Detection of Cerebral Microbleeds in MR Images Using a Single‐Stage Triplanar Ensemble Detection Network (TPE‐Det)
Background Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the prev...
Saved in:
Published in | Journal of magnetic resonance imaging Vol. 58; no. 1; pp. 272 - 283 |
---|---|
Main Authors | , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Hoboken, USA
John Wiley & Sons, Inc
01.07.2023
Wiley Subscription Services, Inc |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Background
Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows.
Purpose
To develop a clinically feasible end‐to‐end CMBs detection network with a single‐stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE‐Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes.
Study Type
Retrospective.
Subjects
Two datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2).
Field Strength/Sequence
A 3 T field strength and 3D GRE sequence scan for SWI reconstructions.
Assessment
The sensitivity, FPavg (false‐positive per subject), and precision measures were computed and analyzed with statistical analysis.
Statistical Tests
A paired t‐test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant.
Results
The proposed TPE‐Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FPavg of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FPavg of 0.55. The precision was significantly higher than the other models.
Data Conclusion
The ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic.
Evidence Level
1
Technical Efficacy
Stage 2 |
---|---|
AbstractList | BackgroundCerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows.PurposeTo develop a clinically feasible end‐to‐end CMBs detection network with a single‐stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE‐Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes.Study TypeRetrospective.SubjectsTwo datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2).Field Strength/SequenceA 3 T field strength and 3D GRE sequence scan for SWI reconstructions.AssessmentThe sensitivity, FPavg (false‐positive per subject), and precision measures were computed and analyzed with statistical analysis.Statistical TestsA paired t‐test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant.ResultsThe proposed TPE‐Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FPavg of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FPavg of 0.55. The precision was significantly higher than the other models.Data ConclusionThe ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic.Evidence Level1Technical EfficacyStage 2 Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows. To develop a clinically feasible end-to-end CMBs detection network with a single-stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE-Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes. Retrospective. Two datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2). A 3 T field strength and 3D GRE sequence scan for SWI reconstructions. The sensitivity, FP (false-positive per subject), and precision measures were computed and analyzed with statistical analysis. A paired t-test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant. The proposed TPE-Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FP of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FP of 0.55. The precision was significantly higher than the other models. The ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic. 1 TECHNICAL EFFICACY: Stage 2. Background Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows. Purpose To develop a clinically feasible end‐to‐end CMBs detection network with a single‐stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE‐Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes. Study Type Retrospective. Subjects Two datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2). Field Strength/Sequence A 3 T field strength and 3D GRE sequence scan for SWI reconstructions. Assessment The sensitivity, FPavg (false‐positive per subject), and precision measures were computed and analyzed with statistical analysis. Statistical Tests A paired t‐test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant. Results The proposed TPE‐Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FPavg of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FPavg of 0.55. The precision was significantly higher than the other models. Data Conclusion The ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic. Evidence Level 1 Technical Efficacy Stage 2 Background Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows. Purpose To develop a clinically feasible end‐to‐end CMBs detection network with a single‐stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE‐Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes. Study Type Retrospective. Subjects Two datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2). Field Strength/Sequence A 3 T field strength and 3D GRE sequence scan for SWI reconstructions. Assessment The sensitivity, FP avg (false‐positive per subject), and precision measures were computed and analyzed with statistical analysis. Statistical Tests A paired t ‐test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant. Results The proposed TPE‐Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FP avg of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FP avg of 0.55. The precision was significantly higher than the other models. Data Conclusion The ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic. Evidence Level 1 Technical Efficacy Stage 2 |
Author | Sohn, Chul‐Ho Al‐masni, Mohammed A. Lee, Haejoon Kim, Eung Yeop Jung, Kyu‐Jin Noh, Young Kang, Koung Mi Lee, Seul Lee, Dong Young Kim, Jun‐Ho Kim, Woo‐Ram Kim, Dong‐Hyun |
Author_xml | – sequence: 1 givenname: Haejoon surname: Lee fullname: Lee, Haejoon organization: Carnegie Mellon University – sequence: 2 givenname: Jun‐Ho surname: Kim fullname: Kim, Jun‐Ho organization: Yonsei University – sequence: 3 givenname: Seul surname: Lee fullname: Lee, Seul organization: Yonsei University – sequence: 4 givenname: Kyu‐Jin surname: Jung fullname: Jung, Kyu‐Jin organization: Yonsei University – sequence: 5 givenname: Woo‐Ram surname: Kim fullname: Kim, Woo‐Ram organization: Gachon University – sequence: 6 givenname: Young surname: Noh fullname: Noh, Young organization: Gil Medical Center – sequence: 7 givenname: Eung Yeop orcidid: 0000-0002-9579-4098 surname: Kim fullname: Kim, Eung Yeop organization: Gil Medical Center – sequence: 8 givenname: Koung Mi surname: Kang fullname: Kang, Koung Mi organization: Seoul National University College of Medicine – sequence: 9 givenname: Chul‐Ho surname: Sohn fullname: Sohn, Chul‐Ho organization: Seoul National University College of Medicine – sequence: 10 