Automatic detection of pulmonary embolism in computed tomography pulmonary angiography using Scaled‐YOLOv4

Background Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and mi...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Medical physics (Lancaster) Ročník 50; číslo 7; s. 4340 - 4350
Hlavní autori:	Xu, Haijun, Li, Huiyao, Xu, Qifei, Zhang, Zewei, Wang, Ping, Li, Dong, Guo, Li
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States 01.07.2023
Predmet:	Algorithms Angiography computed tomography (CT) Computed Tomography Angiography - methods computer‐aided detection deep learning Humans Probability pulmonary embolism Pulmonary Embolism - diagnostic imaging Tomography YOLO YOLO deep learning computer-aided detection computed tomography (CT) pulmonary embolism
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	Background Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed. Methods In this study, we identified a deep learning model Scaled‐YOLOv4 that enables end‐to‐end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model. Results Scaled‐YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51–3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36–86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48–76.24] and 72.74 [95% CI: 72.10–73.38] on Linyi and FUMPE, respectively. Conclusions This deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis.
AbstractList	Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed.BACKGROUNDPulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed.In this study, we identified a deep learning model Scaled-YOLOv4 that enables end-to-end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model.METHODSIn this study, we identified a deep learning model Scaled-YOLOv4 that enables end-to-end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model.Scaled-YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51-3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36-86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48-76.24] and 72.74 [95% CI: 72.10-73.38] on Linyi and FUMPE, respectively.RESULTSScaled-YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51-3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36-86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48-76.24] and 72.74 [95% CI: 72.10-73.38] on Linyi and FUMPE, respectively.This deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis.CONCLUSIONSThis deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis. Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed. In this study, we identified a deep learning model Scaled-YOLOv4 that enables end-to-end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model. Scaled-YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51-3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36-86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48-76.24] and 72.74 [95% CI: 72.10-73.38] on Linyi and FUMPE, respectively. This deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis. Background Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed. Methods In this study, we identified a deep learning model Scaled‐YOLOv4 that enables end‐to‐end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model. Results Scaled‐YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51–3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36–86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48–76.24] and 72.74 [95% CI: 72.10–73.38] on Linyi and FUMPE, respectively. Conclusions This deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis.
