Localization of cementoenamel junction in intraoral ultrasonographs with machine learning
Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs). Three CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with...
Saved in:
Published in | Journal of dentistry Vol. 112; p. 103752 |
---|---|
Main Authors | , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Oxford
Elsevier Ltd
01.09.2021
Elsevier Limited |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs).
Three CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with 1000 and 200 images, respectively. Four clinical raters with different levels of experience with ultrasound tested the networks using the other 200 images. In addition to the comparison of the best approach with each rater, we also employed the simultaneous truth and performance level estimation (STAPLE) algorithm to estimate a ground truth based on all labelings by four clinical raters. The final CEJ location estimate was obtained by taking the first moment of the posterior probability computed using the STAPLE algorithm. The study also computed the machine learning-measured CEJ–alveolar bone crest distance.
Quantitative evaluations of the 200 images showed that the comparison of the best approach with the STAPLE-estimate yielded a mean difference (MD) of 0.26 mm, which is close to the comparison with the most experienced nonclinical rater (MD=0.25 mm) but far better than the comparison with clinical raters (MD=0.27–0.33 mm). The machine learning-measured CEJ–alveolar bone crest distances correlated strongly (R = 0.933, p < 0.001) with the manual clinical labeling and the measurements were in good agreement with the 95% Bland–Altman's lines of agreement between −0.68 and 0.57 mm.
The study demonstrated the feasible use of machine learning methodology to localize CEJ in ultrasound images with clinically acceptable accuracy and reliability. Likelihood-weighted ground truth by combining multiple labels by the clinical experts compared favorably with the predictions by the best deep CNN approach.
Identification of CEJ and its distance from the alveolar bone crest play an important role in the evaluation of periodontal status. Machine learning algorithms can learn from complex features in ultrasound images and have potential to provide a reliable and accurate identification in subsecond. This will greatly assist dental practitioners to provide better point-of-care to patients and enhance the throughput of dental care. |
---|---|
AbstractList | ObjectiveOur goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs).MethodsThree CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with 1000 and 200 images, respectively. Four clinical raters with different levels of experience with ultrasound tested the networks using the other 200 images. In addition to the comparison of the best approach with each rater, we also employed the simultaneous truth and performance level estimation (STAPLE) algorithm to estimate a ground truth based on all labelings by four clinical raters. The final CEJ location estimate was obtained by taking the first moment of the posterior probability computed using the STAPLE algorithm. The study also computed the machine learning-measured CEJ–alveolar bone crest distance.ResultsQuantitative evaluations of the 200 images showed that the comparison of the best approach with the STAPLE-estimate yielded a mean difference (MD) of 0.26 mm, which is close to the comparison with the most experienced nonclinical rater (MD=0.25 mm) but far better than the comparison with clinical raters (MD=0.27–0.33 mm). The machine learning-measured CEJ–alveolar bone crest distances correlated strongly (R = 0.933, p < 0.001) with the manual clinical labeling and the measurements were in good agreement with the 95% Bland–Altman's lines of agreement between −0.68 and 0.57 mm.ConclusionsThe study