app11188485 crossref_primary_10_1302_0301_620X_101B12_BJJ_2019_0850_R1 crossref_primary_10_1177_0846537120941671 crossref_primary_10_1186_s12891_019_2579_z crossref_primary_10_1097_CORR_0000000000001448 crossref_primary_10_1097_CORR_0000000000001685 crossref_primary_10_1308_rcsann_2023_0017 crossref_primary_10_3390_diagnostics14171879 crossref_primary_10_2519_josptmethods_2024_0086 crossref_primary_10_3390_life13010133 crossref_primary_10_1007_s43465_024_01130_6 crossref_primary_10_1016_j_knee_2025_02_001 crossref_primary_10_1080_14737167_2023_2279107 crossref_primary_10_1016_j_ejrad_2020_109373 crossref_primary_10_1007_s00256_018_3016_3 crossref_primary_10_1007_s00586_022_07121_1 crossref_primary_10_2106_JBJS_RVW_21_00142 crossref_primary_10_3389_fped_2022_1005099 crossref_primary_10_1166_jmihi_2021_3899 crossref_primary_10_1016_j_injury_2024_111997 crossref_primary_10_1007_s10278_020_00399_x crossref_primary_10_1007_s43465_019_00023_3 crossref_primary_10_1016_j_engappai_2023_106165 crossref_primary_10_1148_ryai_2019180001 crossref_primary_10_1016_j_clinbiomech_2025_106625 crossref_primary_10_2478_jaiscr_2022_0007
Cites_doi	10.1109/TMI.2016.2535302 10.1126/scitranslmed.3002564 10.1007/s11263-015-0816-y 10.1109/ICCV.2015.123 10.3113/FAI.2011.0861 10.1016/S0363-5023(96)80006-2 10.1117/12.2083124 10.1097/01.bot.0000155310.04886.37 10.1308/rcsann.2016.0237 10.1109/CVPR.2015.7298712 10.1109/WCICA.2014.7052856 10.1007/s00586-017-4956-3 10.1038/nature14539 10.1145/2647868.2654889
ContentType	Journal Article
Copyright	2017 The Author(s). Published by Taylor & Francis on behalf of the Nordic Orthopedic Federation. 2017
Copyright_xml	– notice: 2017 The Author(s). Published by Taylor & Francis on behalf of the Nordic Orthopedic Federation. 2017
DBID	0YH AAYXX CITATION CGR CUY CVF ECM EIF NPM 5PM ADTPV AOWAS D8V D8T ZZAVC DOA
DOI	10.1080/17453674.2017.1344459
DatabaseName	Taylor & Francis Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed PubMed Central (Full Participant titles) SwePub SwePub Articles SWEPUB Kungliga Tekniska Högskolan SWEPUB Freely available online SwePub Articles full text DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid)
DatabaseTitleList	MEDLINE
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 0YH name: Taylor & Francis Online url: https://www.tandfonline.com sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
EISSN	1745-3682
EndPage	586
ExternalDocumentID	oai_doaj_org_article_535a85f3c85244a987b3b0e7c5fcdeb1 oai_swepub_ki_se_495617 oai_DiVA_org_kth_220304 PMC5694800 28681679 10_1080_17453674_2017_1344459 1344459
Genre	Article Journal Article
GroupedDBID	--- .55 04C 0YH 23M 2QV 2WC 34G 36B 39C 4.4 5GY 5RE 5VS 6J9 6PF AAFWJ AAWTL ABDBF ABNNA ACGFO ACGFS ACUHS ADBBV ADCVX ADOJX ADRAZ ADRBQ AEGXH AENEX AFKVX AFPKN AJWEG ALMA_UNASSIGNED_HOLDINGS AOIJS AQTUD BAWUL BCNDV BMSDO CAG CS3 DXH E3Z EAP EBC EBD EBS EBX ECF ECT ECV EHN EIHBH EJD EMB EMK EMOBN ENC ENX EPL EPT ESX F5P GROUPED_DOAJ GX1 H13 HYE KQ8 M48 M4Z O9- OK1 OVT P2P Q~Q RDKPK RNS RPM SV3 TDBHL TFDNU TFW TR2 TUS W2D WQ9 X7M ~1N AAYXX CITATION .GJ 3O- 53G AALIY AFFNX AWYRJ C1A CGR COF CUY CVF ECM EIF NPM O5R O5S ZXP 5PM ADTPV AOWAS D8V D8T ZZAVC
ID	FETCH-LOGICAL-c530t-7cef282b7e90e01a5659fae90135b1983cfce4f789cdd050e37d74f95ca05fd43
IEDL.DBID	0YH
ISICitedReferencesCount	315
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000416605900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1745-3674 1745-3682
IngestDate	Fri Oct 03 12:34:27 EDT 2025 Tue Nov 25 03:38:45 EST 2025 Tue Nov 04 17:23:01 EST 2025 Tue Nov 04 01:52:12 EST 2025 Mon Jul 21 06:05:42 EDT 2025 Sat Nov 29 06:10:28 EST 2025 Tue Nov 18 22:04:28 EST 2025 Mon Oct 20 23:47:29 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