givenname: Dong Young surname: Lee fullname: Lee, Dong Young organization: Medical Research Center Seoul National University – sequence: 11 givenname: Mohammed A. orcidid: 0000-0002-1548-965X surname: Al‐masni fullname: Al‐masni, Mohammed A. email: m.almasani@sejong.ac.kr organization: Sejong University – sequence: 12 givenname: Dong‐Hyun orcidid: 0000-0002-6717-7770 surname: Kim fullname: Kim, Dong‐Hyun email: donghyunkim@yonsei.ac.kr organization: Yonsei University |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36285604$$D View this record in MEDLINE/PubMed |
BookMark | eNp9kEtOwzAQhi0EghbYcABkiQ0gBfyIE3uJSoGiFhCUdeQkk8olj2KnVOw4AmfkJBhaYMdqRjPf_Ja_LlqvmxoQ2qPkhBLCTqeVNSdMhjJeQx0qGAuYkNG674ngAZUk3kJd56aEEKVCsYm2eMSkiEjYQS_n0ELWmqbGTYF7YCG1usQjk9kmLQFyh02NR_d4UOkJOPzoTD3BGj_4UsLH2_tD6-d4bM2s1LW2uF87qPwl_gu-gXbR2Cd8OL7r-wu_ONpBG4UuHeyu6jZ6vOiPe1fB8PZy0DsbBhlnYRwwrvKCExkqSZnwDXCqVR5SmqqI5SBYFsqM8UylaRxR0KIQqVQxMK1ITDK-jQ6WuTPbPM_Btcm0mdvaP5kwyULuRXDlqeMl5T_tnIUimVlTafuaUJJ8KU6-FCffij28v4qcpxXkv-iPUw_QJbAwJbz-E5Vcj-4Hy9BPyaSIuw |
CitedBy_id | crossref_primary_10_1016_j_heliyon_2023_e22879 |
Cites_doi | 10.12779/dnd.2018.17.3.73 10.1161/STROKEAHA.114.006448 10.1016/S1474-4422(09)70013-4 10.1007/3-540-45014-9_1 10.1016/j.neuroimage.2019.05.046 10.1159/000139661 10.1109/TMI.2016.2528129 10.3389/fnins.2019.00422 10.1117/1.JMI.7.5.051202 10.1016/j.media.2021.102184 10.1088/1361-6560/ab0dc0 10.1007/s00138-019-01029-5 10.1002/hbm.10062 10.1148/radiol.2018170803 10.1016/S1474-4422(13)70124-8 10.1109/EMBC44109.2020.9176073 10.31728/jnn.2018.00022 10.2217/fnl.11.42 10.1109/AICAS54282.2022.9869855 10.1016/j.neuroimage.2011.09.061 10.1212/01.wnl.0000194266.55694.1e 10.1016/j.jalz.2011.05.2351 10.1007/s10278-018-0146-z 10.1016/j.nicl.2016.07.002 10.1016/j.jstrokecerebrovasdis.2021.105886 10.1186/alzrt263 10.1109/3DV.2016.79 10.1161/STROKEAHA.114.004130 10.1212/WNL.56.6.773 10.1016/j.nicl.2020.102464 10.1161/STROKEAHA.110.595181 10.1109/CVPR42600.2020.01079 10.1109/ACCESS.2020.2977669 |
ContentType | Journal Article |
Copyright | 2022 International Society for Magnetic Resonance in Medicine. 2023 International Society for Magnetic Resonance in Medicine |
Copyright_xml | – notice: 2022 International Society for Magnetic Resonance in Medicine. – notice: 2023 International Society for Magnetic Resonance in Medicine |
DBID | NPM AAYXX CITATION 7QO 7TK 8FD FR3 K9. P64 |
DOI | 10.1002/jmri.28487 |
DatabaseName | PubMed CrossRef Biotechnology Research Abstracts Neurosciences Abstracts Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Biotechnology and BioEngineering Abstracts |
DatabaseTitle | PubMed CrossRef ProQuest Health & Medical Complete (Alumni) Engineering Research Database Biotechnology Research Abstracts Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts |
DatabaseTitleList | ProQuest Health & Medical Complete (Alumni) PubMed CrossRef |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine |
EISSN | 1522-2586 |
EndPage | 283 |
ExternalDocumentID | 10_1002_jmri_28487 36285604 JMRI28487 |
Genre | researchArticle Journal Article |
GrantInformation_xml | – fundername: National Research Foundation of Korea (NRF) funderid: 2018M3C7A1056884; NRF‐2019R1A2C1090635 – fundername: Korea Medical Device Development Fund funderid: 202011D23 – fundername: National Research Foundation of Korea (NRF) grantid: 2018M3C7A1056884 – fundername: National Research Foundation of Korea (NRF) grantid: NRF-2019R1A2C1090635 – fundername: Korea Medical Device Development Fund grantid: 202011D23 |