Author	Guo, Li Xu, Haijun Xu, Qifei Zhang, Zewei Li, Huiyao Li, Dong Wang, Ping
Author_xml	– sequence: 1 givenname: Haijun surname: Xu fullname: Xu, Haijun organization: Tianjin Medical University – sequence: 2 givenname: Huiyao surname: Li fullname: Li, Huiyao organization: Beijing Shijitan Hospital, Capital Medical University – sequence: 3 givenname: Qifei surname: Xu fullname: Xu, Qifei organization: Linyi people's Hospital – sequence: 4 givenname: Zewei surname: Zhang fullname: Zhang, Zewei organization: National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College – sequence: 5 givenname: Ping surname: Wang fullname: Wang, Ping organization: Tianjin Medical University – sequence: 6 givenname: Dong surname: Li fullname: Li, Dong email: dr_lidong@163.com organization: Tianjin Medical University General Hospital – sequence: 7 givenname: Li surname: Guo fullname: Guo, Li email: yxgl@tmu.edu.cn organization: Tianjin Medical University
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/36633186$$D View this record in MEDLINE/PubMed
BookMark	eNp1kMtKxDAYhYOMOBcFn0C6dNMxt6btchi8wcgI6sJVSNN0jCRNbVpldj6Cz-iT2HFmVERXgT_fOXC-IeiVrlQAHCI4RhDiE1uNEcMo2QEDTGMSUgzTHhhAmNIQUxj1wdD7RwghIxHcA33CGCEoYQNgJm3jrGi0DHLVKNloVwauCKrWWFeKehkomzmjvQ10GUhnq7ZRedBl3KIW1cPyBynKhd5eW6_LRXAjhVH5--vb_Xw2f6b7YLcQxquDzTsCd2ent9OLcDY_v5xOZqEk3YgQJyKSkqUFyagUjKlckAKSKKGYJhAplBBGEqGyvOjGEyZlBFEXRHGUd18JGYHjdW9Vu6dW-YZb7aUyRpTKtZ7jmEUwxiyNOvRog7aZVTmvam27LXxr6LtL1s77WhVfCIJ8JZ_bin_K79DxL1TqRqyMNrXQ5q9AuA68aKOW_xbzq-s1_wGpppVo
CitedBy_id	crossref_primary_10_1007_s10278_025_01506_6 crossref_primary_10_1016_j_bspc_2025_107792 crossref_primary_10_1016_j_ejro_2025_100657 crossref_primary_10_1007_s42452_024_06129_0 crossref_primary_10_1016_j_eswa_2023_123029 crossref_primary_10_1016_j_compbiomed_2024_109402 crossref_primary_10_4081_btvb_2024_123 crossref_primary_10_1007_s40031_024_01180_2 crossref_primary_10_1177_08465371251322705 crossref_primary_10_2478_jce_2025_0003
Cites_doi	10.1016/j.jacr.2018.09.028 10.5578/tt.8562 10.1109/TPAMI.2015.2389824 10.1016/j.annemergmed.2004.10.001 10.1109/CVPR.2018.00913 10.2214/ajr.183.6.01831819 10.1016/j.ejim.2010.04.005 10.3390/biology11010043 10.1148/ryai.2021200254 10.1016/j.asjsur.2016.11.005 10.1109/CVPR46437.2021.01283 10.1016/j.media.2019.101541 10.1109/CVPR.2017.690 10.1148/radiol.2362041558 10.1016/j.autcon.2020.103514 10.1038/s41746-020-0266-y 10.1038/sdata.2018.180 10.1038/s41598-021-95249-3 10.3390/s22010200 10.1007/s00330-020-06998-0 10.1186/s12859-021-04036-4 10.1161/01.CIR.0000078464.82671.78 10.1136/bmjopen-2016-012789 10.1109/CVPR.2016.91 10.1007/978-3-319-10602-1_48 10.1038/s41598-020-78888-w 10.1111/nan.12759 10.1109/CVPR42600.2020.01079 10.1016/j.jacr.2017.02.027 10.1097/RTI.0000000000000361 10.1007/s00330-008-0889-x 10.1016/j.neucom.2020.10.022 10.1109/TPAMI.2016.2577031 10.1109/CVPRW50498.2020.00203 10.1007/s00330-020-06699-8 10.3389/fmed.2021.637375