License	open-access: https://creativecommons.org/licenses/by-nc/3.0: This is an Open Access article distributed under the terms of the Creative Commons Attribution-Non-Commercial License (https://creativecommons.org/licenses/by-nc/3.0) This is an Open Access article distributed under the terms of the Creative Commons Attribution-Non-Commercial License (https://creativecommons.org/licenses/by-nc/3.0)
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c530t-7cef282b7e90e01a5659fae90135b1983cfce4f789cdd050e37d74f95ca05fd43
OpenAccessLink	https://www.tandfonline.com/doi/abs/10.1080/17453674.2017.1344459
PMID	28681679
PageCount	6
ParticipantIDs	swepub_primary_oai_DiVA_org_kth_220304 informaworld_taylorfrancis_310_1080_17453674_2017_1344459 doaj_primary_oai_doaj_org_article_535a85f3c85244a987b3b0e7c5fcdeb1 swepub_primary_oai_swepub_ki_se_495617 pubmed_primary_28681679 crossref_citationtrail_10_1080_17453674_2017_1344459 pubmedcentral_primary_oai_pubmedcentral_nih_gov_5694800 crossref_primary_10_1080_17453674_2017_1344459
PublicationCentury	2000
PublicationDate	2017-11-02
PublicationDateYYYYMMDD	2017-11-02
PublicationDate_xml	– month: 11 year: 2017 text: 2017-11-02 day: 02
PublicationDecade	2010
PublicationPlace	Sweden
PublicationPlace_xml	– name: Sweden
PublicationTitle	Acta orthopaedica
PublicationTitleAlternate	Acta Orthop
PublicationYear	2017
Publisher	Taylor & Francis Medical Journals Sweden
Publisher_xml	– name: Taylor & Francis – name: Medical Journals Sweden
References	Rhodes M. (CIT0017) 2016 CIT0010 CIT0012 CIT0011 CIT0013 CIT0016 CIT0015 Hardy Q. (CIT0009) 2016 CIT0018 Chatfield K (CIT0006) 2014 Erickson B J (CIT0008) 2017; 37 CIT0019 DeAngelis S F. (CIT0007) 2014 Krizhevsky A (CIT0014) 2012 CIT0021 CIT0020 CIT0001 CIT0023 CIT0022 Zbontar J (CIT0025) 2016; 17 CIT0003 CIT0002 CIT0024 CIT0005 CIT0004 29106336 - Acta Orthop. 2017 Dec;88(6):577
References_xml	– volume-title: Machine learning: Bane or blessing for mankind year: 2014 ident: CIT0007 – ident: CIT0024 doi: 10.1109/TMI.2016.2535302 – ident: CIT0011 – ident: CIT0005 doi: 10.1126/scitranslmed.3002564 – ident: CIT0018 doi: 10.1007/s11263-015-0816-y – ident: CIT0010 doi: 10.1109/ICCV.2015.123 – ident: CIT0019 doi: 10.3113/FAI.2011.0861 – ident: CIT0023 – ident: CIT0001 doi: 10.1016/S0363-5023(96)80006-2 – ident: CIT0004 doi: 10.1117/12.2083124 – ident: CIT0002 doi: 10.1097/01.bot.0000155310.04886.37 – ident: CIT0016 – volume: 17 start-page: 2 issue: 1 year: 2016 ident: CIT0025 publication-title: J Mach Learn Res – ident: CIT0020 doi: 10.1308/rcsann.2016.0237 – volume: 37 start-page: 505 issue: 2 year: 2017 ident: CIT0008 publication-title: Radiogr Rev Publ Radiol Soc N Am Inc – ident: CIT0022 doi: 10.1109/CVPR.2015.7298712 – ident: CIT0021 doi: 10.1109/WCICA.2014.7052856 – ident: CIT0003 – ident: CIT0012 doi: 10.1007/s00586-017-4956-3 – ident: CIT0015 doi: 10.1038/nature14539 – ident: CIT0013 doi: 10.1145/2647868.2654889 – start-page: 1097 volume-title: Adv Neural Inf Process Syst 25 year: 2012 ident: CIT0014 – volume-title: Return of the devil in the details: Delving deep into convolutional nets year: 2014 ident: CIT0006 – volume-title: Artificial intelligence software is booming: But why now year: 2016 ident: CIT0009 – volume-title: Whoa, Google’s AI is really good at Pictionary year: 2016 ident: CIT0017 – reference: 29106336 - Acta Orthop. 2017 Dec;88(6):577
SSID	ssj0038490
Score	2.643409
Snippet	Background and purpose - Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and... Background and purpose — Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and...
