MRI‐Based Breast Cancer Classification and Localization by Multiparametric Feature Extraction and Combination Using Deep Learning

Background Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated. Purpose To implement a DL method for breast cancer classification and detection using feature extraction...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of magnetic resonance imaging Ročník 59; číslo 1; s. 148 - 161
Hlavní autori:	Cong, Chao, Li, Xiaoguang, Zhang, Chunlai, Zhang, Jing, Sun, Kaixiang, Liu, Lianluyi, Ambale‐Venkatesh, Bharath, Chen, Xiao, Wang, Yi
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Hoboken, USA John Wiley & Sons, Inc 01.01.2024 Wiley Subscription Services, Inc
Predmet:	Artificial neural networks Breast cancer breast MRI Classification computer‐aided detection Contrast agents Contrast media Deep learning Feature extraction Females Field strength Histopathology Lesions Localization Machine learning Magnetic resonance imaging Medical imaging multiparametric MRI Neural networks Population studies Sensitivity Statistical analysis Statistical tests multiparametric MRI breast MRI deep learning breast cancer computer-aided detection
ISSN:	1053-1807, 1522-2586, 1522-2586
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Background Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated. Purpose To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences. Study Type Retrospective. Population A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female). Field Strength/Sequence T1‐weighted imaging and dynamic contrast‐enhanced MRI (DCE‐MRI) with gradient echo sequences, T2‐weighted imaging (T2WI) with spin‐echo sequences, diffusion‐weighted imaging with single‐shot echo‐planar sequence and at 1.5‐T. Assessment A convolutional neural network and long short‐term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI‐RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE‐MRI and non‐DCE sequences, respectively. Statistical Tests Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P‐value <0.05 was considered statistically significant. Results With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE‐MRI, the DL‐based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE‐MRI/T2WI alone, respectively. Data Conclusion The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent‐free combination is comparable to DCE‐MRI alone and the radiologists' reading in AUC and sensitivity. Evidence Level 3. Technical Efficacy Stage 2.
AbstractList	BackgroundDeep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated.PurposeTo implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences.Study TypeRetrospective.PopulationA total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female).Field Strength/SequenceT1‐weighted imaging and dynamic contrast‐enhanced MRI (DCE‐MRI) with gradient echo sequences, T2‐weighted imaging (T2WI) with spin‐echo sequences, diffusion‐weighted imaging with single‐shot echo‐planar sequence and at 1.5‐T.AssessmentA convolutional neural network and long short‐term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI‐RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE‐MRI and non‐DCE sequences, respectively.Statistical TestsSensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P‐value <0.05 was considered statistically significant.ResultsWith the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE‐MRI, the DL‐based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE‐MRI/T2WI alone, respectively.Data ConclusionThe DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent‐free combination is comparable to DCE‐MRI alone and the radiologists' reading in AUC and sensitivity.Evidence Level3.Technical EfficacyStage 2. Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated.BACKGROUNDDeep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated.To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences.PURPOSETo implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences.Retrospective.STUDY TYPERetrospective.A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female).POPULATIONA total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female).T1-weighted imaging and dynamic contrast-enhanced MRI (DCE-MRI) with gradient echo sequences, T2-weighted imaging (T2WI) with spin-echo sequences, diffusion-weighted imaging with single-shot echo-planar sequence and at 1.5-T.FIELD STRENGTH/SEQUENCET1-weighted imaging and dynamic contrast-enhanced MRI (DCE-MRI) with gradient echo sequences, T2-weighted imaging (T2WI) with spin-echo sequences, diffusion-weighted imaging with single-shot echo-planar sequence and at 1.5-T.A convolutional neural network and long short-term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI-RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE-MRI and non-DCE sequences, respectively.ASSESSMENTA convolutional neural network and long short-term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI-RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE-MRI and non-DCE sequences, respectively.Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P-value <0.05 was considered statistically significant.STATISTICAL TESTSSensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P-value <0.05 was considered statistically significant.With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE-MRI, the DL-based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE-MRI/T2WI alone, respectively.RESULTSWith the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE-MRI, the DL-based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE-MRI/T2WI alone, respectively.The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent-free combination is comparable to DCE-MRI alone and the radiologists' reading in AUC and sensitivity.DATA CONCLUSIONThe DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent-free combination is comparable to DCE-MRI alone and the radiologists' reading in AUC and sensitivity.3.EVIDENCE LEVEL3.Stage 2.TECHNICAL EFFICACYStage 2. Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated. To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences. Retrospective. A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female). T1-weighted imaging and dynamic contrast-enhanced MRI (DCE-MRI) with gradient echo sequences, T2-weighted imaging (T2WI) with spin-echo sequences, diffusion-weighted imaging with single-shot echo-planar sequence and at 1.5-T. A convolutional neural network and long short-term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI-RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE-MRI and non-DCE sequences, respectively. Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P-value <0.05 was considered statistically significant. With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE-MRI, the DL-based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE-MRI/T2WI alone, respectively. The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent-free combination is comparable to DCE-MRI alone and the radiologists' reading in AUC and sensitivity. 3. Stage 2. Background Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated. Purpose To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences. Study Type Retrospective. Population A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female). Field Strength/Sequence T1‐weighted imaging and dynamic contrast‐enhanced MRI (DCE‐MRI) with gradient echo sequences, T2‐weighted imaging (T2WI) with spin‐echo sequences, diffusion‐weighted imaging with single‐shot echo‐planar sequence and at 1.5‐T. Assessment A convolutional neural network and long short‐term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI‐RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE‐MRI and non‐DCE sequences, respectively. Statistical Tests Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P‐value <0.05 was considered statistically significant. Results With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE‐MRI, the DL‐based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE‐MRI/T2WI alone, respectively. Data Conclusion The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent‐free combination is comparable to DCE‐MRI alone and the radiologists' reading in AUC and sensitivity. Evidence Level 3. Technical Efficacy Stage 2.
