Weakly-supervised deep learning for ultrasound diagnosis of breast cancer

Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms...

Full description

Saved in:

Bibliographic Details
Published in:	Scientific reports Vol. 11; no. 1; pp. 24382 - 10
Main Authors:	Kim, Jaeil, Kim, Hye Jung, Kim, Chanho, Lee, Jin Hwa, Kim, Keum Won, Park, Young Mi, Kim, Hye Won, Ki, So Yeon, Kim, You Me, Kim, Won Hwa
Format:	Journal Article
Language:	English
Published:	London Nature Publishing Group UK 21.12.2021 Nature Publishing Group Nature Portfolio
Subjects:	631/67 631/67/1347 692/4028 692/700 692/700/1421/1860 Adolescent Adult Aged Aged, 80 and over Algorithms Annotations Automation Breast - diagnostic imaging Breast - pathology Breast cancer Breast Neoplasms - diagnosis Breast Neoplasms - diagnostic imaging Case-Control Studies Deep Learning Diagnosis, Differential Differential diagnosis Female Follow-Up Studies Humanities and Social Sciences Humans Image Interpretation, Computer-Assisted - methods Localization Middle Aged multidisciplinary Neural Networks, Computer Prognosis Retrospective Studies ROC Curve Science Science (multidisciplinary) Ultrasonic imaging Ultrasonography, Mammary - methods Ultrasound Young Adult United States > US
ISSN:	2045-2322, 2045-2322
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92–0.96, which were not statistically different (all P s > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92–0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86–0.90, which were not statistically different ( P s > 0.05) or higher ( P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84–0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis.
AbstractList	Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92-0.96, which were not statistically different (all Ps > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92-0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86-0.90, which were not statistically different (Ps > 0.05) or higher (P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84-0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis.Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92-0.96, which were not statistically different (all Ps > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92-0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86-0.90, which were not statistically different (Ps > 0.05) or higher (P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84-0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis. Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92-0.96, which were not statistically different (all Ps > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92-0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86-0.90, which were not statistically different (Ps > 0.05) or higher (P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84-0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis. Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92–0.96, which were not statistically different (all P s > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92–0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86–0.90, which were not statistically different ( P s > 0.05) or higher ( P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84–0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis. Abstract Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92–0.96, which were not statistically different (all Ps > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92–0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86–0.90, which were not statistically different (Ps > 0.05) or higher (P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84–0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis.
ArticleNumber	24382
Author	Kim, Hye Jung Lee, Jin Hwa Kim, You Me Kim, Chanho Park, Young Mi Kim, Hye Won Ki, So Yeon Kim, Won Hwa Kim, Keum Won Kim, Jaeil