SourceID	doaj swepub pubmedcentral pubmed crossref informaworld
SourceType	Open Website Open Access Repository Index Database Enrichment Source Publisher
StartPage	581
SubjectTerms	Artificial Intelligence Fractures, Bone - diagnosis Humans Radiographic Image Enhancement Radiography - methods Reproducibility of Results
Subtitle	Deep learning algorithms-are they on par with humans for diagnosing fractures?
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZQxYELAvFaXvIBcUvrxPba5oIKpeJUcQDUm-X40Y3aZlfZLBKc-BHwB_kleOzsKqmQ9sItdmL5MRPPjMfzDUKv6pqUnom6sNTZgomgCulEtFJCzUrDDPM-J5sQZ2fy_Fx9GqX6gjthGR44L9wRp9xIHqiVPEoiE03kmtbEC8uDdXGjgd03aj1bYyrvwVQyNYRC8oLOBdvG7khyBHVQBde6xGFJGWMAVDqSSgm8_wZ06UhA3bw8OYEYTWLp9B66O-iT-DjP4z665dsH6DcUMzQEbkaYmzj2hA3AkPyIEguDy2a5Ak8Njn1srg3ujGsyhvX6DT7xfoWHrBIX2FxdLLumX1yv__z8ZTqPo-b4HS9bvDIdhtNcnNL9rVMfLl_gg3YBwrA20ah_-xB9Of3w-f3HYsi_UFhOSV8I60O0yGrhFfGkNFH3U8HEQkl5XSpJbbCeBSGVdY5w4qlwggXFrSE8OEYfoYN22fonCMdtxJHAZWmNieLQ1FHTqojwUvpokzo_Q2y7_toO4OSQI-NKlwOG6ZZsGsimB7LN0OGu2Sqjc-xr8A6Iu_sYwLVTRWQ5PbCc3sdyM6TGrKH7dLYSciIUTfcM4HFmn90QKjmX4AubITFhrMkYp2_aZpGAwPlcsajwz9DrzIKTJifN1-M0rct-oasKXOD__nCouoxPXoO9XIqn_2OZnqE7MPMUuFk9Rwd9t_Ev0G37rW_W3cv0v_4FCOlGYQ priority: 102 providerName: Directory of Open Access Journals
Title	Artificial intelligence for analyzing orthopedic trauma radiographs
URI	https://www.tandfonline.com/doi/abs/10.1080/17453674.2017.1344459 https://www.ncbi.nlm.nih.gov/pubmed/28681679 https://pubmed.ncbi.nlm.nih.gov/PMC5694800 https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-220304 http://kipublications.ki.se/Default.aspx?queryparsed=id:137148607 https://doaj.org/article/535a85f3c85244a987b3b0e7c5fcdeb1
Volume	88
WOSCitedRecordID	wos000416605900005&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1745-3682 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0038490 issn: 1745-3674 databaseCode: DOA dateStart: 20090101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVAWR databaseName: Taylor & Francis Online customDbUrl: eissn: 1745-3682 dateEnd: 20211130 omitProxy: false ssIdentifier: ssj0038490 issn: 1745-3674 databaseCode: 0YH dateStart: 20091001 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis – providerCode: PRVAWR databaseName: Taylor & Francis Online Journals customDbUrl: eissn: 1745-3682 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0038490 issn: 1745-3674 databaseCode: TFW dateStart: 20050101 