Deep Learning-Assisted Diagnosis of Pediatric Skull Fractures on Plain Radiographs
Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) an...
Saved in:
Published in | Korean journal of radiology Vol. 23; no. 3; pp. 343 - 354 |
---|---|
Main Authors | , , , , , , , , , , , |
Format | Journal Article |
Language | Korean |
Published |
2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs. |
---|---|
AbstractList | Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs. |
Author | Jae Won Choi Yun Young Lee Seok Young Koh Jung-Eun Cheon Ji Hoon Phi June Young Seo Young Hun Choi Injoon Kim Jaekwang Yang Ji Young Ha Yeon Jin Cho Woo Sun Kim |
Author_xml | – sequence: 1 fullname: Jae Won Choi – sequence: 2 fullname: Yeon Jin Cho – sequence: 3 fullname: Ji Young Ha – sequence: 4 fullname: Yun Young Lee – sequence: 5 fullname: Seok Young Koh – sequence: 6 fullname: June Young Seo – sequence: 7 fullname: Young Hun Choi – sequence: 8 fullname: Jung-Eun Cheon – sequence: 9 fullname: Ji Hoon Phi – sequence: 10 fullname: Injoon Kim – sequence: 11 fullname: Jaekwang Yang – sequence: 12 fullname: Woo Sun Kim |
BookMark | eNqNjNEKgjAYRkcUpNU77KZLYf6zdJeSSVSQWPcy3LTlmLLp--dFD9DVx-EcPh8tTW_kAnlAyCFIKCVL5IUALDgyYGvkO_chBBhJIg-VmZQDvktujTJtkDqn3CgFzhRvTT8D7htcSKH4aFWNn92kNc4tr8fJylkaXGiuDC65UH1r-fB2W7RquHZy99sN2ufn1-kSdPO1qoxwurqmtwcQgDCJIwphHDFK_-2-3nRAgg |
ContentType | Journal Article |
DBID | JDI |
DEWEY | 616.0757 |
DatabaseName | KoreaScience (Open Access) |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine |
DocumentTitleAlternate | Deep Learning-Assisted Diagnosis of Pediatric Skull Fractures on Plain Radiographs |
EISSN | 2005-8330 |
EndPage | 354 |
ExternalDocumentID | JAKO202218743217493 |
GroupedDBID | --- 29L 2WC 5-W 53G 5GY 8JR 8XY 9ZL ADBBV ADRAZ AENEX AFKRA ALMA_UNASSIGNED_HOLDINGS AOIJS BAWUL BENPR CCPQU CS3 DIK DU5 E3Z EBD EF. EMOBN F5P FRP GX1 HYE JDI KQ8 M48 M~E O5R O5S OK1 P6G PIMPY RNS RPM SV3 TR2 W2D WH7 XSB |
ID | FETCH-kisti_ndsl_JAKO2022187432174933 |
IEDL.DBID | M48 |
ISSN | 1229-6929 |
IngestDate | Wed Jul 17 02:10:56 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | true |
Issue | 3 |
Keywords | Deep learning Plain radiograph Skull fracture Artificial intelligence Pediatric |
Language | Korean |
LinkModel | DirectLink |
MergedId | FETCHMERGED-kisti_ndsl_JAKO2022187432174933 |
Notes | KISTI1.1003/JNL.JAKO202218743217493 |
OpenAccessLink | http://journals.scholarsportal.info/openUrl.xqy?issn=1229-6929&volume=23&issue=3&spage=343 |
ParticipantIDs | kisti_ndsl_JAKO202218743217493 |
PublicationCentury | 2000 |
PublicationDate | 2022 |
PublicationDateYYYYMMDD | 2022-01-01 |
PublicationDate_xml | – year: 2022 text: 2022 |
PublicationDecade | 2020 |
PublicationTitle | Korean journal of radiology |
PublicationTitleAlternate | Korean journal of radiology : official journal of the Korean Radiological Society |
PublicationYear | 2022 |
SSID | ssj0029084 |
Score | 4.600686 |
Snippet | Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children.... |
SourceID | kisti |
SourceType | Open Access Repository |
StartPage | 343 |
Title | Deep Learning-Assisted Diagnosis of Pediatric Skull Fractures on Plain Radiographs |
URI | http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO202218743217493&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01 |
Volume | 23 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV3dS8MwED_GBPFF_MTPkgfdW6QmaUefZLqVMekc1cHeRrqkUlZaXTfQ_96kicUH0dcQQrjLcffL3f0O4Mr3-cInPMGSCoZZmkgcUJFgFayngt5Kj9Ts-tHYH07ZaObNWvDdQmAFWP0K7fQ8qekqv_l4_7wz1kp07YZy8B1ryoR2MovyjD1SVhOBEqoff8SaBAMJ3HoYcXOCik11wJb9cC7hHuzaqBD1jBr3obUsD2A7snnvQ4j7Ur4hy4X6ipVMtXYE6ptCuaxCZYqaqRvoeamAJQp1A9RGwWlUFmiS86xAMReZ4aiujuA6HLw8DHF9oXkhqnw-6j0-EeVu9QQ9qlFEQOkxtIuykCeAuiwJXM4XmnKYpVRwwn3JuEdl1-OUuafg_H3W2X8bzmFHr5i_hwtor1cbeam88TpxYOt-MJ7ETi3fLzoujes |
link.rule.ids | 230,315,786,790,891,2236,4043 |
linkProvider | Scholars Portal |
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=Deep+Learning-Assisted+Diagnosis+of+Pediatric+Skull+Fractures+on+Plain+Radiographs&rft.jtitle=Korean+journal+of+radiology&rft.au=Jae+Won+Choi&rft.au=Yeon+Jin+Cho&rft.au=Ji+Young+Ha&rft.au=Yun+Young+Lee&rft.date=2022&rft.issn=1229-6929&rft.eissn=2005-8330&rft.volume=23&rft.issue=3&rft.spage=343&rft.epage=354&rft.externalDBID=n%2Fa&rft.externalDocID=JAKO202218743217493 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1229-6929&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1229-6929&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1229-6929&client=summon |