Author_xml	– sequence: 1 givenname: Jaeil surname: Kim fullname: Kim, Jaeil organization: School of Computer Science and Engineering, Kyungpook National University – sequence: 2 givenname: Hye Jung surname: Kim fullname: Kim, Hye Jung organization: Department of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital – sequence: 3 givenname: Chanho surname: Kim fullname: Kim, Chanho organization: School of Computer Science and Engineering, Kyungpook National University – sequence: 4 givenname: Jin Hwa surname: Lee fullname: Lee, Jin Hwa organization: Department of Radiology, Dong-A University College of Medicine – sequence: 5 givenname: Keum Won surname: Kim fullname: Kim, Keum Won organization: Departments of Radiology, School of Medicine, Konyang University, Konyang Univeristy Hospital – sequence: 6 givenname: Young Mi surname: Park fullname: Park, Young Mi organization: Department of Radiology, School of Medicine, Inje University, Busan Paik Hospital – sequence: 7 givenname: Hye Won surname: Kim fullname: Kim, Hye Won organization: Department of Radiology, Wonkwang University Hospital, Wonkwang University School of Medicine – sequence: 8 givenname: So Yeon surname: Ki fullname: Ki, So Yeon organization: Department of Radiology, School of Medicine, Chonnam National University, Chonnam National University Hwasun Hospital – sequence: 9 givenname: You Me surname: Kim fullname: Kim, You Me organization: Department of Radiology, School of Medicine, Dankook University, Dankook University Hospital – sequence: 10 givenname: Won Hwa surname: Kim fullname: Kim, Won Hwa email: greenoaktree9@gmail.com organization: Department of Radiology, School of Medicine, Kyungpook National University, Kyungpook National University Chilgok Hospital
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/34934144$$D View this record in MEDLINE/PubMed
BookMark	eNp9Uk1vFSEUJabG1to_4MJM4sbNKFyYgdmYmMaPlzRxo3FJGOYy8pwHT5hp0n9f-qbVtouy4cI953CA85IchRiQkNeMvmeUqw9ZsKZTNQVWlyVta_mMnAAVTQ0c4OhefUzOct7SMhroBOtekGMuOi6YECdk8wvNn-mqzsse06XPOFQD4r6a0KTgw1i5mKplmpPJcQml6c0YYva5iq7qE5o8V9YEi-kVee7MlPHsdj4lP798_nH-rb74_nVz_umito2gc41usFQ4xengLO2BO85BoOokOOrEoTJcSTpYaLBxMIBpygWFal3vKPJTsll1h2i2ep_8zqQrHY3Xh42YRm3S7O2E2rGODj1zYLkUrWoVl1I4aITolXRGFa2Pq9Z-6Xc4WAzlotMD0Yed4H_rMV5q1XYgaFME3t0KpPh3wTzrnc8Wp8kEjEvW0DKQspzeFejbR9BtXFIoT3VAAXDV8YJ6c9_RPyt3P1YAagXYFHNO6LT1s5l9vDHoJ82ovsmHXvOhSz70IR9aFio8ot6pP0niKykXcBgx_bf9BOsaIsrMQw
CitedBy_id	crossref_primary_10_1016_j_bspc_2024_106351 crossref_primary_10_14366_usg_24171 crossref_primary_10_1016_j_compmedimag_2023_102233 crossref_primary_10_1148_ryai_220185 crossref_primary_10_1007_s13198_024_02390_z crossref_primary_10_1016_j_media_2024_103187 crossref_primary_10_1016_j_arthro_2022_03_037 crossref_primary_10_3389_fonc_2025_1517278 crossref_primary_10_1016_j_bspc_2022_103831 crossref_primary_10_3390_cancers14071651 crossref_primary_10_3390_healthcare10112300 crossref_primary_10_1007_s11042_025_20606_7 crossref_primary_10_4048_jbc_2024_0303 crossref_primary_10_3390_s25082361 crossref_primary_10_3390_cancers15123139 crossref_primary_10_1038_s41598_025_99009_5 crossref_primary_10_1109_TMI_2024_3366940 crossref_primary_10_1109_ACCESS_2024_3429386 crossref_primary_10_1016_j_bbe_2024_01_002 crossref_primary_10_1007_s00521_025_11215_4 crossref_primary_10_1109_ACCESS_2025_3560211 crossref_primary_10_1186_s12880_025_01701_5 crossref_primary_10_1016_j_medengphy_2025_104288 crossref_primary_10_1007_s11548_022_02658_4 crossref_primary_10_1016_j_media_2025_103552 crossref_primary_10_3390_ijms26157134 crossref_primary_10_3390_cancers14215334 crossref_primary_10_4048_jbc_2025_0123 crossref_primary_10_1016_j_crad_2024_08_002 crossref_primary_10_1038_s41598_024_55298_w crossref_primary_10_1002_cai2_136 crossref_primary_10_1007_s11548_024_03098_y crossref_primary_10_1016_j_media_2023_102960 crossref_primary_10_1016_j_compbiomed_2024_109391 crossref_primary_10_1109_RBME_2024_3357877 crossref_primary_10_1371_journal_pdig_0001019
Cites_doi	10.1088/1361-6560/aa82ec 10.1097/MD.0000000000014146 10.2214/ajr.184.4.01841260 10.1109/TIP.2008.2001043 10.2214/AJR.18.20532 10.1007/s10439-018-2095-6 10.1016/j.bspc.2020.102027 10.1371/journal.pcbi.1007792 10.2214/AJR.13.12072 10.1038/s41551-018-0324-9 10.1109/JBHI.2017.2731873 10.1109/TMI.2018.2872031 10.1002/jmri.26721 10.1016/j.media.2019.03.009 10.1007/s11604-019-00831-5 10.14366/usg.20117 10.1186/s12880-019-0349-x 10.1002/mp.13361 10.1002/mp.13268 10.1007/s00330-018-5668-8 10.1088/1361-6560/ab5093 10.1016/j.artmed.2019.01.001 10.1148/rg.305095144 10.1148/radiol.2412051710 10.1016/j.aca.2021.338522 10.1109/TMI.2016.2528162 10.4329/wjr.v11.i2.19 10.1109/TBME.2018.2877577 10.1016/j.patcog.2018.02.012 10.1117/12.2549203 10.1145/3233547.3233573 10.1259/bjr.20170576 10.1007/978-3-319-24574-4_28 10.1109/ICCV.2017.74 10.1109/CVPR.2016.319 10.1109/CVPR.2015.7298668 10.1109/CVPR.2017.369
ContentType	Journal Article