GroupedDBID | --- -DZ .3N .GA .GJ .Y3 05W 0R~ 10A 1L6 1OB 1OC 1ZS 24P 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 AAHHS AANLZ AAONW AASGY AAWTL AAXRX AAZKR ABCQN ABCUV ABEML ABIJN ABJNI ABLJU ABOCM ABPVW ABQWH ABXGK ACAHQ ACBWZ ACCFJ ACCZN ACGFO ACGFS ACGOF ACIWK ACMXC ACPOU ACPRK ACSCC ACXBN ACXQS ADBBV ADBTR ADEOM ADIZJ ADKYN ADMGS ADOZA ADXAS ADZMN AEEZP AEGXH AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFFPM AFGKR AFPWT AFRAH AFZJQ AHBTC AHMBA AIACR AIAGR AITYG AIURR AIWBW AJBDE ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN 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 RGB RIWAO RJQFR ROL RWI RX1 RYL SAMSI SUPJJ SV3 TEORI TWZ UB1 V2E V8K V9Y W8V W99 WBKPD WHWMO WIB WIH WIJ WIK WIN WJL WOHZO WQJ WRC WUP WVDHM WXI WXSBR XG1 XV2 ZXP ZZTAW ~IA ~WT ACXME NPM ZA5 AAYXX CITATION 7QO 7TK 8FD FR3 K9. P64 |
ID | FETCH-LOGICAL-c3247-239df308498125308e31a9d411b962de52c48c23c9bb761ea5f5b897e2a9070c3 |
IEDL.DBID | DR2 |
ISSN | 1053-1807 |
IngestDate | Fri Sep 13 10:31:42 EDT 2024 Fri Aug 23 02:05:14 EDT 2024 Thu May 23 23:31:29 EDT 2024 Sat Aug 24 00:58:43 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Keywords | deep learning cerebral microbleeds computer-aided detection susceptibility-weighted imaging EfficientDet CNNs |
Language | English |
License | 2022 International Society for Magnetic Resonance in Medicine. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c3247-239df308498125308e31a9d411b962de52c48c23c9bb761ea5f5b897e2a9070c3 |
ORCID | 0000-0002-1548-965X 0000-0002-9579-4098 0000-0002-6717-7770 |
PMID | 36285604 |
PQID | 2824336239 |
PQPubID | 1006400 |
PageCount | 12 |
ParticipantIDs | proquest_journals_2824336239 crossref_primary_10_1002_jmri_28487 pubmed_primary_36285604 wiley_primary_10_1002_jmri_28487_JMRI28487 |
PublicationCentury | 2000 |
PublicationDate | July 2023 2023-Jul 2023-07-00 20230701 |
PublicationDateYYYYMMDD | 2023-07-01 |
PublicationDate_xml | – month: 07 year: 2023 text: July 2023 |
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 | 2023 |
Publisher | John Wiley & Sons, Inc Wiley Subscription Services, Inc |
Publisher_xml | – name: John Wiley & Sons, Inc – name: Wiley Subscription Services, Inc |
References | 2002; 17 2018; 287 2019; 30 2019; 32 2019; 13 2009 1999; 20 2000; 1857 2012; 59 2011; 6 2021; 30 2021; 73 2010; 41 2014; 45 2016; 35 2011; 7 2016; 12 2020; 8 2020; 7 2018; 17 2015; 28 2019; 64 2022 2021 2006; 66 2020 2013; 12 2020; 28 2014; 15 2008; 26 2009; 8 2016 2001; 56 2018; 10 2014; 6 2019; 198 e_1_2_6_32_1 e_1_2_6_10_1 e_1_2_6_31_1 Ganaie M (e_1_2_6_39_1) 2021 e_1_2_6_19_1 Ren SQ (e_1_2_6_29_1) 2015; 28 Settles B (e_1_2_6_41_1) 2009 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_12_1 Sudre CH (e_1_2_6_22_1) 2021 e_1_2_6_33_1 e_1_2_6_17_1 e_1_2_6_18_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_40_1 Srivastava N (e_1_2_6_20_1) 2014; 15 e_1_2_6_9_1 e_1_2_6_8_1 Çiçek Ö (e_1_2_6_30_1) 2016 Fazekas F (e_1_2_6_34_1) 1999; 20 e_1_2_6_5_1 e_1_2_6_4_1 e_1_2_6_7_1 e_1_2_6_6_1 e_1_2_6_25_1 e_1_2_6_24_1 e_1_2_6_3_1 e_1_2_6_23_1 e_1_2_6_2_1 e_1_2_6_28_1 e_1_2_6_27_1 e_1_2_6_26_1 |