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagcODCQ7xSoMoBcUuxY3ttH0th1VPFoUA5WX7SqGW32k059NczdpzVpgL1AJcodjLReDL2zNjjzwi9tRaTwIRtHPWuYSKqRnoBUUq0jBhmWAjDYRPi-FienqrPJZtwXdIqUwwdB6CIPFanzm3sesyIew9ONKczkWZEiNgnlDHG1V10r4XQJGV14e9H42BMJVNlTyRvEs24iedvn5mYp4zifwPDdMtS3cyinGCNZvs0f_QfWvYYPSzOaX0waNMTdCcsnqLDVBxwJupuC8CzBm5rkzBNrsH81Wn9Z3mZln1q4PPqp6lXxncDIPb6Gfoy_3RyeNSUoxcaxynuG-FChGDMiqBwwMSA26eigQKh3BIlqYsusCikct5jjgMVXrCouDOYR8_oc7SzWC7CS1TDCOJx5JI4Y8ASGgtOVotFkDJAOOpDhdgoce0KLnk6HuNCkwJfOkpFJ6noIpUK7W_ILgdgjtsIPqTfuXk54WrniuXqhy7dVHPKjeSROsnB7zFKCkstDsLx6DyYtQqpbWXQfZ5WicMZKJrewsCLQWE2LLRyJtMyWIXERJUmPE6fLLqzjAHOZ4qBr1-hd4PSTUg-dl8PcrPO-zPdtmn1-88vlqpzuAs6hcpE7P5DC1-hB6mYt2q2r9FOv7oKb9B996vv1qu93DH38qQHXE_m334DIeU4iQ
linkProvider	Taylor & Francis
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagIMGFh3iF8sgBcUuxY3ttH_taFVH2tEBvluNHGxV2q23KgV-Px05WmwrUA9zi2BONnbFnxvZ8g9C7psHEM9FUljpbMRFUJZ2IXkpoGDHMMO9zsgkxm8mTE7UZCwPXKsGHDhkoIq3VMLlhM3q4EvchWtGcTgRsiRCxQyhjjKvb6A6Puhau9c2n34bVmEqm-qBIXgHNEMXzt8-M9FOC8b8GYrqhqq5foxyBjSYFNX34P7r2CD3ozdNyN8vTY3TLL56gfShmpImy3YDwLCO7pQFUk19RAZZwArS8gIOfMjJ69cOUK-PaDIl9-RR9mR7O94-qPvlCZTnFXSWsD9Eda4RX2GNiouGngokFQnlDlKQ2WM-CkMo6hzn2VDjBguLWYB4co8_Q1mK58C9QGdcQhwOXxBoTdaFpoplVY-Gl9NEhdb5AbBhybXtkckiQ8V2THsB0GBUNo6L7USnQzprsIkNz3ESwB_9z3RiQtdOL5epU9xNVc8qN5IFayaPlY5QUDW2wF5YH66JiK5DalAbdpY2VkLOgaHoDA8-zxKxZqOVEwkFYgcRIlkY8jmsW7VlCAecTxaK1X6D3WepGJAft193UrfPuTNc1nH__uWH_6jw-eQ3OMhEv_6GHb9G9o_nnY338cfZpG92HqhS4Wb9CW93qyr9Gd-3Prr1cvUmz9Dd5JDqs
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagINQLD_EKzxwQtxQ7ttf2sbSsQKBVDwV6s_xso8LuajftgV-PX1ltKlAPcItjTzR2xp4Zj_0NAG-0hsgRphuDrWkI86LhlgUvxWuCFFHEuZxsgs1m_OREHJXThOtyrDL60D4DRaS1Ok7upfXDibh3wYimeMLijghiewgTQqi4CW4lcKwg0sfT78NijDkR5U4kbSLNcInnb58ZqaeE4n8Fw3RLU109RTnCGk36aXrvP_TsPrhbjNN6P0vTA3DDzR-Cg1jMOBN1twXgWQduaxUxTX4F9VfH-M9iGcM-deDz4qeqV8p2GRB7_Qh8nX44PvjYlNQLjaEY9g0zzgdnTDMnoINIBbNPeBUKCFONBMfGG0c848JYCyl0mFlGvKBGQeotwY_Bznwxd09BHVYQCz3lyCgVNKHSwchqIXOcu-COWlcBMoy4NAWXPKbH-CFRgS8dRkXGUZFlVCqwtyFbZmCO6wjex9-5aRxxtdOLxepUlmkqKaaKU48Np8HuUYIzjTV0zFBvbFBrFRDbwiD7tK3icw4Uia9h4EkWmA0LLZ_wGAarABuJ0ojHcc28O0sY4HQiSLD1K_A2C92I5LD7tp-6dd6fybaN0e8_NyyvzsOTk9FVRuzZP_TwNbhzdDiVXz7NPj8Hu7Em3dpsX4CdfnXhXoLb5rLv1qtXaY7-BmXcOVA
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=Artificial+intelligence+for+analyzing+orthopedic+trauma+radiographs&rft.jtitle=Acta+orthopaedica&rft.au=Olczak%2C+Jakub&rft.au=Fahlberg%2C+Niklas&rft.au=Maki%2C+Atsuto&rft.au=Razavian%2C+Ali+Sharif&rft.date=2017-11-02&rft.issn=1745-3674&rft.eissn=1745-3682&rft.volume=88&rft.issue=6&rft.spage=581&rft.epage=586&rft_id=info:doi/10.1080%2F17453674.2017.1344459&rft.externalDBID=n%2Fa&rft.externalDocID=10_1080_17453674_2017_1344459
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1745-3674&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1745-3674&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1745-3674&client=summon