ContentType	Journal Article
Copyright	2023 American Association of Physicists in Medicine.
Copyright_xml	– notice: 2023 American Association of Physicists in Medicine.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1002/mp.16218
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 - Academic MEDLINE
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	4350
ExternalDocumentID	36633186 10_1002_mp_16218 MP16218
Genre	article Journal Article
GrantInformation_xml	– fundername: Tianjin Natural Science Foundation funderid: 18JCYBJC95600 – fundername: Tianjin Municipal Education Commission funderid: 2021KJ264 – fundername: National Natural Science Foundation of China funderid: 31900812 – fundername: National Natural Scientific Foundation of China funderid: 81974277 – fundername: Tianjin Natural Science Foundation grantid: 18JCYBJC95600 – fundername: National Natural Scientific Foundation of China grantid: 81974277 – fundername: Tianjin Municipal Education Commission grantid: 2021KJ264 – fundername: National Natural Science Foundation of China grantid: 31900812
GroupedDBID	--- --Z -DZ .GJ 0R~ 1OB 1OC 29M 2WC 33P 36B 3O- 4.4 53G 5GY 5RE 5VS AAHHS AAHQN AAIPD AAMNL AANLZ AAQQT AASGY AAXRX AAYCA AAZKR ABCUV ABDPE ABEFU ABFTF ABJNI ABLJU ABQWH ABTAH ABXGK ACAHQ ACBEA ACCFJ ACCZN ACGFO ACGFS ACGOF ACPOU ACXBN ACXQS ADBBV ADBTR ADKYN ADOZA ADXAS ADZMN AEEZP AEGXH AEIGN AENEX AEQDE AEUYR AFBPY AFFPM AFWVQ AHBTC AIACR AIAGR AITYG AIURR AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMYDB ASPBG BFHJK C45 CS3 DCZOG DRFUL DRMAN DRSTM DU5 EBD EBS EJD EMB EMOBN F5P HDBZQ HGLYW I-F KBYEO LATKE LEEKS LOXES LUTES LYRES MEWTI O9- OVD P2P P2W PALCI PHY RJQFR RNS ROL SAMSI SUPJJ SV3 TEORI TN5 TWZ USG WOHZO WXSBR XJT ZGI ZVN ZXP ZY4 ZZTAW AAMMB AAYXX ABUFD ADMLS AEFGJ AEYWJ AGHNM AGXDD AGYGG AIDQK AIDYY AIQQE CITATION LH4 CGR CUY CVF ECM EIF NPM 7X8
ID	FETCH-LOGICAL-c3218-28a5cc69f3b4ca66eda3f0358424801e183638aebdf00236cc501218175d83683
IEDL.DBID	DRFUL
ISICitedReferencesCount	12
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000917006100001&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	Thu Sep 04 16:36:16 EDT 2025 Mon Jul 21 06:00:38 EDT 2025 Sat Nov 29 06:02:53 EST 2025 Tue Nov 18 20:40:37 EST 2025 Wed Jan 22 16:21:43 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Keywords	YOLO deep learning computer-aided detection computed tomography (CT) pulmonary embolism
Language	English
License	2023 American Association of Physicists in Medicine.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c3218-28a5cc69f3b4ca66eda3f0358424801e183638aebdf00236cc501218175d83683
Notes	Haijun Xu and Huiyao Li contributed equally to this study. ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
PMID	36633186
PQID	2765072695
PQPubID	23479
PageCount	11
ParticipantIDs	proquest_miscellaneous_2765072695 pubmed_primary_36633186 crossref_primary_10_1002_mp_16218 crossref_citationtrail_10_1002_mp_16218 wiley_primary_10_1002_mp_16218_MP16218