References_xml | – year: 2009 – volume: 10 start-page: 80 issue: 2 year: 2018 end-page: 94 article-title: Cerebral microbleeds: Incidence, imaging characteristics, common and uncommon causes publication-title: J Neurosonol Neuroimag – volume: 8 start-page: 43325 year: 2020 end-page: 43335 article-title: Stenosis detection from time‐of‐flight magnetic resonance angiography via deep learning 3D squeeze and excitation residual networks publication-title: IEEE Access – volume: 12 start-page: 822 issue: 8 year: 2013 end-page: 838 article-title: Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration publication-title: Lancet Neurol – start-page: 1 year: 2021 end-page: 44 article-title: Where is VALDO ‐ vascular lesions detection and segmentation challenge at MICCAI 2021 publication-title: arXiv – volume: 45 start-page: 1492 issue: 5 year: 2014 end-page: 1494 article-title: Risk factors, stroke prevention treatments, and prevalence of cerebral microbleeds in the Framingham heart study publication-title: Stroke – volume: 20 start-page: 637 issue: 4 year: 1999 end-page: 642 article-title: Histopathologic analysis of foci of signal loss on gradient‐echo T2*‐weighted MR images in patients with spontaneous intracerebral hemorrhage: Evidence of microangiopathy‐related microbleeds publication-title: AJNR Am J Neuroradiol – start-page: 565 year: 2016 end-page: 571 – volume: 17 start-page: 143 issue: 3 year: 2002 end-page: 155 article-title: Fast robust automated brain extraction publication-title: Hum Brain Mapp – volume: 12 start-page: 241 year: 2016 end-page: 251 article-title: Automated detection of cerebral microbleeds in patients with traumatic brain injury publication-title: Neuroimage‐Clin – volume: 8 start-page: 165 issue: 2 year: 2009 end-page: 174 article-title: Cerebral microbleeds: A guide to detection and interpretation publication-title: Lancet Neurol – volume: 56 start-page: 773 issue: 6 year: 2001 end-page: 777 article-title: Recurrent brain hemorrhage is more frequent than ischemic stroke after intracranial hemorrhage publication-title: Neurology – start-page: 424 year: 2016 end-page: 432 – volume: 7 start-page: 367 issue: 4 year: 2011 end-page: 385 article-title: Amyloid‐related imaging abnormalities in amyloid‐modifying therapeutic trials: Recommendations from the Alzheimer's Association research roundtable workgroup publication-title: Alzheimers Dement – volume: 198 start-page: 271 year: 2019 end-page: 282 article-title: Cerebral microbleed detection using susceptibility weighted imaging and deep learning publication-title: Neuroimage – start-page: 1 year: 2022 end-page: 4 – volume: 6 start-page: 587 issue: 5 year: 2011 end-page: 611 article-title: Cerebral microbleeds: Detection, mechanisms and clinical challenges publication-title: Future Neurol – volume: 64 start-page: 115004 issue: 11 year: 2019 article-title: Higher SNR PET image prediction using a deep learning model and MRI image publication-title: Phys Med Biol – start-page: 1055 year: 2020 end-page: 1058 – volume: 6 start-page: 33 issue: 3 year: 2014 article-title: Cerebral microbleeds: Overview and implications in cognitive impairment publication-title: Alzheimers Res Ther – volume: 32 start-page: 766 issue: 5 year: 2019 end-page: 772 article-title: Toward automatic detection of radiation‐induced cerebral microbleeds using a 3D deep residual network publication-title: J Digit Imaging – volume: 26 start-page: 142 issue: 2 year: 2008 end-page: 146 