Author	Wang, Yi Zhang, Jing Li, Xiaoguang Chen, Xiao Liu, Lianluyi Cong, Chao Ambale‐Venkatesh, Bharath Zhang, Chunlai Sun, Kaixiang
Author_xml	– sequence: 1 givenname: Chao orcidid: 0000-0002-1714-1892 surname: Cong fullname: Cong, Chao organization: Daping Hospital, Army Medical University – sequence: 2 givenname: Xiaoguang surname: Li fullname: Li, Xiaoguang organization: Daping Hospital, Army Medical University – sequence: 3 givenname: Chunlai surname: Zhang fullname: Zhang, Chunlai organization: Daping Hospital, Army Medical University – sequence: 4 givenname: Jing surname: Zhang fullname: Zhang, Jing organization: Daping Hospital, Army Medical University – sequence: 5 givenname: Kaixiang surname: Sun fullname: Sun, Kaixiang organization: Chongqing University of Technology – sequence: 6 givenname: Lianluyi surname: Liu fullname: Liu, Lianluyi organization: Chongqing University of Technology – sequence: 7 givenname: Bharath orcidid: 0000-0002-2330-2373 surname: Ambale‐Venkatesh fullname: Ambale‐Venkatesh, Bharath organization: Johns Hopkins University School of Medicine – sequence: 8 givenname: Xiao surname: Chen fullname: Chen, Xiao email: xiaochen229@foxmail.com organization: Daping Hospital, Army Medical University – sequence: 9 givenname: Yi surname: Wang fullname: Wang, Yi email: ywhxl@qq.com organization: Daping Hospital, Army Medical University
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37013422$$D View this record in MEDLINE/PubMed
BookMark	eNp9kctu1DAUhi1URC-w4QGQJTYIKa0v4zhe0rSFVlMhIbq2TpwzyKPEGexEdLqqxAvwjDwJblO6qBArX_R9R0f_v092whCQkNecHXLGxNG6j_5QVJrLZ2SPKyEKoapyJ9-ZkgWvmN4l-ymtGWPGLNQLsis143IhxB75efnl_Pftr2NI2NLjiJBGWkNwGGndQUp-5R2MfggUQkuXg4PO38wfzZZeTt3oNxChxzF6R88QxikiPb0eI7hHrR76xofZuko-fKMniBu6RIghv16S5yvoEr56OA_I1dnp1_pTsfz88bz-sCycVFoWTWsQTFO50jDdIkOmHGtRVZqpViBgI7AUhmvVOgXIWYYXla4qRA1GNvKAvJvnbuLwfcI02t4nh10HAYcpWaGNkiXnymT07RN0PUwx5O2sqIwpF6UsdabePFBT02NrN9H3ELf2b7wZeD8DLg4pRVw9IpzZu-7sXXf2vrsMsyew8-N9aDlM3_1b4bPyw3e4_c9we5F7np0_PSet6A
CitedBy_id	crossref_primary_10_1016_j_asjsur_2024_11_224 crossref_primary_10_1007_s00330_025_11406_6 crossref_primary_10_1016_j_bspc_2025_108085 crossref_primary_10_3390_biomedinformatics5030046 crossref_primary_10_1002_jmri_29358 crossref_primary_10_1016_j_mri_2025_110457 crossref_primary_10_1002_jmri_28733 crossref_primary_10_1016_j_clbc_2023_10_010 crossref_primary_10_1053_j_semnuclmed_2025_01_008 crossref_primary_10_1016_j_engappai_2025_111089 crossref_primary_10_1109_TAI_2025_3543822 crossref_primary_10_3389_fmed_2025_1659422 crossref_primary_10_1007_s40846_024_00912_5 crossref_primary_10_1088_1741_2552_ad788b crossref_primary_10_1148_ryai_240206
Cites_doi	10.2214/AJR.15.15957 10.1002/jmri.27332 10.1007/978-3-319-66179-7_68 10.1109/LSP.2014.2337313 10.1007/s10549-020-05533-5 10.1148/radiol.2018181352 10.1016/j.acra.2022.12.038 10.1609/aaai.v31i1.11231 10.1109/ICIP.2009.5414044 10.1007/BF02295996 10.1002/mp.13849 10.1007/s10278-013-9622-7 10.1002/jmri.25790 10.1111/1759-7714.13309 10.1097/RLI.0000000000000544 10.1007/978-3-642-24797-2_4 10.1002/jmri.26852 10.1002/(SICI)1522-2594(199912)42:6<1072::AID-MRM11>3.0.CO;2-M 10.1007/s11517-020-02232-7 10.1097/RLI.0000000000000465 10.1016/j.media.2018.10.011 10.1002/jmri.26721 10.1259/bjr.20160715 10.1200/JCO.2013.52.5386 10.3322/caac.21754 10.1148/radiol.2019182947 10.1038/s41598-020-70940-z 10.1148/ryai.2021200159 10.1007/978-3-319-10602-1_48 10.1016/j.artmed.2019.101781 10.1038/s41598-020-67441-4