Copyright	The Author(s) 2021 2021. The Author(s). The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2021 – notice: 2021. The Author(s). – notice: The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88A 88E 88I 8FE 8FH 8FI 8FJ 8FK ABUWG AEUYN AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. LK8 M0S M1P M2P M7P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 5PM DOA
DOI	10.1038/s41598-021-03806-7
DatabaseName	Springer Nature OA Free Journals CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Biology Database (Alumni Edition) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Journals Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest One Sustainability ProQuest Central UK/Ireland ProQuest Central Essentials Biological Science Collection ProQuest Central Natural Science Collection ProQuest One Community College ProQuest Central Korea Proquest Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) Biological Sciences ProQuest Health & Medical Collection Medical Database Science Database Biological Science Database Proquest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central China ProQuest Biology Journals (Alumni Edition) ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Sustainability ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE CrossRef Publicly Available Content Database
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: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	2045-2322
EndPage	10
ExternalDocumentID	oai_doaj_org_article_f190db1f2c37468683774f2544b87fa8 PMC8692405 34934144 10_1038_s41598_021_03806_7
Genre	Research Support, Non-U.S. Gov't Journal Article
GeographicLocations	United States--US
GeographicLocations_xml	– name: United States--US
GrantInformation_xml	– fundername: Korean Society of Breast Imaging & Korean Society for Breast Screening grantid: KSBI & KSFBS-2017-01 – fundername: National Research Foundation of Korea grantid: 2020R1I1A3074639; 2019R1G1A1098655; 2020R1C1C1006453 funderid: http://dx.doi.org/10.13039/501100003725 – fundername: Daegu Metropolitan and Daegu-Gyeongbuk Medical Innovation Foundation (2021 Daegu Medi-Startup Program) – fundername: ; – fundername: ; grantid: KSBI & KSFBS-2017-01 – fundername: ; grantid: 2020R1I1A3074639; 2019R1G1A1098655; 2020R1C1C1006453
GroupedDBID	0R~ 3V. 4.4 53G 5VS 7X7 88A 88E 88I 8FE 8FH 8FI 8FJ AAFWJ AAJSJ AAKDD ABDBF ABUWG ACGFS ACSMW ACUHS ADBBV ADRAZ AENEX AEUYN AFKRA AJTQC ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BAWUL BBNVY BCNDV BENPR BHPHI BPHCQ BVXVI C6C CCPQU DIK DWQXO EBD EBLON EBS ESX FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE KQ8 LK8 M0L M1P M2P M48 M7P M~E NAO OK1 PIMPY PQQKQ PROAC PSQYO RNT RNTTT RPM SNYQT UKHRP AASML AAYXX AFFHD AFPKN CITATION PHGZM PHGZT PJZUB PPXIY PQGLB CGR CUY CVF ECM EIF NPM 7XB 8FK K9. PKEHL PQEST PQUKI PRINS Q9U 7X8 PUEGO 5PM
ID	FETCH-LOGICAL-c540t-efdc04f830dfc0b23f3324e8972f0f44e897a3870dc25e5f2d2a5380486fbf0e3
IEDL.DBID	M2P
ISICitedReferencesCount	36
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000732567600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2045-2322
IngestDate	Fri Oct 03 12:37:00 EDT 2025 Tue Nov 04 01:52:23 EST 2025 Thu Sep 04 19:51:50 EDT 2025 Tue Oct 07 09:04:41 EDT 2025 Thu Jan 02 22:56:29 EST 2025 Tue Nov 18 20:02:48 EST 2025 Sat Nov 29 02:51:05 EST 2025 Fri Feb 21 02:39:05 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	2021. The Author(s). Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c540t-efdc04f830dfc0b23f3324e8972f0f44e897a3870dc25e5f2d2a5380486fbf0e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
OpenAccessLink	https://www.proquest.com/docview/2612223893?pq-origsite=%requestingapplication%
PMID	34934144
PQID	2612223893
PQPubID	2041939
PageCount	10
ParticipantIDs	doaj_primary_oai_doaj_org_article_f190db1f2c37468683774f2544b87fa8 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8692405 proquest_miscellaneous_2612773749 proquest_journals_2612223893 pubmed_primary_34934144 crossref_citationtrail_10_1038_s41598_021_03806_7 crossref_primary_10_1038_s41598_021_03806_7 springer_journals_10_1038_s41598_021_03806_7
PublicationCentury	2000
PublicationDate	2021-12-21
PublicationDateYYYYMMDD	2021-12-21
PublicationDate_xml	– month: 12 year: 2021 text: 2021-12-21 day: 21
PublicationDecade	2020
PublicationPlace	London
PublicationPlace_xml	– name: London – name: England
PublicationTitle	Scientific reports
PublicationTitleAbbrev	Sci Rep
PublicationTitleAlternate	Sci Rep
PublicationYear	2021
Publisher	Nature Publishing Group UK Nature Publishing Group Nature Portfolio
Publisher_xml	– name: Nature Publishing Group UK – name: Nature Publishing Group – name: Nature Portfolio