article-title: Direct comparison of histology of microbleeds with postmortem MR images publication-title: Cerebrovasc Dis – volume: 28 start-page: 91 year: 2015 end-page: 99 article-title: Faster R‐CNN: Towards real‐time object detection with region proposal networks publication-title: Adv Neur In – volume: 41 start-page: S103 issue: 10 Suppl year: 2010 end-page: S106 article-title: Prevalence and risk factors of cerebral microbleeds: An update of the Rotterdam scan study publication-title: Stroke – volume: 15 start-page: 1929 year: 2014 end-page: 1958 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res – volume: 30 issue: 9 year: 2021 article-title: Novel approaches to detection of cerebral microbleeds: Single deep learning model to achieve a balanced performance publication-title: J Stroke Cerebrovasc – start-page: 10781 year: 2020 end-page: 10790 – volume: 28 year: 2020 article-title: Automated detection of cerebral microbleeds in MR images: A two‐stage deep learning approach publication-title: Neuroimage‐Clin – volume: 30 start-page: 1123 issue: 7–8 year: 2019 end-page: 1133 article-title: Detecting cerebral microbleeds with transfer learning publication-title: Mach Vision Appl – volume: 66 start-page: 165 issue: 2 year: 2006 end-page: 171 article-title: Cerebral microbleeds on MRI ‐ prevalence, associations, and potential clinical implications publication-title: Neurology – start-page: 1 year: 2021 end-page: 47 article-title: Ensemble deep learning: A review publication-title: arXiv Preprint – volume: 7 start-page: 051202 issue: 5 year: 2020 article-title: 2D CNN versus 3D CNN for false‐positive reduction in lung cancer screening publication-title: J Med Imaging – volume: 35 start-page: 1182 issue: 5 year: 2016 end-page: 1195 article-title: Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks publication-title: IEEE Trans Med Imaging – volume: 13 start-page: 422 year: 2019 article-title: Cerebral micro‐bleeding detection based on densely connected neural network publication-title: Front Neurosci‐Switz – volume: 287 start-page: 11 issue: 1 year: 2018 end-page: 28 article-title: Cerebral microbleeds: Imaging and clinical significance publication-title: Radiology – volume: 59 start-page: 2266 issue: 3 year: 2012 end-page: 2273 article-title: Efficient detection of cerebral microbleeds on 7.0 T MR images using the radial symmetry transform publication-title: Neuroimage – volume: 45 start-page: 2900 issue: 10 year: 2014 end-page: 2905 article-title: Number of cerebral microbleeds and risk of intracerebral hemorrhage after intravenous thrombolysis publication-title: Stroke – volume: 73 year: 2021 article-title: Triplanar ensemble U‐net model for white matter hyperintensities segmentation on MR images publication-title: Med Image Anal – volume: 1857 start-page: 1 year: 2000 end-page: 15 article-title: Ensemble methods in machine learning publication-title: Lect Notes Comput Sc – volume: 17 start-page: 73 issue: 3 year: 2018 end-page: 82 article-title: Characteristics of cerebral microbleeds publication-title: Dement Neurocogn Disord – ident: e_1_2_6_5_1 doi: 10.12779/dnd.2018.17.3.73 – ident: e_1_2_6_35_1 doi: 10.1161/STROKEAHA.114.006448 – start-page: 1 year: 2021 ident: e_1_2_6_39_1 article-title: Ensemble deep learning: A review publication-title: arXiv Preprint contributor: fullname: Ganaie M – ident: e_1_2_6_26_1 