demonstrated the feasible use of machine learning methodology to localize CEJ in ultrasound images with clinically acceptable accuracy and reliability. Likelihood-weighted ground truth by combining multiple labels by the clinical experts compared favorably with the predictions by the best deep CNN approach.Clinical significanceIdentification of CEJ and its distance from the alveolar bone crest play an important role in the evaluation of periodontal status. Machine learning algorithms can learn from complex features in ultrasound images and have potential to provide a reliable and accurate identification in subsecond. This will greatly assist dental practitioners to provide better point-of-care to patients and enhance the throughput of dental care. Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs). Three CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with 1000 and 200 images, respectively. Four clinical raters with different levels of experience with ultrasound tested the networks using the other 200 images. In addition to the comparison of the best approach with each rater, we also employed the simultaneous truth and performance level estimation (STAPLE) algorithm to estimate a ground truth based on all labelings by four clinical raters. The final CEJ location estimate was obtained by taking the first moment of the posterior probability computed using the STAPLE algorithm. The study also computed the machine learning-measured CEJ–alveolar bone crest distance. Quantitative evaluations of the 200 images showed that the comparison of the best approach with the STAPLE-estimate yielded a mean difference (MD) of 0.26 mm, which is close to the comparison with the most experienced nonclinical rater (MD=0.25 mm) but far better than the comparison with clinical raters (MD=0.27–0.33 mm). The machine learning-measured CEJ–alveolar bone crest distances correlated strongly (R = 0.933, p < 0.001) with the manual clinical labeling and the measurements were in good agreement with the 95% Bland–Altman's lines of agreement between −0.68 and 0.57 mm. The study demonstrated the feasible use of machine learning methodology to localize CEJ in ultrasound images with clinically acceptable accuracy and reliability. Likelihood-weighted ground truth by combining multiple labels by the clinical experts compared favorably with the predictions by the best deep CNN approach. Identification of CEJ and its distance from the alveolar bone crest play an important role in the evaluation of periodontal status. Machine learning algorithms can learn from complex features in ultrasound images and have potential to provide a reliable and accurate identification in subsecond. This will greatly assist dental practitioners to provide better point-of-care to patients and enhance the throughput of dental care. |
ArticleNumber | 103752 |
Author | Lou, Edmond H.M. Almeida, Fabiana T. Le, Lawrence H. Nguyen, Kim-Cuong T. Major, Paul W. Li, Mengxun Kaipatur, Neelambar R. Punithakumar, Kumaradevan Le, Binh M. |
Author_xml | – sequence: 1 givenname: Kim-Cuong T. surname: Nguyen fullname: Nguyen, Kim-Cuong T. organization: Department of Radiology & Diagnostic Imaging, University of Alberta, Edmonton, Canada – sequence: 2 givenname: Binh M. surname: Le fullname: Le, Binh M. organization: Department of Radiology & Diagnostic Imaging, University of Alberta, Edmonton, Canada – sequence: 3 givenname: Mengxun orcidid: 0000-0001-5553-2221 surname: Li fullname: Li, Mengxun organization: Department of Implantology, School and Hospital of Stomatology, Wuhan University, Wuhan, China – sequence: 4 givenname: Fabiana T. orcidid: 0000-0002-2088-4224 surname: Almeida fullname: Almeida, Fabiana T. organization: School of Dentistry, University of Alberta, Edmonton, Canada – sequence: 5 givenname: Paul W. surname: Major fullname: Major, Paul W. organization: School