ContentType	Journal Article
Copyright	2023 International Society for Magnetic Resonance in Medicine. 2024 International Society for Magnetic Resonance in Medicine
Copyright_xml	– notice: 2023 International Society for Magnetic Resonance in Medicine. – notice: 2024 International Society for Magnetic Resonance in Medicine
DBID	AAYXX CITATION NPM 7QO 7TK 8FD FR3 K9. P64 7X8
DOI	10.1002/jmri.28713
DatabaseName	CrossRef PubMed Biotechnology Research Abstracts Neurosciences Abstracts Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed ProQuest Health & Medical Complete (Alumni) Engineering Research Database Biotechnology Research Abstracts Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitleList	ProQuest Health & Medical Complete (Alumni) MEDLINE - Academic PubMed
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
EISSN	1522-2586
EndPage	161
ExternalDocumentID	37013422 10_1002_jmri_28713 JMRI28713
Genre	researchArticle Journal Article
GrantInformation_xml	– fundername: National Natural Science Foundation of China funderid: 61901068 – fundername: Chongqing Clinical Research Centre of Imaging and Nuclear Medicine funderid: CSTC2015YFPT – fundername: Science and Technology Research Program of Chongqing Municipal Education funderid: KJQN202001131 – fundername: National Natural Science Foundation of China grantid: 61901068 – fundername: Science and Technology Research Program of Chongqing Municipal Education grantid: KJQN202001131 – fundername: Chongqing Clinical Research Centre of Imaging and Nuclear Medicine grantid: CSTC2015YFPT
GroupedDBID	--- -DZ .3N .GA .GJ .Y3 05W 0R~ 10A 1L6 1OB 1OC 1ZS 31~ 33P 3O- 3SF 3WU 4.4 4ZD 50Y 50Z 51W 51X 52M 52N 52O 52P 52R 52S 52T 52U 52V 52W 52X 53G 5GY 5RE 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A01 A03 AAESR AAEVG AAHQN AAIPD AAMMB AAMNL AANHP AANLZ AAONW AASGY AAWTL AAXRX AAYCA AAZKR ABCQN ABCUV ABEML ABIJN ABJNI ABLJU ABOCM ABPVW ABQWH ABXGK ACAHQ ACBWZ ACCZN ACGFO ACGFS ACGOF ACIWK ACMXC ACPOU ACPRK ACRPL ACSCC ACXBN ACXQS ACYXJ ADBBV ADBTR ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN AEFGJ AEGXH AEIGN AEIMD AENEX AEUYR AEYWJ AFBPY AFFPM AFGKR AFRAH AFWVQ AFZJQ AGHNM AGQPQ AGXDD AGYGG AHBTC AHMBA AIACR AIAGR AIDQK AIDYY AIQQE AITYG AIURR ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ASPBG ATUGU AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMXJE BROTX BRXPI BY8 C45 CS3 D-6 D-7 D-E D-F DCZOG DPXWK DR2 DRFUL DRMAN DRSTM DU5 EBD EBS EJD EMOBN F00 F01 F04 F5P FEDTE FUBAC G-S G.N GNP GODZA H.X HBH HDBZQ HF~ HGLYW HHY HHZ HVGLF HZ~ IX1 J0M JPC KBYEO KQQ LATKE LAW LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES M65 MEWTI MK4 MRFUL MRMAN MRSTM MSFUL MSMAN MSSTM MXFUL MXMAN MXSTM N04 N05 N9A NF~ NNB O66 O9- OIG OVD P2P P2W P2X P2Z P4B P4D PALCI PQQKQ Q.N Q11 QB0 QRW R.K RIWAO RJQFR ROL RX1 RYL SAMSI SUPJJ SV3 TEORI TWZ UB1 V2E V8K V9Y W8V W99 WBKPD WHWMO WIB WIH WIJ WIK WIN WJL WOHZO WQJ WVDHM WXI WXSBR XG1 XV2 ZXP ZZTAW ~IA ~WT AAYXX CITATION O8X NPM 7QO 7TK 8FD FR3 K9. P64 7X8
ID	FETCH-LOGICAL-c3573-bd9ea9b8c6907de0e05c0de58705d2eaeb2e629175dc5ae10a9b48788ee7a93b3
IEDL.DBID	DRFUL
ISICitedReferencesCount	15
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000963752800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1053-1807 1522-2586