PublicationCentury	2000
PublicationDate	July 2023 2023-07-00 2023-Jul 20230701
PublicationDateYYYYMMDD	2023-07-01
PublicationDate_xml	– month: 07 year: 2023 text: July 2023
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Medical physics (Lancaster)
PublicationTitleAlternate	Med Phys
PublicationYear	2023
References	2021; 8 2017; 7 2015; 37 2021; 3 2021; 22 2021; 422 2008; 18 2005; 236 2004; 183 2019; 58 2022; 48 2018; 41 2021; 122 2020; 10 2005; 45 2010; 21 2003; 107 2020; 3 2018; 5 2021; 11 2017; 14 2020; 30 2021 2017; 39 2020 2015; 63 2018 2017 2016 2014 2018; 33 2018; 15 e_1_2_7_6_1 e_1_2_7_3_1 e_1_2_7_9_1 e_1_2_7_8_1 Expert Panel on Vascular Imaging (e_1_2_7_5_1) 2018; 15 e_1_2_7_7_1 e_1_2_7_19_1 e_1_2_7_18_1 e_1_2_7_17_1 e_1_2_7_16_1 e_1_2_7_40_1 e_1_2_7_2_1 e_1_2_7_15_1 e_1_2_7_14_1 e_1_2_7_13_1 e_1_2_7_12_1 e_1_2_7_11_1 e_1_2_7_10_1 e_1_2_7_26_1 e_1_2_7_27_1 e_1_2_7_28_1 e_1_2_7_29_1 e_1_2_7_30_1 e_1_2_7_25_1 e_1_2_7_31_1 e_1_2_7_24_1 e_1_2_7_32_1 e_1_2_7_23_1 e_1_2_7_33_1 e_1_2_7_22_1 e_1_2_7_34_1 e_1_2_7_21_1 e_1_2_7_35_1 e_1_2_7_20_1 e_1_2_7_36_1 e_1_2_7_37_1 e_1_2_7_38_1 e_1_2_7_39_1 Expert Panels on Cardiac and Thoracic Imaging (e_1_2_7_4_1) 2017; 14
References_xml	– volume: 39 start-page: 1137 issue: 6 year: 2017 end-page: 1149 article-title: Faster R‐CNN: towards real‐time object detection with region proposal networks publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 22 start-page: 200 issue: 1 year: 2021 article-title: Traffic lights detection and recognition method based on the improved YOLOv4 algorithm publication-title: Sensors (Basel) – volume: 21 start-page: 278 issue: 4 year: 2010 end-page: 282 article-title: Delay and misdiagnosis in sub‐massive and non‐massive acute pulmonary embolism publication-title: Eur J Intern Med – volume: 58 year: 2019 article-title: Computer‐aided detection and visualization of pulmonary embolism using a novel, compact, and discriminative image representation publication-title: Med Image Anal – volume: 63 start-page: 13 issue: 1 year: 2015 end-page: 21 article-title: [Misdiagnosis of pulmonary embolism and causes] publication-title: Tuberk Toraks – year: 2021 – volume: 183 start-page: 1819 issue: 6 year: 2004 end-page: 1827 article-title: Accuracy of CT in the diagnosis of pulmonary embolism: a systematic literature review publication-title: AJR Am J Roentgenol – volume: 30 start-page: 6545 issue: 12 year: 2020 end-page: 6553 article-title: Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI‐powered algorithm publication-title: Eur Radiol – volume: 45 start-page: 302 issue: 3 year: 2005 end-page: 310 article-title: The mortality of untreated pulmonary embolism in emergency department patients publication-title: Ann Emerg Med – volume: 22 start-page: 112 issue: 1 year: 2021 article-title: Malaria parasite detection in thick blood smear microscopic images using modified YOLOV3 and YOLOV4 models publication-title: BMC Bioinformatics – volume: 15 start-page: S413 issue: 11S year: 2018 end-page: S417 article-title: ACR appropriateness criteria((R)) suspected lower extremity deep vein thrombosis publication-title: J Am Coll