of Dentistry, University of Alberta, Edmonton, Canada – sequence: 6 givenname: Neelambar R. surname: Kaipatur fullname: Kaipatur, Neelambar R. organization: School of Dentistry, University of Alberta, Edmonton, Canada – sequence: 7 givenname: Edmond H.M. surname: Lou fullname: Lou, Edmond H.M. organization: Department of Biomedical Engineering, University of Alberta, Edmonton, Canada – sequence: 8 givenname: Kumaradevan orcidid: 0000-0003-3835-1079 surname: Punithakumar fullname: Punithakumar, Kumaradevan email: punithak@ualberta.ca organization: Department of Radiology & Diagnostic Imaging, University of Alberta, Edmonton, Canada – sequence: 9 givenname: Lawrence H. orcidid: 0000-0003-1907-1258 surname: Le fullname: Le, Lawrence H. email: lawrence.le@ualberta.ca organization: Department of Radiology & Diagnostic Imaging, University of Alberta, Edmonton, Canada |
BookMark | eNp9kE1Lw0AQhhepYFv9BV4CnlP3I8kmBw9S_IKCFwU9LZvJpN2Q7NbdRNFfb9p4FgZmmJn3HeZZkJl1Fgm5ZHTFKMuum1VToe1XnHI2doRM-QmZs1wWMZPZ24zMqaA0TiXjZ2QRQkMpTSgv5uR940C35kf3xtnI1RFgNzo5tLrDNmoGC8eJOUTvtfO6jYZ2rIKzbuv1fheiL9Pvok7DzliMWtTeGrs9J6e1bgNe_OUleb2_e1k_xpvnh6f17SYGIVgfC81qnSYAOodCQCFLXrIk5VrmDLDIEYSsBdZlIlGIUiclh5InWZZmEispxJJcTb577z4GDL1q3ODteFLxVNJESJkm45aYtsC7EDzWau9Np_23YlQdGKpGHRmqA0M1MRxVN5MKxwc-DXoVwKAFrIxH6FXlzL_6X23Nfx8 |
CitedBy_id | crossref_primary_10_1002_admt_202301732 crossref_primary_10_1117_1_JBO_27_5_056005 crossref_primary_10_3390_s22197101 crossref_primary_10_1002_admt_202100798 crossref_primary_10_1111_joor_13691 crossref_primary_10_1016_j_pacs_2022_100408 crossref_primary_10_1155_2023_5494429 crossref_primary_10_1259_dmfr_20220044 crossref_primary_10_1259_dmfr_20220220 crossref_primary_10_7717_peerj_cs_888 crossref_primary_10_1111_cid_13231 crossref_primary_10_1016_j_ultrasmedbio_2023_01_011 crossref_primary_10_1016_j_zemedi_2023_01_005 crossref_primary_10_1111_prd_12591 |
Cites_doi | 10.1016/j.ultrasmedbio.2015.09.012 10.1109/TVCG.2018.2839685 10.11152/mu.2013.2066.173.rch 10.1177/0022034520969115 10.1016/j.jdent.2021.103615 10.1259/dmfr.20180076 10.1177/0022034520915714 10.5624/isd.2019.49.1.1 10.15386/mpr-1521 10.1155/2012/563421 10.1016/j.jdent.2018.07.015 10.1259/dmfr.20170344 10.1016/j.jdent.2021.103610 10.1177/0022034520920593 10.1038/s41598-019-44839-3 10.4103/0972-124X.142437 10.1046/j.0906-6713.2002.003422.x 10.1177/0022034512457373 10.1007/s10439-016-1634-2 10.1111/j.1600-051X.1984.tb00911.x 10.1902/jop.1992.63.12s.1072 10.1109/TMI.2004.828354 10.1002/(SICI)1097-0258(19980115)17:1<101::AID-SIM727>3.0.CO;2-E 10.1002/JPER.17-0721 10.3390/info11020125 10.1177/0022034520901715 10.1111/j.1600-051X.1984.tb01347.x |
ContentType | Journal Article |
Copyright | 2021 Copyright Elsevier Limited Sep 2021 |
Copyright_xml | – notice: 2021 – notice: Copyright Elsevier Limited Sep 2021 |
DBID | AAYXX CITATION 7QF 7QP 7QQ 7SE 7SR 7TA 7TB 8BQ 8FD F28 FR3 H8G JG9 K9. |
DOI | 10.1016/j.jdent.2021.103752 |
DatabaseName | CrossRef Aluminium Industry Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Corrosion Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Copper Technical Reference Library Materials Research Database ProQuest Health & Medical Complete (Alumni) |
DatabaseTitle | CrossRef Materials Research Database Aluminium Industry Abstracts Technology Research Database Mechanical & Transportation Engineering Abstracts ProQuest Health & Medical Complete (Alumni) Ceramic Abstracts Materials Business File METADEX Copper Technical Reference Library Engineered Materials Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts ANTE: Abstracts in New Technology & Engineering |
DatabaseTitleList | Materials Research Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Dentistry |
EISSN | 1879-176X |
ExternalDocumentID | 10_1016_j_jdent_2021_103752 S0300571221001731 |