IngestDate	Fri Jul 11 15:08:36 EDT 2025 Sat Nov 29 14:47:27 EST 2025 Mon Jul 21 05:38:14 EDT 2025 Tue Nov 18 22:00:44 EST 2025 Sat Nov 29 06:08:47 EST 2025 Thu Sep 25 07:34:18 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	multiparametric MRI breast MRI deep learning breast cancer computer-aided detection
Language	English
License	2023 International Society for Magnetic Resonance in Medicine.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c3573-bd9ea9b8c6907de0e05c0de58705d2eaeb2e629175dc5ae10a9b48788ee7a93b3
Notes	Chao Cong and Xiaoguang Li contributed equally to this work. ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-1714-1892 0000-0002-2330-2373
PMID	37013422
PQID	2899646367
PQPubID	1006400
PageCount	14
ParticipantIDs	proquest_miscellaneous_2795361159 proquest_journals_2899646367 pubmed_primary_37013422 crossref_primary_10_1002_jmri_28713 crossref_citationtrail_10_1002_jmri_28713 wiley_primary_10_1002_jmri_28713_JMRI28713
PublicationCentury	2000
PublicationDate	January 2024
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– month: 01 year: 2024 text: January 2024
PublicationDecade	2020
PublicationPlace	Hoboken, USA
PublicationPlace_xml	– name: Hoboken, USA – name: United States – name: Nashville
PublicationSubtitle	JMRI
PublicationTitle	Journal of magnetic resonance imaging
PublicationTitleAlternate	J Magn Reson Imaging
PublicationYear	2024
Publisher	John Wiley & Sons, Inc Wiley Subscription Services, Inc
Publisher_xml	– name: John Wiley & Sons, Inc – name: Wiley Subscription Services, Inc
References	2023; 10 2019; 290 2013; 26 2019; 51 2021; 3 2019; 50 2012 2022; 72 2016; 207 2019; 54 2020; 180 2016; 10 2009 2020; 58 1999; 42 2020; 11 2020; 103 2020; 10 2018; 47 2014; 21 2021; 54 2017; 90 2023 2022 2020; 52 1947; 12 2020; 47 2017 2016 2014 2019; 292 2018; 53 2014; 32 Magny SJ (e_1_2_6_24_1) 2022 e_1_2_6_32_1 e_1_2_6_10_1 Lingle W (e_1_2_6_22_1) 2016; 10 e_1_2_6_13_1 e_1_2_6_36_1 e_1_2_6_14_1 e_1_2_6_35_1 e_1_2_6_11_1 e_1_2_6_34_1 e_1_2_6_12_1 e_1_2_6_33_1 e_1_2_6_17_1 He K (e_1_2_6_28_1) 2016 e_1_2_6_18_1 e_1_2_6_39_1 e_1_2_6_15_1 e_1_2_6_38_1 e_1_2_6_16_1 e_1_2_6_37_1 e_1_2_6_21_1 e_1_2_6_20_1 e_1_2_6_41_1 e_1_2_6_40_1 Graves A (e_1_2_6_25_1) 2012 Huang G (e_1_2_6_30_1) 2017 e_1_2_6_9_1 Hagiwara A (e_1_2_6_8_1) 2023; 10 e_1_2_6_5_1 e_1_2_6_4_1 e_1_2_6_7_1 e_1_2_6_6_1 Adachi M (e_1_2_6_19_1) 2020; 10 e_1_2_6_3_1 e_1_2_6_23_1 e_1_2_6_2_1 Selvaraju RR (e_1_2_6_31_1) 2017 e_1_2_6_29_1 e_1_2_6_27_1 e_1_2_6_26_1
References_xml	– volume: 54 start-page: 686 issue: 3 year: 2021 end-page: 702 article-title: AI‐enhanced diagnosis of challenging lesions in breast MRI: A methodology and application primer publication-title: J Magn Reson Imaging – volume: 292 start-page: 520 issue: 3 year: 2019 end-page: 536 article-title: Breast MRI: State of the art publication-title: Radiology – volume: 90 issue: 1069 year: 2017 article-title: The potential of multiparametric MRI of the breast publication-title: Br J Radiol – year: 2022 article-title: Breast Imaging Reporting and Data System publication-title: StatPearls. Treasure Island (FL): StatPearls Publishing; – volume: 10 issue: 1097 year: 2023 article-title: Multiparametric MRI: From simultaneous rapid acquisition methods and analysis techniques using scoring, machine learning, radiomics, and deep learning to the generation of novel metrics publication-title: Invest Radiol – volume: 52 start-page: 998 issue: 4 