Radiol – volume: 30 start-page: 3567 issue: 6 year: 2020 end-page: 3575 article-title: Evaluation of acute pulmonary embolism and clot burden on CTPA with deep learning publication-title: Eur Radiol – volume: 33 start-page: 350 issue: 6 year: 2018 end-page: 357 article-title: Radiologist performance in the detection of pulmonary embolism: features that favor correct interpretation and risk factors for errors publication-title: J Thorac Imaging – year: 2018 – year: 2014 – volume: 37 start-page: 1904 issue: 9 year: 2015 end-page: 1916 article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 11 issue: 1 year: 2021 article-title: Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta‐analysis publication-title: Sci Rep – volume: 422 start-page: 345 year: 2021 end-page: 353 article-title: Probability‐based mask R‐CNN for pulmonary embolism detection publication-title: Neurocomputing – volume: 236 start-page: 677 issue: 2 year: 2005 end-page: 684 article-title: CT depiction of pulmonary emboli: display window settings publication-title: Radiology – volume: 3 start-page: 61 issue: 1 year: 2020 article-title: PENet—a scalable deep‐learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging publication-title: npj Digital Medicine – volume: 3 issue: 2 year: 2021 article-title: The RSNA pulmonary embolism CT dataset publication-title: Radiol Artif Intell – volume: 18 start-page: 1350 issue: 7 year: 2008 end-page: 1355 article-title: Computer‐aided detection of pulmonary embolism: influence on radiologists' detection performance with respect to vessel segments publication-title: Eur Radiol – volume: 48 issue: 1 year: 2022 article-title: Deep learning‐based model for diagnosing Alzheimer's disease and tauopathies publication-title: Neuropathol Appl Neurobiol – year: 2017 article-title: YOLO9000: better, faster, stronger – volume: 8 year: 2021 article-title: Diagnostic delay of pulmonary embolism in COVID‐19 patients publication-title: Front Med (Lausanne) – volume: 122 year: 2021 article-title: A real‐time detection approach for bridge cracks based on YOLOv4‐FPM publication-title: Automat Constr – volume: 107 start-page: I22 issue: 23 year: 2003 end-page: I30 article-title: Natural history of venous thromboembolism publication-title: Circulation – year: 2020 – volume: 5 year: 2018 article-title: A new dataset of computed‐tomography angiography images for computer‐aided detection of pulmonary embolism publication-title: Sci Data – volume: 14 start-page: S2 issue: 5S year: 2017 end-page: S12 article-title: ACR appropriateness criteria((R)) acute chest pain‐suspected pulmonary embolism publication-title: J Am Coll Radiol – volume: 7 issue: 3 year: 2017 article-title: Clinical characteristics associated with diagnostic delay of pulmonary embolism in primary care: a retrospective observational study publication-title: BMJ Open – volume: 10 issue: 1 year: 2020 article-title: Multimodal fusion with deep neural networks for leveraging CT imaging and electronic health record: a case‐study in pulmonary embolism detection publication-title: Sci Rep – year: 2017 – volume: 11 start-page: 43 issue: 1 year: 2021 