References	Berg, Blume, Cormack, Mendelson (CR3) 2006; 241 Lamy, Sekar, Guezennec, Bouaud, Seroussi (CR35) 2019; 94 Becker, Mueller, Stoffel, Marcon, Ghafoor, Boss (CR19) 2018; 91 Hong, Rosen, Soo, Baker (CR26) 2005; 184 CR16 CR38 Jager, Knoll, Hamprecht (CR7) 2008; 17 CR37 Mendelson (CR4) 2019; 212 CR11 CR33 CR30 Hu (CR32) 2019; 46 Wu (CR5) 2019; 11 Lee (CR36) 2019; 3 Cao, Duan, Yang, Yue, Chen (CR13) 2019; 19 Zhou (CR10) 2019; 50 Shin (CR15) 2016; 35 Fujioka (CR21) 2019; 37 Brem, Lenihan, Lieberman, Torrente (CR1) 2015; 204 Shin, Lee, Yun, Lee (CR24) 2019; 38 Byra (CR31) 2020; 61 Han (CR17) 2017; 62 Cheplygina, de Bruijne, Pluim (CR9) 2019; 54 Kim, Kim, Kim, Kim (CR6) 2021; 40 Yap (CR23) 2018; 22 Park (CR20) 2019; 98 CR8 Anguita-Ruiz, Segura-Delgado, Alcalá, Aguilera, Alcalá-Fdez (CR34) 2020; 16 Xian, Zhang, Cheng, Xu, Zhang, Ding (CR28) 2018; 79 CR29 Du (CR14) 2018; 46 CR25 Raza, Goldkamp, Chikarmane, Birdwell (CR27) 2010; 30 Byra (CR18) 2019; 46 Tanaka, Chiu, Watanabe, Kaoku, Yamaguchi (CR22) 2019; 64 Mishra, Chaudhury, Sarkar, Soin (CR12) 2019; 66 Leonoor (CR39) 2021; 1177 Vourtsis, Berg (CR2) 2019; 29 H Lee (3806_CR36) 2019; 3 H Tanaka (3806_CR22) 2019; 64 3806_CR29 M Byra (3806_CR18) 2019; 46 D Mishra (3806_CR12) 2019; 66 M Xian (3806_CR28) 2018; 79 3806_CR25 Y Hu (3806_CR32) 2019; 46 SY Shin (3806_CR24) 2019; 38 3806_CR8 S Raza (3806_CR27) 2010; 30 HC Shin (3806_CR15) 2016; 35 Y Du (3806_CR14) 2018; 46 MH Yap (3806_CR23) 2018; 22 T Fujioka (3806_CR21) 2019; 37 RF Brem (3806_CR1) 2015; 204 V Cheplygina (3806_CR9) 2019; 54 A Anguita-Ruiz (3806_CR34) 2020; 16 EB Mendelson (3806_CR4) 2019; 212 3806_CR16 3806_CR38 3806_CR37 Z Cao (3806_CR13) 2019; 19 S Han (3806_CR17) 2017; 62 3806_CR11 3806_CR33 EM Leonoor (3806_CR39) 2021; 1177 JB Lamy (3806_CR35) 2019; 94 AS Becker (3806_CR19) 2018; 91 3806_CR30 M Byra (3806_CR31) 2020; 61 WA Berg (3806_CR3) 2006; 241 J Zhou (3806_CR10) 2019; 50 HJ Park (3806_CR20) 2019; 98 AS Hong (3806_CR26) 2005; 184 A Vourtsis (3806_CR2) 2019; 29 M Jager (3806_CR7) 2008; 17 GG Wu (3806_CR5) 2019; 11 J Kim (3806_CR6) 2021; 40
References_xml	– volume: 62 start-page: 7714 year: 2017 end-page: 7728 ident: CR17 article-title: A deep learning framework for supporting the classification of breast lesions in ultrasound images publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/aa82ec – volume: 91 start-page: 20170576 year: 2018 ident: CR19 article-title: Classification of breast cancer in ultrasound imaging using a generic deep learning analysis software: a pilot study publication-title: Br. J. Radiol. – volume: 98 start-page: e14146 year: 2019 ident: CR20 article-title: A computer-aided diagnosis system using artificial intelligence for the diagnosis and characterization of breast masses on ultrasound: Added value for the inexperienced breast radiologist publication-title: Medicine doi: 10.1097/MD.0000000000014146 – volume: 184 start-page: 1260 year: 2005 end-page: 1265 ident: CR26 article-title: BI-RADS for sonography: positive and negative predictive values of sonographic features publication-title: AJR Am J Roentgenol. doi: 10.2214/ajr.184.4.01841260 – volume: 17 start-page: 1700 year: 2008 end-page: 1708 ident: CR7 article-title: Weakly supervised learning of a classifier for unusual event detection publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2008.2001043 – ident: CR16 – ident: CR37 – ident: CR30 – volume: 212 start-page: 293 year: 2019 end-page: 299 ident: CR4 article-title: Artificial intelligence in breast imaging: Potentials and limitations publication-title: AJR Am. J. Roentgenol. doi: 10.2214/AJR.18.20532 – volume: 46 start-page: 1988 year: 2018 end-page: 1999 ident: CR14 article-title: Classification of tumor epithelium and stroma by exploiting image features learned by deep convolutional neural networks publication-title: Ann. Biomed. Eng. doi: 10.1007/s10439-018-2095-6 – volume: 61 start-page: 102027 year: 2020 ident: CR31 article-title: Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2020.102027 – ident: CR33 – volume: 16 start-page: e1007792 year: 2020 ident: CR34 article-title: eXplainable artificial intelligence (XAI) for the identification of biologically relevant gene expression patterns in longitudinal human studies, insights from obesity research publication-title: PLoS Comput Biol. doi: 10.1371/journal.pcbi.1007792 – ident: CR29 – volume: 204 start-page: 234 year: 2015 end-page: 240 ident: CR1 article-title: Screening