year: 2020 end-page: 1018 article-title: Machine learning in breast MRI publication-title: J Magn Reson Imaging – volume: 53 start-page: 587 issue: 10 year: 2018 end-page: 595 article-title: Diffusion‐weighted imaging with apparent diffusion coefficient mapping for breast cancer detection as a stand‐alone parameter: Comparison with dynamic contrast‐enhanced and multiparametric magnetic resonance imaging publication-title: Invest Radiol – volume: 72 start-page: 524 issue: 6 year: 2022 end-page: 541 article-title: Breast cancer statistics, 2022 publication-title: CA Cancer J Clin – volume: 103 year: 2020 article-title: Multi‐planar 3D breast segmentation in MRI via deep convolutional neural networks publication-title: Artif Intell Med – start-page: 770 year: 2016 end-page: 778 article-title: Deep residual learning for image recognition publication-title: Proc IEEE Conf Comput Vis Pattern Recogn. Las Vegas, NV – volume: 11 start-page: 651 issue: 3 year: 2020 end-page: 658 article-title: Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using a deep learning (DL) method publication-title: Thoracic Cancer – volume: 26 start-page: 1045 issue: 6 year: 2013 end-page: 1057 article-title: The cancer imaging archive (TCIA): Maintaining and operating a public information repository publication-title: J Digit Imaging – volume: 32 start-page: 2304 issue: 22 year: 2014 end-page: 2310 article-title: Abbreviated breast magnetic resonance imaging (MRI): First postcontrast subtracted images and maximum‐intensity projection—A novel approach to breast cancer screening with MRI publication-title: J Clin Oncol – volume: 50 start-page: 1144 issue: 4 year: 2019 end-page: 1151 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 – year: 2016 – start-page: 618 year: 2017 end-page: 626 article-title: Grad‐cam: Visual explanations from deep networks via gradient‐based localization publication-title: Proc IEEE Int Conf Comput Vis. Venice, Italy, – volume: 10 start-page: 10536 issue: 1 year: 2020 article-title: A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI publication-title: Sci Rep – volume: 207 start-page: 1159 issue: 5 year: 2016 end-page: 1166 article-title: Kinetic analysis of benign and malignant breast lesions with ultrafast dynamic contrast‐enhanced MRI: Comparison with standard kinetic assessment publication-title: AJR Am J Roentgenol – start-page: 3873 year: 2009 end-page: 3876 – volume: 42 start-page: 1072 issue: 6 year: 1999 end-page: 1081 article-title: On standardizing the MR image intensity scale publication-title: Magn Reson Med – volume: 51 start-page: 116 year: 2019 end-page: 124 article-title: A graph‐based lesion characterization and deep embedding approach for improved computer‐aided diagnosis of nonmass breast MRI lesions publication-title: Med Image Anal – volume: 290 start-page: 290 issue: 2 year: 2019 end-page: 297 article-title: Radiomic versus convolutional neural networks analysis for classification of contrast‐enhancing lesions at multiparametric breast MRI publication-title: Radiology – volume: 180 start-page: 407 issue: 2 year: 2020 end-page: 421 article-title: Multiparametric radiomics methods for breast cancer tissue characterization using radiological imaging publication-title: Breast Cancer Res Treat – volume: 12 start-page: 153 issue: 2 year: 1947 end-page: 157 article-title: Note on the sampling error of the difference