article-title: Deep ensemble model for COVID‐19 diagnosis and classification using chest CT images publication-title: Biology (Basel) – year: 2016 article-title: You only look once: unified, real‐time object detection – volume: 41 start-page: 176 issue: 2 year: 2018 end-page: 182 article-title: Epidemiological updates of venous thromboembolism in a Chinese population publication-title: Asian J Surg – year: 2018 article-title: Path aggregation network for instance segmentation – volume: 15 start-page: S413 issue: 11 year: 2018 ident: e_1_2_7_5_1 article-title: ACR appropriateness criteria((R)) suspected lower extremity deep vein thrombosis publication-title: J Am Coll Radiol doi: 10.1016/j.jacr.2018.09.028 – ident: e_1_2_7_9_1 doi: 10.5578/tt.8562 – ident: e_1_2_7_31_1 doi: 10.1109/TPAMI.2015.2389824 – ident: e_1_2_7_2_1 doi: 10.1016/j.annemergmed.2004.10.001 – ident: e_1_2_7_32_1 doi: 10.1109/CVPR.2018.00913 – ident: e_1_2_7_39_1 doi: 10.2214/ajr.183.6.01831819 – ident: e_1_2_7_7_1 doi: 10.1016/j.ejim.2010.04.005 – ident: e_1_2_7_13_1 doi: 10.3390/biology11010043 – ident: e_1_2_7_40_1 doi: 10.1148/ryai.2021200254 – ident: e_1_2_7_6_1 doi: 10.1016/j.asjsur.2016.11.005 – ident: e_1_2_7_33_1 doi: 10.1109/CVPR46437.2021.01283 – ident: e_1_2_7_16_1 doi: 10.1016/j.media.2019.101541 – ident: e_1_2_7_22_1 doi: 10.1109/CVPR.2017.690 – ident: e_1_2_7_29_1 doi: 10.1148/radiol.2362041558 – ident: e_1_2_7_25_1 doi: 10.1016/j.autcon.2020.103514 – ident: e_1_2_7_19_1 doi: 10.1038/s41746-020-0266-y – ident: e_1_2_7_28_1 doi: 10.1038/sdata.2018.180 – ident: e_1_2_7_11_1 doi: 10.1038/s41598-021-95249-3 – ident: e_1_2_7_26_1 doi: 10.3390/s22010200 – ident: e_1_2_7_15_1 doi: 10.1007/s00330-020-06998-0 – ident: e_1_2_7_21_1 – ident: e_1_2_7_27_1 doi: 10.1186/s12859-021-04036-4 – ident: e_1_2_7_3_1 doi: 10.1161/01.CIR.0000078464.82671.78 – ident: e_1_2_7_10_1 doi: 10.1136/bmjopen-2016-012789 – ident: e_1_2_7_24_1 – ident: e_1_2_7_35_1 – ident: e_1_2_7_23_1 doi: 10.1109/CVPR.2016.91 – ident: e_1_2_7_36_1 doi: 10.1007/978-3-319-10602-1_48 – ident: e_1_2_7_20_1 doi: 10.1038/s41598-020-78888-w – ident: e_1_2_7_14_1 doi: 10.1111/nan.12759 – ident: e_1_2_7_34_1 doi: 10.1109/CVPR42600.2020.01079 – volume: 14 start-page: S2 issue: 5 year: 2017 ident: e_1_2_7_4_1 article-title: ACR appropriateness criteria((R)) acute chest pain‐suspected pulmonary embolism publication-title: J Am Coll Radiol doi: 10.1016/j.jacr.2017.02.027 – ident: e_1_2_7_12_1 doi: 10.1097/RTI.0000000000000361 – ident: e_1_2_7_38_1 doi: 10.1007/s00330-008-0889-x – ident: e_1_2_7_17_1 doi: 10.1016/j.neucom.2020.10.022 – ident: e_1_2_7_37_1 doi: 10.1109/TPAMI.2016.2577031 – ident: e_1_2_7_30_1 doi: 10.1109/CVPRW50498.2020.00203 – ident: e_1_2_7_18_1 doi: 10.1007/s00330-020-06699-8 – ident: e_1_2_7_8_1 doi: 10.3389/fmed.2021.637375
SSID	ssj0006350
Score	2.4751093
Snippet	Background Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography... Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt...
SourceID	proquest pubmed crossref wiley
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	4340