breast ultrasound: past, present, and future publication-title: AJR Am. J. Roentgenol. doi: 10.2214/AJR.13.12072 – ident: CR8 – volume: 3 start-page: 173 year: 2019 end-page: 182 ident: CR36 article-title: An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets publication-title: Nat Biomed Eng. doi: 10.1038/s41551-018-0324-9 – ident: CR25 – volume: 22 start-page: 1218 year: 2018 end-page: 1226 ident: CR23 article-title: Automated breast ultrasound lesions detection using convolutional neural networks publication-title: IEEE J. Biomed Health Inform. doi: 10.1109/JBHI.2017.2731873 – volume: 38 start-page: 762 year: 2019 end-page: 774 ident: CR24 article-title: Joint weakly and semi-supervised deep learning for localization and classification of masses in breast ultrasound images publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2018.2872031 – volume: 50 start-page: 1144 year: 2019 end-page: 1151 ident: CR10 article-title: Weakly supervised 3D deep learning for breast cancer classification and localization of the lesions in MR images publication-title: J. Magn. Reson. Imaging. doi: 10.1002/jmri.26721 – volume: 54 start-page: 280 year: 2019 end-page: 296 ident: CR9 article-title: Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis publication-title: Med. Image Anal. doi: 10.1016/j.media.2019.03.009 – volume: 37 start-page: 466 year: 2019 end-page: 472 ident: CR21 article-title: Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network publication-title: Jpn. J. Radiol. doi: 10.1007/s11604-019-00831-5 – volume: 40 start-page: 183 year: 2021 end-page: 190 ident: CR6 article-title: Artificial intelligence in breast ultrasonography publication-title: Ultrasonography doi: 10.14366/usg.20117 – ident: CR38 – volume: 19 start-page: 51 year: 2019 ident: CR13 article-title: An experimental study on breast lesion detection and classification from ultrasound images using deep learning architectures publication-title: BMC Med. Imaging. doi: 10.1186/s12880-019-0349-x – volume: 46 start-page: 746 year: 2019 end-page: 755 ident: CR18 article-title: Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion publication-title: Med. Phys. doi: 10.1002/mp.13361 – volume: 46 start-page: 215 year: 2019 end-page: 228 ident: CR32 article-title: Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model publication-title: Med Phys. doi: 10.1002/mp.13268 – volume: 29 start-page: 1762 year: 2019 end-page: 1777 ident: CR2 article-title: Breast density implications and supplemental screening publication-title: Eur. Radiol. doi: 10.1007/s00330-018-5668-8 – ident: CR11 – volume: 64 start-page: 235013 year: 2019 ident: CR22 article-title: Computer-aided diagnosis system for breast ultrasound images using deep learning publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/ab5093 – volume: 94 start-page: 42 year: 2019 end-page: 53 ident: CR35 article-title: Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach publication-title: Artif Intell Med. doi: 10.1016/j.artmed.2019.01.001 – volume: 30 start-page: 1199 year: 2010 end-page: 1213 ident: CR27 article-title: US of breast masses categorized as BI-RADS 3, 4, and 5: pictorial review of factors influencing clinical management publication-title: Radiographics doi: 10.1148/rg.305095144 – volume: 241 start-page: 55 year: 2006 end-page: 365 ident: CR3 article-title: Operator dependence of physician-performed whole-breast US: Lesion detection and characterization publication-title: Radiology doi: 10.1148/radiol.2412051710 – volume: 1177 start-page: 338522 year: 2021 ident: CR39 article-title: Automated biomarker candidate discovery in imaging mass spectrometry data through spatially localized shapley additive explanations publication-title: Analytica Chimica Acta. doi: 10.1016/j.aca.2021.338522 – volume: 35 start-page: 1285 year: 2016 end-page: 1298 ident: CR15 article-title: Deep convolutional neural networks for computer-aided detection: CNN Architectures, dataset characteristics and transfer learning publication-title: IEEE Trans. Med. Imaging. doi: 10.1109/TMI.2016.2528162 – volume: 11 start-page: 19 year: 2019 end-page: 26 ident: CR5 article-title: Artificial intelligence in breast ultrasound publication-title: World J. Radiol. doi: 10.4329/wjr.v11.i2.19 – volume: 66 start-page: 1637 year: 2019 end-page: 1648 ident: CR12 article-title: Ultrasound image segmentation: A deeply supervised network with attention to boundaries publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2018.2877577 – volume: 79 start-page: 340 year: 2018 end-page: 355 ident: CR28 article-title: Automatic breast ultrasound image segmentation: A survey publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2018.02.012 – volume: 98 start-page: e14146 year: 2019 ident: 3806_CR20 publication-title: Medicine doi: 10.1097/MD.0000000000014146 – volume: 66 start-page: 1637 year: 2019 ident: 3806_CR12 publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2018.2877577 – ident: 3806_CR38 – volume: 30 start-page: 1199 year: 2010 ident: 3806_CR27 publication-title: Radiographics doi: 10.1148/rg.305095144 – volume: 40 start-page: 183 year: 2021 ident: 3806_CR6 publication-title: Ultrasonography doi: 10.14366/usg.20117 – volume: 46 start-page: 746 year: 2019 ident: 3806_CR18 publication-title: Med. Phys. doi: 10.1002/mp.13361 – volume: 29 start-page: 1762 year: 2019 ident: 3806_CR2 publication-title: Eur. Radiol. doi: 10.1007/s00330-018-5668-8 – volume: 212 start-page: 293 year: 2019 ident: 3806_CR4 publication-title: AJR Am. J. Roentgenol. doi: 10.2214/AJR.18.20532 – volume: 204 start-page: 234 year: 2015 ident: 3806_CR1 publication-title: AJR Am. J. Roentgenol. doi: 10.2214/AJR.13.12072 – volume: 54 start-page: 280 year: 2019 ident: 3806_CR9 publication-title: Med. Image Anal. doi: 10.1016/j.media.2019.03.009 – volume: 19 start-page: 51 year: 2019 ident: 3806_CR13 publication-title: BMC Med. Imaging. doi: 10.1186/s12880-019-0349-x – volume: 3 start-page: 173 year: 2019 ident: 3806_CR36 publication-title: Nat Biomed Eng. doi: 10.1038/s41551-018-0324-9 – volume: 17 start-page: 1700 year: 2008 ident: 3806_CR7 publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2008.2001043 – volume: 62 start-page: 7714 year: 2017 ident: 3806_CR17 publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/aa82ec – ident: 3806_CR25 doi: 10.1117/12.2549203 – ident: 3806_CR11 doi: 10.1145/3233547.3233573 – volume: 91 start-page: 20170576 year: 2018 ident: 3806_CR19 publication-title: Br. J. Radiol. doi: 10.1259/bjr.20170576 – volume: 38 start-page: 762 year: 2019 ident: 3806_CR24 publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2018.2872031 – volume: 94 start-page: 42 year: 2019 ident: 3806_CR35 publication-title: Artif Intell Med. doi: 10.1016/j.artmed.2019.01.001 – volume: 61 start-page: 102027 year: 2020 ident: 3806_CR31 publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2020.102027 – ident: 3806_CR30 – volume: 16 start-page: e1007792 year: 2020 ident: 3806_CR34 publication-title: PLoS Comput Biol. doi: 10.1371/journal.pcbi.1007792 – volume: 64 start-page: 235013 year: 2019 ident: 3806_CR22 publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/ab5093 – volume: 11 start-page: 19 year: 2019 ident: 3806_CR5 publication-title: World J. Radiol. doi: 10.4329/wjr.v11.i2.19 – volume: 79 start-page: 340 year: 2018 ident: 3806_CR28 publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2018.02.012 – ident: 3806_CR29 doi: 10.1007/978-3-319-24574-4_28 – ident: 3806_CR33 doi: 10.1109/ICCV.2017.74 – volume: 46 start-page: 1988 year: 2018 ident: 3806_CR14 publication-title: Ann. Biomed. Eng. doi: 10.1007/s10439-018-2095-6 – volume: 50 start-page: 1144 year: 2019 ident: 3806_CR10 publication-title: J. Magn. Reson. Imaging. doi: 10.1002/jmri.26721 – volume: 35 start-page: 1285 year: 2016 ident: 3806_CR15 publication-title: IEEE Trans. Med. Imaging. doi: 10.1109/TMI.2016.2528162 – volume: 46 start-page: 215 year: 2019 ident: 3806_CR32 publication-title: Med Phys. doi: 10.1002/mp.13268 – ident: 3806_CR37 doi: 10.1109/CVPR.2016.319 – ident: 3806_CR8 doi: 10.1109/CVPR.2015.7298668 – volume: 184 start-page: 1260 year: 2005 ident: 3806_CR26 publication-title: AJR Am J Roentgenol. doi: 10.2214/ajr.184.4.01841260 – volume: 37 start-page: 466 year: 2019 ident: 3806_CR21 publication-title: Jpn. J. Radiol. doi: 10.1007/s11604-019-00831-5 – volume: 241 start-page: 55 year: 2006 ident: 3806_CR3 publication-title: Radiology doi: 10.1148/radiol.2412051710 – ident: 3806_CR16 doi: 10.1109/CVPR.2017.369 – volume: 22 start-page: 1218 year: 2018 ident: 3806_CR23 publication-title: IEEE J. Biomed Health Inform. doi: 10.1109/JBHI.2017.2731873 – volume: 1177 start-page: 338522 year: 2021 ident: 3806_CR39 publication-title: Analytica Chimica Acta. doi: 10.1016/j.aca.2021.338522
SSID	ssj0000529419
Score	2.5612674
Snippet	Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to... Abstract Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We...