GroupedDBID | --- --K --M .1- .FO .~1 0R~ 0SF 1B1 1P~ 1RT 1~. 1~5 29K 34H 3V. 4.4 457 4G. 53G 5GY 5VS 7-5 71M 7RV 7X7 8FE 8FG 8FH 8FI 8P~ 9JM AABNK AACTN AAEDT AAEDW AAGKA AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABBQC ABFNM ABJCF ABJNI ABLVK ABMAC ABMZM ABOCM ABXDB ABYKQ ACDAQ ACGFS ACIUM ACIWK ACPRK ACRLP ADBBV ADEZE ADMUD AEBSH AEKER AENEX AEVXI AFCTW AFFNX AFKRA AFKWA AFRHN AFTJW AFXIZ AGHFR AGUBO AGYEJ AHHHB AHMBA AIEXJ AIKHN AITUG AJBFU AJOXV AJRQY AJUYK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX ASPBG AVWKF AXJTR AZFZN AZQEC BBNVY BENPR BHPHI BKEYQ BKOJK BLXMC BNPGV BPHCQ BVXVI CS3 D-I DU5 EBD EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN FYUFA G-2 G-Q GBLVA GUQSH HCIFZ HDX HMK HMO HVGLF HZ~ IAO IEA IHE IHR INR J1W KOM L6V LCYCR LH1 LK8 M1P M29 M2O M41 M7P M7S MO0 N9A NCXOZ O-L O9- OAUVE OB- OM. OZT P-8 P-9 P2P PC. PQQKQ PROAC Q38 R2- RIG ROL RPZ SAE SCC SDF SDG SEL SES SEW SPCBC SSH SSZ T5K WH7 WOW WUQ Z5R ZGI ~G- AAXKI AAYXX ADVLN AFJKZ AKRWK CITATION 7QF 7QP 7QQ 7SE 7SR 7TA 7TB 8BQ 8FD F28 FR3 H8G JG9 K9. |
ID | FETCH-LOGICAL-c331t-3a1fa54cca8c93c97b2b1452a781ce98ec37f3efb47e33ba4b2cb2466567ed733 |
IEDL.DBID | AIKHN |
ISSN | 0300-5712 |
IngestDate | Thu Oct 10 19:46:09 EDT 2024 Thu Sep 26 19:33:57 EDT 2024 Fri Feb 23 02:43:14 EST 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Deep learning Medical imaging Ultrasound imaging Cementoenamel junction (CEJ) Machine learning Alveolar bone Convolutional neural networks (CNNs) |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c331t-3a1fa54cca8c93c97b2b1452a781ce98ec37f3efb47e33ba4b2cb2466567ed733 |
ORCID | 0000-0003-3835-1079 0000-0002-2088-4224 0000-0003-1907-1258 0000-0001-5553-2221 |
PQID | 2570437754 |
PQPubID | 1226341 |
ParticipantIDs | proquest_journals_2570437754 crossref_primary_10_1016_j_jdent_2021_103752 elsevier_sciencedirect_doi_10_1016_j_jdent_2021_103752 |
PublicationCentury | 2000 |
PublicationDate | September 2021 2021-09-00 20210901 |
PublicationDateYYYYMMDD | 2021-09-01 |
PublicationDate_xml | – month: 09 year: 2021 text: September 2021 |
PublicationDecade | 2020 |
PublicationPlace | Oxford |
PublicationPlace_xml | – name: Oxford |
PublicationTitle | Journal of dentistry |
PublicationYear | 2021 |
Publisher | Elsevier Ltd Elsevier Limited |
Publisher_xml | – name: Elsevier Ltd – name: Elsevier Limited |
References | Löst (bib0001) 1984; 11 Xu, Liu, Zheng (bib0038) 2018; 25 Burt, Torosdagli, Khosravan, RaviPrakash, Mortazi, Tissavirasingham (bib0016) 2018; 91 Portney, Watkins (bib0037) 2009 Eke, Dye, Wei, Thornton-Evans, Genco (bib0003) 2012; 91 Smith (bib0034) 2017 Nguyen, Le, Kaipatur, Zheng, Lou, Major (bib0011) 2016; 44 Badersten, Nilvéaus, Egelberg (bib0036) 1984; 11 Chifor, Badea, Chifor, Mitrea, Crisan, Badea (bib0013) 2019; 92 Chollet (bib0028) 2017 Chifor, Badea, Mitrea, Badea, Crisan, Chifor (bib0012) 2015; 17 Nguyen, Duong, Almeida, Major, Kaipatur, Pham (bib0010) 2020; 99 Askar, Krois, Rohrer, Mertens, Elhennawy, Ottolenghi (bib0024) 2021 Kingma D.P., B.J. Adam: A method for stochastic optimization. Buslaev, Iglovikov, Khvedchenya, Parinov, Druzhinin, Kalinin (bib0029) 2020; 11 Froum, Wang (bib0008) 2018; 39 Chan H.-L.A., Kripfgans O.D. Dental ultrasound in periodontology and implantology. Lee, Kim, Jeong, Choi (bib0022) 2018; 77 Walter, Eliasziw, Donner (bib0035) 1998; 17 Pihlstrom (bib0004) 1992; 63 Hwang, Jung, Cho, Heo (bib0017) 2019; 49 Schwendicke, Singh, Lee, Gaudin, Chaurasia, Wiegand (bib0019) 2021; 107 Warfield, Zou, Wells (bib0025) 2004; 23 He, Zhang, Ren, Sun (bib0027) 2016 Pradeep, Rajababu, Satyanarayana, Sagar (bib0002) 2012 Krois, Ekert, Meinhold, Golla, Kharbot, Wittemeier (bib0023) 2019; 9 Huang, Liu, Van Der Maaten, Weinberger (bib0026) 2017 Bhaskar, Chan, MacEachern, Kripfgans (bib0009) 2018; 47 Shan, Tay, Gu (bib0020) 2021; 100 Vandana, Haneet (bib0006) 2014; 18 Fa, Samek, Krois (bib0018) 2020; 99 Lee, Adhikari, Liu, Jeong, Kim, Yoon (bib0039) 2019; 48 Prajapati, Nagaraj, Mitra (bib0032) 2017 Armitage (bib0007) 2004; 34 2014. Yu, Cho, Kim, Kim, Kim, Choi (bib0033) 2020; 99 Miki, Muramatsu, Hayashi, Zhou, Hara, Katsumata (bib0021) 2017 Zhong, Zheng, Kang, Li, Yang (bib0030) 2020 Papapanou, Sanz, Buduneli, Dietrich, Feres, Fine (bib0005) 2018; 89 Nguyen, Le, Kaipatur, Major (bib0014) 2016; 42 Chifor (10.1016/j.jdent.2021.103752_bib0013) 2019; 92 Smith (10.1016/j.jdent.2021.103752_bib0034) 2017 Xu (10.1016/j.jdent.2021.103752_bib0038) 2018; 25 Miki (10.1016/j.jdent.2021.103752_bib0021) 2017 Eke (10.1016/j.jdent.2021.103752_bib0003) 2012; 91 Shan (10.1016/j.jdent.2021.103752_bib0020) 2021; 100 Askar (10.1016/j.jdent.2021.103752_bib0024) 2021 Warfield (10.1016/j.jdent.2021.103752_bib0025) 2004; 23 10.1016/j.jdent.2021.103752_bib0031 Portney (10.1016/j.jdent.2021.103752_bib0037) 2009 Zhong (10.1016/j.jdent.2021.103752_bib0030) 2020 Nguyen (10.1016/j.jdent.2021.103752_bib0010) 2020; 99 Pradeep (10.1016/j.jdent.2021.103752_bib0002) 2012 10.1016/j.jdent.2021.103752_bib0015 Badersten (10.1016/j.jdent.2021.103752_bib0036) 1984; 11 He (10.1016/j.jdent.2021.103752_bib0027) 2016 Vandana (10.1016/j.jdent.2021.103752_bib0006) 2014; 18 Chollet (10.1016/j.jdent.2021.103752_bib0028) 2017 Nguyen (10.1016/j.jdent.2021.103752_bib0014) 2016; 42 Lee (10.1016/j.jdent.2021.103752_bib0039) 2019; 48 Hwang (10.1016/j.jdent.2021.103752_bib0017) 2019; 49 Buslaev (10.1016/j.jdent.2021.103752_bib0029) 2020; 11 Huang (10.1016/j.jdent.2021.103752_bib0026) 2017 Froum (10.1016/j.jdent.2021.103752_bib0008) 2018; 39 Walter (10.1016/j.jdent.2021.103752_bib0035) 1998; 17 Pihlstrom (10.1016/j.jdent.2021.103752_bib0004) 1992; 63 Löst (10.1016/j.jdent.2021.103752_bib0001) 1984; 11 Armitage (10.1016/j.jdent.2021.103752_bib0007) 2004; 34 Burt (10.1016/j.jdent.2021.103752_bib0016) 2018; 91 Krois (10.1016/j.jdent.2021.103752_bib0023) 2019; 9 Yu (10.1016/j.jdent.2021.103752_bib0033) 2020; 99 Schwendicke (10.1016/j.jdent.2021.103752_bib0019) 2021; 107 Lee (10.1016/j.jdent.2021.103752_bib0022) 2018; 77 Chifor (10.1016/j.jdent.2021.103752_bib0012) 2015; 17 Bhaskar (10.1016/j.jdent.2021.103752_bib0009) 2018; 47 Nguyen (10.1016/j.jdent.2021.103752_bib0011) 2016; 44 Papapanou (10.1016/j.jdent.2021.103752_bib0005) 2018; 89 Prajapati (10.1016/j.jdent.2021.103752_bib0032) 2017 Fa (10.1016/j.jdent.2021.103752_bib0018) 2020; 99 |
References_xml | – start-page: 464 year: 2017 end-page: 472 ident: bib0034 article-title: Cyclical learning rates for training neural networks publication-title: 2017 IEEE winter conference on applications of computer vision (WACV) contributor: fullname: Smith – start-page: 770 year: 2016 end-page: 778 ident: bib0027 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition contributor: fullname: Sun – volume: 9 start-page: 1 year: 2019 end-page: 6 ident: bib0023 article-title: Deep learning for the radiographic detection of periodontal bone loss publication-title: Sci. Rep. contributor: fullname: Wittemeier – volume: 91 start-page: 914 year: 2012 end-page: 920 ident: bib0003 article-title: Prevalence of periodontitis in adults in the United States: 2009 and 2010 publication-title: J. Dent. Res. contributor: fullname: Genco – start-page: 1251 year: 2017 end-page: 1258 ident: bib0028 article-title: Xception: deep learning with depthwise separable convolutions publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition contributor: fullname: Chollet – volume: 107 year: 2021 ident: bib0019 article-title: Artificial intelligence in dental research: checklist for authors, reviewers, readers publication-title: J. Dent. contributor: fullname: Wiegand – volume: 39 start-page: 20 year: 2018 end-page: 25 ident: bib0008 article-title: Risks and benefits of probing around natural teeth and dental implants publication-title: Compendium of Continuing Education in