between correlated proportions or percentages publication-title: Psychometrika – year: 2023 article-title: Deep learning‐based automatic diagnosis of breast cancer on MRI using mask R‐CNN for detection followed by ResNet50 for classification publication-title: Acad Radiol – volume: 3 issue: 3 year: 2021 article-title: Improved classification of benign and malignant breast lesions using deep feature maximum intensity projection MRI in breast cancer diagnosis using dynamic contrast‐enhanced MRI publication-title: Radiol Artif Intell – start-page: 37 year: 2012 end-page: 45 – volume: 10 issue: 5 year: 2020 article-title: Detection and diagnosis of breast cancer using artificial intelligence based assessment of maximum intensity projection dynamic contrast‐enhanced magnetic resonance images publication-title: Diagnostics (Basel) – volume: 58 start-page: 2413 issue: 10 year: 2020 end-page: 2425 article-title: A comprehensive hierarchical classification based on multi‐features of breast DCE‐MRI for cancer diagnosis publication-title: Med Biol Eng Comput – start-page: 594 year: 2017 end-page: 602 – volume: 10 year: 2016 article-title: Radiology data from the cancer genome atlas breast invasive carcinoma [TCGA‐BRCA] collection publication-title: Cancer Imag Archiv – start-page: 740 year: 2014 end-page: 755 – volume: 10 start-page: 1 issue: 1 year: 2020 end-page: 11 article-title: MRI‐based radiomics in breast cancer: Feature robustness with respect to inter‐observer segmentation variability publication-title: Sci Rep – volume: 54 start-page: 325 issue: 6 year: 2019 end-page: 332 article-title: Artificial intelligence‐based classification of breast lesions imaged with a multiparametric breast MRI protocol with ultrafast DCE‐MRI, T2, and DWI publication-title: Invest Radiol – year: 2017 – volume: 47 start-page: 75 issue: 1 year: 2020 end-page: 88 article-title: Multiparametric deep learning tissue signatures for a radiological biomarker of breast cancer: Preliminary results publication-title: Med Phys – volume: 21 start-page: 1389 issue: 11 year: 2014 end-page: 1393 article-title: Fast implementation of DeLong's algorithm for comparing the areas under correlated receiver operating characteristic curves publication-title: IEEE Signal Process Lett – volume: 2022 article-title: Cancer Facts & Figures 2022 publication-title: American Cancer Society – volume: 47 start-page: 301 issue: 2 year: 2018 end-page: 315 article-title: Multiparametric MRI of the breast: A review publication-title: J Magn Reson Imaging – start-page: 4700 year: 2017 end-page: 4708 article-title: Densely connected convolutional networks publication-title: Proc IEEE Conf Comput Vis Pattern Recogn. Honolulu, HI, – ident: e_1_2_6_40_1 doi: 10.2214/AJR.15.15957 – ident: e_1_2_6_7_1 doi: 10.1002/jmri.27332 – ident: e_1_2_6_37_1 doi: 10.1007/978-3-319-66179-7_68 – ident: e_1_2_6_33_1 doi: 10.1109/LSP.2014.2337313 – volume: 10 year: 2016 ident: e_1_2_6_22_1 article-title: Radiology data from the cancer genome atlas breast invasive carcinoma [TCGA‐BRCA] collection publication-title: Cancer Imag Archiv – ident: e_1_2_6_20_1 doi: 10.1007/s10549-020-05533-5 – ident: e_1_2_6_13_1 doi: 10.1148/radiol.2018181352 – ident: e_1_2_6_38_1 doi: 10.1016/j.acra.2022.12.038 – start-page: 770 year: 2016 ident: e_1_2_6_28_1 article-title: Deep residual learning for image recognition publication-title: Proc IEEE Conf Comput Vis Pattern Recogn. Las Vegas, NV – ident: e_1_2_6_29_1 doi: 10.1609/aaai.v31i1.11231 – start-page: 4700 year: 2017 ident: e_1_2_6_30_1 article-title: Densely connected convolutional networks publication-title: Proc IEEE Conf Comput Vis Pattern Recogn. Honolulu, HI, – ident: e_1_2_6_26_1 doi: 10.1109/ICIP.2009.5414044 – ident: e_1_2_6_34_1 doi: 10.1007/BF02295996 – ident: e_1_2_6_15_1 doi: 10.1002/mp.13849 – ident: e_1_2_6_23_1 doi: 10.1007/s10278-013-9622-7 – ident: e_1_2_6_6_1 doi: 10.1002/jmri.25790 – ident: e_1_2_6_14_1 doi: 10.1111/1759-7714.13309 – ident: e_1_2_6_17_1 doi: 10.1097/RLI.0000000000000544 – start-page: 37 volume-title: Long short‐term memory. Supervised sequence labelling with recurrent neural networks year: 2012 ident: e_1_2_6_25_1 doi: 10.1007/978-3-642-24797-2_4 – ident: e_1_2_6_10_1 doi: 10.1002/jmri.26852 – ident: e_1_2_6_2_1 – volume: 10 issue: 1097 year: 2023 ident: e_1_2_6_8_1 article-title: Multiparametric MRI: From simultaneous rapid acquisition methods and analysis techniques using scoring, machine learning, radiomics, and deep learning to the generation of novel metrics publication-title: Invest Radiol – ident: e_1_2_6_27_1 doi: 10.1002/(SICI)1522-2594(199912)42:6<1072::AID-MRM11>3.0.CO;2-M – ident: e_1_2_6_36_1 doi: 10.1007/s11517-020-02232-7 – ident: e_1_2_6_16_1 doi: 10.1097/RLI.0000000000000465 – ident: e_1_2_6_12_1 doi: 10.1016/j.media.2018.10.011 – ident: e_1_2_6_9_1 doi: 10.1002/jmri.26721 – ident: e_1_2_6_32_1 – ident: e_1_2_6_4_1 doi: 10.1259/bjr.20160715 – ident: e_1_2_6_41_1 doi: 10.1200/JCO.2013.52.5386 – volume: 10 issue: 5 year: 2020 ident: e_1_2_6_19_1 article-title: Detection and diagnosis of breast cancer using artificial intelligence based assessment of maximum intensity projection dynamic contrast‐enhanced magnetic resonance images publication-title: Diagnostics (Basel) – ident: e_1_2_6_3_1 doi: 10.3322/caac.21754 – ident: e_1_2_6_5_1 doi: 10.1148/radiol.2019182947 – ident: e_1_2_6_21_1 doi: 10.1038/s41598-020-70940-z – ident: e_1_2_6_39_1 doi: 10.1148/ryai.2021200159 – ident: e_1_2_6_35_1 doi: 10.1007/978-3-319-10602-1_48 – year: 2022 ident: e_1_2_6_24_1 article-title: Breast Imaging Reporting and Data System publication-title: StatPearls. Treasure Island (FL): StatPearls Publishing; – start-page: 618 year: 2017 ident: e_1_2_6_31_1 article-title: Grad‐cam: Visual explanations from deep networks via gradient‐based localization publication-title: Proc IEEE Int Conf Comput Vis. Venice, Italy, – ident: e_1_2_6_11_1 doi: 10.1016/j.artmed.2019.101781 – ident: e_1_2_6_18_1 doi: 10.1038/s41598-020-67441-4
SSID	ssj0009945
Score	2.4981833
Snippet	Background Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer... Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not... BackgroundDeep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer...
SourceID	proquest pubmed crossref wiley
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	148
SubjectTerms	Artificial neural networks Breast cancer breast MRI Classification computer‐aided detection Contrast agents Contrast media Deep learning Feature extraction Females Field strength Histopathology Lesions Localization Machine learning Magnetic resonance imaging Medical imaging multiparametric MRI Neural networks Population studies Sensitivity Statistical analysis Statistical tests