SourceID	doaj pubmedcentral proquest pubmed crossref springer
SourceType	Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	24382
SubjectTerms	631/67 631/67/1347 692/4028 692/700 692/700/1421/1860 Adolescent Adult Aged Aged, 80 and over Algorithms Annotations Automation Breast - diagnostic imaging Breast - pathology Breast cancer Breast Neoplasms - diagnosis Breast Neoplasms - diagnostic imaging Case-Control Studies Deep Learning Diagnosis, Differential Differential diagnosis Female Follow-Up Studies Humanities and Social Sciences Humans Image Interpretation, Computer-Assisted - methods Localization Middle Aged multidisciplinary Neural Networks, Computer Prognosis Retrospective Studies ROC Curve Science Science (multidisciplinary) Ultrasonic imaging Ultrasonography, Mammary - methods Ultrasound Young Adult
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB6hqpW4oJbyCLTISNyoVcd2YucIqBW9VBxA9GYlfsCKVXa12UXqv-_Yzi7d8rr0FiVOMvo8tr-Rx98AvKl4rerKSSoq3VEZvKeNrhz1vsS5r24xZHCp2IS6vNRXV82nW6W-Yk5YlgfOwJ0GXLFcVwZuhZK1rjGgUjJEYa1Oq9CmY75MNbeCqazqzRtZNuMpGSb06YArVTxNxmMGkcYwWm2tREmw_08s8_dkyTs7pmkhOt-HRyODJO-y5QfwwPePYS_XlLw-hIuvvv0xvabDah6ngcE74ryfk7E8xDeCLJWspviTIVZUIi7n2k0GMgukiynqS2KjKyyewJfzs88fPtKxXgK1yLuW1AdnmQxaMBcs67gIAumS143igQWZrlqBA9RZXvkqcMdbnO-i6F7oAvPiKez0s94_ByI720YpOOd4kEog1kgLpFeyqZHQMFZAucbO2FFMPNa0mJq0qS20yXgbxNskvI0q4O3mnXmW0vhn6_exSzYtowx2uoHOYUbnMP9zjgKO1h1qxrE5mCiahqQIiVoBrzePcVTFrZK297NVbqMUfrQp4Fnu_40lQiIUGIcWoLY8Y8vU7Sf95HtS7tY1hrusKuBk7UO_zPo7FC_uA4qX8JBH5y855eUR7CwXK38Mu_bncjIsXqXRcwM4Nhmy priority: 102 providerName: Directory of Open Access Journals
Title	Weakly-supervised deep learning for ultrasound diagnosis of breast cancer
URI	https://link.springer.com/article/10.1038/s41598-021-03806-7 https://www.ncbi.nlm.nih.gov/pubmed/34934144 https://www.proquest.com/docview/2612223893 https://www.proquest.com/docview/2612773749 https://pubmed.ncbi.nlm.nih.gov/PMC8692405 https://doaj.org/article/f190db1f2c37468683774f2544b87fa8
Volume	11
WOSCitedRecordID	wos000732567600014&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: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M7P dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: 7X7 dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M2P dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9NAEB7RBqReeD8MJTISN7Bq76696xOiqBU9NLIQiHCy7H2UiMhO4wSp_56ZtZMqPHrhsrLidbTeee-MvwF4nbJMZqkREU9VHQlnbZSr1ETWJqj7sgpDBuObTcjJRE2neTEcuHVDWeVGJ3pFbVpNZ-RHBHWFpgzN67vFZURdoyi7OrTQ2IMRejYJlXSds2J7xkJZLJHkw7cyMVdHHdor-qaMUR2RwmBa7tgjD9v_N1_zz5LJ3_Km3hyd3vvfF7kPdwdHNHzfc84DuGWbh3Cnb0159QjOvtrqx_wq6tYL0iadNaGxdhEOXSYuQnR2w_UcV9lRY6bQ9CV7sy5sXVhTpfsq1MRRy8fw5fTk84eP0dB2IdLovq0i64yOhVM8Nk7HNeOOo9dlVS6Zi53wVxVHOTeapTZ1zLAK1SZh97naxZY_gf2mbewzCEWtK0KUM4Y5IbmoFXoXwkqRZ-gXxXEAyWbzSz1gklNrjHnpc-NclT3BSiRY6QlWygDebJ9Z9IgcN84-JppuZxKatv-hXV6Ug3CWDr0iUyeOaS5FpjIM2qVwBN5WK-kqFcDhhpTlIOJdeU3HAF5tb6NwUsalamy77udIiX-aB_C0Z6DtSrjArcBwNgC5w1o7S92908y-ewBwlWHUHKcBvN0w4fWy_r0Vz29-ixdwwEguEhax5BD2V8u1fQm39c_VrFuOYU9OpR_VGEbHJ5Pi09ifX4y9yNEocRwVZ-fFt1-b9S-W