SubjectTerms	Algorithms Angiography computed tomography (CT) Computed Tomography Angiography - methods computer‐aided detection deep learning Humans Probability pulmonary embolism Pulmonary Embolism - diagnostic imaging Tomography YOLO
Title	Automatic detection of pulmonary embolism in computed tomography pulmonary angiography using Scaled‐YOLOv4
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fmp.16218 https://www.ncbi.nlm.nih.gov/pubmed/36633186 https://www.proquest.com/docview/2765072695
Volume	50
WOSCitedRecordID	wos000917006100001&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/eLvHCXMwpV1LT9tAEB6VQCsufaQU0ha0lar2ZAjr3bVzRG0jDgGiQqT0ZO3LKFJiRzjhzE_gN_JLOrtrp41opUo9WbJn16udpz2z3wB8tOgXLLU84l0ZRyzX3UgJFUfojHKWKGbTwOlBcn6ejse9YV1V6c7CBHyI1Q83pxneXjsFl6o6-gUaOpsfHgt0UBuwSVFseQs2v37vjwYrO4yuNBxA6TGXQ-AN9GyXHjVj153RowhzPWD1Hqf_4n_W-hKe13EmOQmC8Qqe2KINz87qTHobnvrST129hunJclF64FZi7MJXZhWkzMl8OUURxXcSO1PldFLNyKQgOnSBMATH1GjXv1HK4nrS3HUV9dfkEmXAmoe7-x8Xg4tbtgOj_rerL6dR3YMh0jEuOKKp5FqLXh4rpqUQ1sg4x91OGXXAMxYtAmqwtMrkHoxea-5Q4lKMSgw-SuM30CrKwu4BMUzgx4zBgMrg2GOUAs6sVJyqJBW5ZB343DAj0zVAueuTMc0CtDLNZvPMb2MHPqwo5wGU4080DT8z1BiXBpGFLZdVRhOMShMqerwDu4HRq1liDMDQyokOfPL8_Ov02dnQX9_-K-E72Had6kOl73toLW6Wdh-29O1iUt0cwEYyTg9qCf4Js5vyKg
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3da9swED_apt32srXZV_apwlifvKa2LDvsKWwNHXM-6BJIn4wsycWQ2KGJ-7w_YX_j_pKdJDtt6AaDPhnsky10p7ufpdPvAD4ojAvKVb7jt7nn0FS0nYQlnoPBKKVBQlVoNR0Fg0E4nXZGW_C5Pgtj-SHWC256Zhh_rSe4XpA-vmENnS8-nTCMUNvQoGhFaN6Nr-e9SbR2xBhL7QmUDtWbCH7NPdt2j-u2m9HoDsTcRKwm5PSe3Kuz-_C4Qpqka03jALZU3oQH_WovvQl7JvlTLJ_CrFuuCkPdSqRamdysnBQpWZQzNFL8KFHzpJhlyznJciJsHQhJsE3Fd31LkueXWX1X59Rfkh9oBUr-_vnrYhgNr-kzmPROx1_OnKoKgyM87LDjhtwXgnVSL6GCM6Yk99K2h8DF1dQzCn0Cjj5XiUwNHb0QvuaJCxGXSHwUes9hJy9y9RKIpAx_ZyRCKoltT9AOfKp44rtJELKU0xYc1dqIRUVRritlzGJLruzG80VshrEFh2vJhaXl-JtMrdAY54zeCOG5Kspl7AaISwOXdfwWvLCaXr_FQwiGfo614KNR6D9fH_dH5vrqfwXfw8OzcT-Ko2-D76_hka5bb_N-38DO6qpUb2FXXK-y5dW7ypD_AH5v9TI
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bT9swFD5i7YZ4AdZxKbDNk6btKRASx0nFEwKqofWmbZXgKXJsB1Vqk4i2PPMT-I38Eo7tpFBtkybtKVJynFg5ty_x8XcAPivMC8pTgRO43HdoKlwnYYnvYDJKaZhQFVlNd8JeL7q6ag1W4KTaC2P5IRY_3LRnmHitHVwVMj16Zg2dFIfHDDPUK6hT3UOmBvXzH-1hZxGIMZfaHSgtqhcRgop71vWOqrHL2eg3iLmMWE3KaW_812Q3Yb1EmuTUmsZbWFFZA1a75Vp6A96Y4k8xfQfj0_ksN9StRKqZqc3KSJ6SYj5GI8WHEjVJ8vFoOiGjjAjbB0ISHFPyXb-Q5NnNqDqra-pvyE-0AiUf7x-u-53-Hd2CYfvi19k3p-zC4AgfJ-x4EQ-EYK3UT6jgjCnJ_dT1Ebh4mnpGYUxAH-Yqkamhoxci0DxxEeISiZcifxtqWZ6pXSCSMvyckQipJI49RjsIqOJJ4CVhxFJOm_C10kYsSopy3SljHFtyZS-eFLF5jU34tJAsLC3Hn2QqhcboM3ohhGcqn09jL0RcGnqsFTRhx2p6cRcfIRjGOdaEL0ahf7193B2Y496_Cn6E1cF5O-5c9r7vw5puW2_Lfg-gNrudq_fwWtzNRtPbD6UdPwEZjPSt
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=Automatic+detection+of+pulmonary+embolism+in+computed+tomography+pulmonary+angiography+using+Scaled%E2%80%90YOLOv4&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Xu%2C+Haijun&rft.au=Li%2C+Huiyao&rft.au=Xu%2C+Qifei&rft.au=Zhang%2C+Zewei&rft.date=2023-07-01&rft.issn=0094-2405&rft.eissn=2473-4209&rft.volume=50&rft.issue=7&rft.spage=4340&rft.epage=4350&rft_id=info:doi/10.1002%2Fmp.16218&rft.externalDBID=10.1002%252Fmp.16218&rft.externalDocID=MP16218
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