doi: 10.1016/S1474-4422(09)70013-4 – volume: 20 start-page: 637 issue: 4 year: 1999 ident: e_1_2_6_34_1 article-title: Histopathologic analysis of foci of signal loss on gradient‐echo T2*‐weighted MR images in patients with spontaneous intracerebral hemorrhage: Evidence of microangiopathy‐related microbleeds publication-title: AJNR Am J Neuroradiol contributor: fullname: Fazekas F – ident: e_1_2_6_40_1 doi: 10.1007/3-540-45014-9_1 – ident: e_1_2_6_9_1 doi: 10.1016/j.neuroimage.2019.05.046 – ident: e_1_2_6_25_1 doi: 10.1159/000139661 – ident: e_1_2_6_8_1 doi: 10.1109/TMI.2016.2528129 – ident: e_1_2_6_15_1 doi: 10.3389/fnins.2019.00422 – ident: e_1_2_6_18_1 doi: 10.1117/1.JMI.7.5.051202 – ident: e_1_2_6_21_1 doi: 10.1016/j.media.2021.102184 – ident: e_1_2_6_38_1 doi: 10.1088/1361-6560/ab0dc0 – ident: e_1_2_6_16_1 doi: 10.1007/s00138-019-01029-5 – volume-title: Active learning literature survey, Report 1648 year: 2009 ident: e_1_2_6_41_1 contributor: fullname: Settles B – ident: e_1_2_6_27_1 doi: 10.1002/hbm.10062 – volume: 15 start-page: 1929 year: 2014 ident: e_1_2_6_20_1 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J Mach Learn Res contributor: fullname: Srivastava N – volume: 28 start-page: 91 year: 2015 ident: e_1_2_6_29_1 article-title: Faster R‐CNN: Towards real‐time object detection with region proposal networks publication-title: Adv Neur In contributor: fullname: Ren SQ – start-page: 1 year: 2021 ident: e_1_2_6_22_1 article-title: Where is VALDO ‐ vascular lesions detection and segmentation challenge at MICCAI 2021 publication-title: arXiv contributor: fullname: Sudre CH – ident: e_1_2_6_3_1 doi: 10.1148/radiol.2018170803 – ident: e_1_2_6_23_1 doi: 10.1016/S1474-4422(13)70124-8 – ident: e_1_2_6_14_1 doi: 10.1109/EMBC44109.2020.9176073 – ident: e_1_2_6_7_1 doi: 10.31728/jnn.2018.00022 – ident: e_1_2_6_6_1 doi: 10.2217/fnl.11.42 – ident: e_1_2_6_17_1 doi: 10.1109/AICAS54282.2022.9869855 – ident: e_1_2_6_31_1 doi: 10.1016/j.neuroimage.2011.09.061 – ident: e_1_2_6_4_1 doi: 10.1212/01.wnl.0000194266.55694.1e – ident: e_1_2_6_37_1 doi: 10.1016/j.jalz.2011.05.2351 – ident: e_1_2_6_10_1 doi: 10.1007/s10278-018-0146-z – ident: e_1_2_6_24_1 doi: 10.1016/j.nicl.2016.07.002 – ident: e_1_2_6_12_1 doi: 10.1016/j.jstrokecerebrovasdis.2021.105886 – ident: e_1_2_6_2_1 doi: 10.1186/alzrt263 – ident: e_1_2_6_19_1 doi: 10.1109/3DV.2016.79 – ident: e_1_2_6_33_1 doi: 10.1161/STROKEAHA.114.004130 – ident: e_1_2_6_36_1 doi: 10.1212/WNL.56.6.773 – start-page: 424 volume-title: International conference on medical image computing and computer‐assisted intervention (MICCAI), medical image computing and computer‐assisted intervention – MICCAI 2016 year: 2016 ident: e_1_2_6_30_1 contributor: fullname: Çiçek Ö – ident: e_1_2_6_11_1 doi: 10.1016/j.nicl.2020.102464 – ident: e_1_2_6_32_1 doi: 10.1161/STROKEAHA.110.595181 – ident: e_1_2_6_28_1 doi: 10.1109/CVPR42600.2020.01079 – ident: e_1_2_6_13_1 doi: 10.1109/ACCESS.2020.2977669 |
SSID | ssj0009945 |
Score | 2.4694803 |
Snippet | Background
Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging... Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to... BackgroundCerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging... |
SourceID | proquest crossref pubmed wiley |
SourceType | Aggregation Database Index Database Publisher |
StartPage | 272 |