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VAoIL70eggJHgBFET24mdA0K8qq5aVj0U0ZubxHZZscoum13Q_il-IzN5bLU8euuBW5Q4lmN_M_M5M54BeJbwVKWJlaFIdBFK71yY6cSGzsWo-9Ictwy2KTahhkN9dJQdbMDP_iwMhVX2OrFR1HZS0j_ybUp1haYMzevr6beQqkaRd7UvodHCYs8tf-CWrX41eI_r-5zznQ-H73bDrqpAWCI7mYfO2zKSXovI-jIquPACSYXTmeI-8rK5ygXC2JY8cYnnlueoFSg1nS985AT2ewEuSsosRqGC_GD1T4e8ZjLOurM5kdDbNdpHOsPGKW5J4-Zdrdm_pkzA37jtnyGav_lpG_O3c_1_m7gbcK0j2uxNKxk3YcNVt-ByW3pzeRsGn13-dbwM68WUtGXtLLPOTVlXReOEIZlnizHOSk2Fp5htQxJHNZt4VlAk_5yVJDGzO_DpXL7jLmxWk8rdByaLMqeMedZyL5WQhUb2JJ2SWYq8L4oCiPvFNmWXc51Kf4xN4_sX2rQAMQgQ0wDEqABerN6ZthlHzmz9ljC0aknZwpsbk9mJ6ZSP8cj6bBF7XgolU51qgaTfU3K6Qiuf6wC2euiYToXV5hQ3ATxdPUblQx6lvHKTRdtGKew0C-BeC9jVSITEqcDtegBqDcprQ11_Uo2-NAnOdZoh0UwCeNmD_nRY_56KB2d_xRO4snv4cd_sD4Z7D-EqJ5mMecjjLdiczxbuEVwqv89H9exxI9QMjs9bGH4BhiGFxw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwEB4tXUBceD8CCxgJThA1sZ3YOSAELBXVQtUDiN2TSWJ7qaiS0rSg_jV-HeO8VuWxtz1wixLHcuxvZr6JxzMAjyMaizjS3GeRzHxujfETGWnfmBB1X5yiy6DrYhNiMpGHh8l0B352Z2FcWGWnE2tFrcvc_SMfulRXaMrQvA5tGxYx3R-9WHzzXQUpt9PaldNoIHJgNj_Qfauej_dxrZ9QOnrz4fVbv60w4OfIVFa-sToPuJUs0DYPMsosQ4JhZCKoDSyvr1KGkNY5jUxkqaYpagiXps5mNjAM-z0Hu0jJOR3A7nT8fnrU_-Fxe2g8TNqTOgGTwwqtpTvRRl0Uk0RXXmxZw7powN-Y7p8Bm7_t2tbGcHTlf57Gq3C5peDkZSMz12DHFNfhQlOUc3MDxp9M-nW-8av1wunRymiijVmQtr7GMUGaT9ZznKHKlaQiuglWnFWktCRzMf4rkjtZWt6Ej2fyHbdgUJSFuQOEZ3nqculpTS0XjGcSeRU3gicxMsIg8CDsFl7lbTZ2VxRkruqoACZVAxaFYFE1WJTw4Gn_zqLJRXJq61cOT31Ll0e8vlEuj1WrlpRFPqiz0NKcCR7LWDJ0B6xLW5dJYVPpwV4HI9Uqt0qdYMiDR_1jVEturyktTLlu2giBnSYe3G7A24-EcZwKdOQ9EFuw3hrq9pNi9qVOfS7jBClo5MGzTgBOhvXvqbh7-lc8hIsoA-rdeHJwDy5RJ54h9Wm4B4PVcm3uw_n8-2pWLR-0Ek7g81lLwy8ngZAQ
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=Weakly-supervised+deep+learning+for+ultrasound+diagnosis+of+breast+cancer&rft.jtitle=Scientific+reports&rft.au=Kim%2C+Jaeil&rft.au=Kim%2C+Hye+Jung&rft.au=Kim%2C+Chanho&rft.au=Lee%2C+Jin+Hwa&rft.date=2021-12-21&rft.issn=2045-2322&rft.eissn=2045-2322&rft.volume=11&rft.issue=1&rft_id=info:doi/10.1038%2Fs41598-021-03806-7&rft.externalDBID=n%2Fa&rft.externalDocID=10_1038_s41598_021_03806_7
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2045-2322&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2045-2322&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2045-2322&client=summon