Title	MRI‐Based Breast Cancer Classification and Localization by Multiparametric Feature Extraction and Combination Using Deep Learning
URI	https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fjmri.28713 https://www.ncbi.nlm.nih.gov/pubmed/37013422 https://www.proquest.com/docview/2899646367 https://www.proquest.com/docview/2795361159
Volume	59
WOSCitedRecordID	wos000963752800001&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 - Journals customDbUrl: eissn: 1522-2586 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009945 issn: 1053-1807 databaseCode: DRFUL dateStart: 19990101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1faxQxEB_aq0hfqlXbrtYS0ReFbfeSzWUDvtg_h5W2SLFwb8smmS0t7bbs3Ym-CX4BP6OfxEx2b4-iCOLbwk7IsjOT-U2S-Q3AKzUoOXc-O8mco90qVcbGZDJO-6WwItUGXRqaTaiTk2w00h8X4O2sFqbhh-g23MgzwnpNDl6Y8c6cNPTyur7YJrwvFmGJe8NNe7C0fzo8O5qT7urQpNhDCBH3s0R19KR8Zz76bkD6DWXeBa0h6gwf_N_3PoSVFm2yd415rMICVo_g_nF7nv4Yvh-fHv789mPXhzLHdul--oTtkR3ULHTLpHtEQXWsqBw7orjX1m0y85WF4l3iDr-mtlyWEZyc1sgOvkzqpl4iDPNLjk-_m1HhhgLbR7xlLbPr-RM4Gx582nsft20ZYiukErFxGgttMkuJtcMEE2kTh9J7vnQcC5-r44D7NFA6KwvsJ17YG0GWIapCCyPWoFfdVLgBLHUFYRQhtCzTUibGIKcVwRmhben6Ebye6Sa3LWc5tc64yhu2ZZ7TX83DX43gZSd72zB1_FFqc6bivPXWcU5J54CY01QEL7rX3s_o8KSo8GbqZRQddHv8rCNYb0yjm0YoD6RTziN4EyzgL_PnH7xiw9PTfxF-Bsvco6lm72cTepN6is_hnv08uRjXW7CoRtlWa_2_AJ1ACeQ
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7BFgEX3o9AASO4UCk0a8fr-EgfqxZ2V6hqpd6i2J6gIppW6S6CGxJ_gN_IL8HjuFlVICTELVLGchTPeL4Zj78BeKlGNefORyeFc5StUnVqTCHTfFgLK3Jt0OWh2YSazYrDQ_0-1ubQXZiOH6JPuJFlhP2aDJwS0utL1tCPx-3RawL84jKs5F6P5ABWtvbGB5Ml664OXYo9hhDpsMhUz0_K15ejL3qk32DmRdQa3M745n9-8C24EfEme9MpyG24hM0duDqNJ-p34ft0b_fntx8b3pk5tkEV6nO2SZrQstAvkyqJwuKxqnFsQp4v3txk5isL13eJPfyYGnNZRoBy0SLb_jJvuxsTYZjfdHwA3o0KNQpsC_GURW7XD_fgYLy9v7mTxsYMqRVSidQ4jZU2haXQ2mGGmbSZQ-ltXzqOlY_WccR9ICidlRUOMy_s1aAoEFWlhRH3YdCcNPgQWO4qQilCaFnntcyMQU57gjNC29oNE3h1vjiljazl1DzjU9nxLfOS_moZ_moCL3rZ046r449Sq-drXEZ7PSsp7BwRd5pK4Hn_2lsaHZ9UDZ4svIyio26PoHUCDzrd6KcRykPpnPME1oIK_GX-8q1f2PD06F-En8G1nf3ppJzszt49huvcY6suE7QKg3m7wCdwxX6eH521T6MR_AI2Ngzs
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NbtQwEB5Bi6pe-P8JFDCCC0ihWTtex0fa7YrCdlVVVOotiu0JakXTVbqL4IbEC_CMPAkex82qAiEhbpEylqPMjP2NPfMNwAs1rDl3PjopnKPTKlWnxhQyzQe1sCLXBl0emk2o6bQ4OtL7MTeHamE6foj-wI08I6zX5OA4c_XmkjX05LQ9fk2AX1yF1VzqoffL1dHB-HCyZN3VoUuxxxAiHRSZ6vlJ-eZy9OUd6TeYeRm1hm1nfOM_P_gmXI94k73pDOQWXMHmNqztxRv1O_B972D357cfW34zc2yLMtTnbJssoWWhXyZlEgXlsapxbEI7X6zcZOYrC-W7xB5-So25LCNAuWiR7XyZt13FRBjmFx0fgHejQo4CGyHOWOR2_XgXDsc7H7bfprExQ2qFVCI1TmOlTWEptHaYYSZt5lB635eOY-WjdRxyHwhKZ2WFg8wLezMoCkRVaWHEPVhpzhp8ACx3FaEUIbSs81pmxiCnNcEZoW3tBgm8vFBOaSNrOTXP-FR2fMu8pL9ahr-awPNedtZxdfxRauNCx2X01_OSws4hcaepBJ71r72n0fVJ1eDZwssouur2CFoncL-zjX4aoTyUzjlP4FUwgb_MX77zig1PD_9F-Cms7Y_G5WR3-v4RrHMPrbqDoA1YmbcLfAzX7Of58Xn7JPrAL6_4DGc
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=MRI-Based+Breast+Cancer+Classification+and+Localization+by+Multiparametric+Feature+Extraction+and+Combination+Using+Deep+Learning&rft.jtitle=Journal+of+magnetic+resonance+imaging&rft.au=Cong%2C+Chao&rft.au=Li%2C+Xiaoguang&rft.au=Zhang%2C+Chunlai&rft.au=Zhang%2C+Jing&rft.date=2024-01-01&rft.issn=1522-2586&rft.eissn=1522-2586&rft.volume=59&rft.issue=1&rft.spage=148&rft_id=info:doi/10.1002%2Fjmri.28713&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-1807&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-1807&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-1807&client=summon