SubjectTerms | Artificial neural networks Brain cerebral microbleeds CNNs computer‐aided detection deep learning EfficientDet Field strength Hemorrhage Information processing Magnetic resonance imaging Neural networks Sensitivity analysis Statistical analysis Statistical tests susceptibility‐weighted imaging |
Title | Detection of Cerebral Microbleeds in MR Images Using a Single‐Stage Triplanar Ensemble Detection Network (TPE‐Det) |
URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fjmri.28487 https://www.ncbi.nlm.nih.gov/pubmed/36285604 https://www.proquest.com/docview/2824336239/abstract/ |
Volume | 58 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LaxRBEC5CDuJF43s1SoMeVJjN9GMeDV4kbkgCE2TdQC4y9KNGoruTsLPx4Mmf4G_0l1jdsw-iIOhpGnq6mOnqrvq6u_orgBe2QSxQyMQok9MCJXWJFs6TMUSeubIoeBM29KuT_PBUHZ9lZ1vwZnUXpueHWG-4hZkR7XWY4MZ2exvS0M-z-fmQjGsZrpIHJr2AiMYb7iitY4Ziwg8y4WVarLlJxd6m6XVv9AfEvI5Yo8s5uA0fVx_bR5p8GV4t7NB9-43H8X__ZgduLbEoe9sPnjuwhe1duFEtT9vvwdd3uIiRWi27aNg-zsMh85RVIYbPTsntdey8ZdWYHc3IKnUshh8wwz7QY4o_v_8gJPsJ2YTs0tS0Zs5GbYczask2gk_6MHT2cvJ-RC2o4tV9OD0YTfYPk2WehsQRHCsSIbVvZFoqTWghowJKbrRXnFudC4-ZcKp0QjptbZFzNFmT2VLTEDG0NE-dfADb7UWLj4D50nGD2mntvRKea4W6yUpPVliINBcDeL7SV33Z03HUPfGyqEMX1rELB7C7UmW9nJId1QglyV1LPYCHvXrXImS4SJqnagCvo5L-Irs-rsZHsfT4X15-AjdDovo-0HcXthfzK3xKcGZhn8Vh-ws9yvEx |
link.rule.ids | 315,786,790,1382,27957,27958,46329,46753 |
linkProvider | Wiley-Blackwell |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LbxMxELZKK0EvpeVRAn1YggMgbbp-7MNHVFIlpRuhkEq9rbz2LGqbbFE27YETP4HfyC9h7N0mKpWQ4LSW_JDW45n5bI-_IeRNUQIkwEWgpY5xgxKaQHFj0RgCi0yaJKx0B_rZMO6fyuOz6KyNzXFvYRp-iMWBm9MMb6-dgrsD6YMla-jFdHbeReuaJg_IGup75HdUoyV7lFI-RzEiCBGwNEwW7KT8YNn3rj-6BzLvYlbvdI4eN5lVa89V6GJNLrvX86Jrvv_B5Pjf_7NJNlo4Sj8062eLrED1hDzM2gv3p-TmI8x9sFZFr0p6CDN3zzyhmQvjKybo-Wp6XtFsRAdTNEw19REIVNMv-JnArx8_Ecx-BTpG0zTRlZ7RXlXDFHvS5cDDJhKdvh1_7mEPrHj3jJwe9caH_aBN1RAYRGRJwIWypQhTqRAwRFgAwbSykrFCxdxCxI1MDRdGFUUSM9BRGRWpwlWicXceGvGcrFZXFbwg1KaGaVBGKWslt0xJUGWUWjTEnIcx75DXtwLLvzWMHHnDvcxzN4W5n8IO2bmVZd5qZY01XAr02EJ1yHYj38UQwr0ljUPZIe-9lP4ydn6cjQa-9PJfGu-TR_1xdpKfDIafXpF1l7e-ifvdIavz2TXsIrqZF3t-Df8GXlj1Uw |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LbxMxEB6VVqq4QCnQBgpYggMgbbp-7MNSL6hJ1LRsVIVU6gWtvLa3KiTbKkk5cOpP6G_sL-nYm4daJCQ4rSXvWLue8cxne_wZ4ENRWptYxgMlVIwTlFAHkmmDztDSSKdJQku3oJ_14oMTcXgana7A3vwsTM0PsVhwcyPD-2s3wC9NubskDf0xGp830bmmySNYEzFnzqZb_SV5lJT-imIEEDygaZgsyEnZ7lL2fjj6A2Peh6w-5nSewvf519apJj-bV9OiqX8_IHL839_ZgCczMEq-1NbzDFZstQnr2Wy7_Tn8atmpT9WqyEVJ9u3Y7TIPSeaS-Iohxr0JOa9I1ifdEbqlCfH5B0SRb_gY2tvrG4SyZ5YM0DENVaXGpF1N7AglybLhXp2HTj4OjtsogRWfXsBJpz3YPwhmFzUEGvFYEjAuTcnDVEiECxEWLKdKGkFpIWNmbMS0SDXjWhZFElOrojIqUok2onBuHmr-Elari8puAzGppspKLaUxghkqhZVllBp0w4yFMWvA-7m-8suajyOvmZdZ7row913YgJ25KvPZmJxgDRMc4zWXDdiq1btogruTpHEoGvDZK-kvbeeHWb_rS6_-5eV3sH7c6uRfu72j1_DYXVpfJ_3uwOp0fGXfILSZFm-9Bd8Bjw_0Ag |
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=Detection+of+Cerebral+Microbleeds+in+MR+Images+Using+a+Single%E2%80%90Stage+Triplanar+Ensemble+Detection+Network+%28TPE%E2%80%90Det%29&rft.jtitle=Journal+of+magnetic+resonance+imaging&rft.au=Lee%2C+Haejoon&rft.au=Jun%E2%80%90Ho+Kim&rft.au=Seul%2C+Lee&rft.au=Kyu%E2%80%90Jin+Jung&rft.date=2023-07-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.issn=1053-1807&rft.eissn=1522-2586&rft.volume=58&rft.issue=1&rft.spage=272&rft.epage=283&rft_id=info:doi/10.1002%2Fjmri.28487&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 |