Dentistry (Jamesburg, NJ: 1995) contributor: fullname: Wang – volume: 92 start-page: S20 year: 2019 ident: bib0013 article-title: Periodontal evaluation using a non-invasive imaging method (ultrasonography) publication-title: Med. Pharmacy Rep. contributor: fullname: Badea – year: 2009 ident: bib0037 article-title: Foundations of Clinical Research: Applications to Practice contributor: fullname: Watkins – volume: 11 start-page: 583 year: 1984 end-page: 589 ident: bib0001 article-title: Depth of alveolar bone dehiscences in relation to gingival recessions publication-title: J. Clin. Periodontol. contributor: fullname: Löst – volume: 42 start-page: 333 year: 2016 end-page: 338 ident: bib0014 article-title: Imaging the cemento-enamel junction using a 20-MHz ultrasonic transducer publication-title: Ultrasound Med. Biol. contributor: fullname: Major – volume: 11 start-page: 475 year: 1984 end-page: 485 ident: bib0036 article-title: Reproducibility of probing attachment level measurements publication-title: J. Clin. Periodontol. contributor: fullname: Egelberg – volume: 17 start-page: 101 year: 1998 end-page: 110 ident: bib0035 article-title: Sample size and optimal designs for reliability studies publication-title: Stat. Med. contributor: fullname: Donner – year: 2021 ident: bib0024 article-title: Detecting white spot lesions on dental photography using deep learning: a pilot study publication-title: J. Dent. contributor: fullname: Ottolenghi – volume: 23 start-page: 903 year: 2004 end-page: 921 ident: bib0025 article-title: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation publication-title: IEEE Trans. Med. Imaging contributor: fullname: Wells – volume: 48 year: 2019 ident: bib0039 article-title: Osteoporosis detection in panoramic radiographs using a deep convolutional neural network-based computer-assisted diagnosis system: a preliminary study publication-title: Dentomaxillofacial Radiol. contributor: fullname: Yoon – volume: 99 start-page: 1054 year: 2020 end-page: 1061 ident: bib0010 article-title: Alveolar bone segmentation in intraoral ultrasonographs with machine learning publication-title: J. Dent. Res. contributor: fullname: Pham – volume: 44 start-page: 2874 year: 2016 end-page: 2886 ident: bib0011 article-title: High-resolution ultrasonic imaging of dento-periodontal tissues using a multi-element phased array system publication-title: Ann. Biomed. Eng. contributor: fullname: Major – volume: 17 start-page: 273 year: 2015 end-page: 279 ident: bib0012 article-title: Computer-assisted identification of the gingival sulcus and periodontal epithelial junction on high-frequency ultrasound images publication-title: Med. Ultrasonogr. contributor: fullname: Chifor – volume: 89 start-page: S173 year: 2018 end-page: SS82 ident: bib0005 article-title: Periodontitis: consensus report of workgroup 2 of the 2017 world workshop on the classification of periodontal and peri-implant diseases and conditions publication-title: J. Periodontol. contributor: fullname: Fine – volume: 91 year: 2018 ident: bib0016 article-title: Deep learning beyond cats and dogs: recent advances in diagnosing breast cancer with deep neural networks publication-title: Br. J. Radiol. contributor: fullname: Tissavirasingham – volume: 47 year: 2018 ident: bib0009 article-title: Updates on ultrasound research in implant dentistry: a systematic review of potential clinical indications publication-title: Dentomaxillofacial Radiol. contributor: fullname: Kripfgans – volume: 49 start-page: 1 year: 2019 ident: bib0017 article-title: An overview of deep learning in the field of dentistry publication-title: Imaging Sci. Dentistry contributor: fullname: Heo – start-page: 13001 year: 2020 end-page: 13008 ident: bib0030 article-title: Random erasing data augmentation publication-title: Proceedings of the AAAI Conference on Artificial Intelligence; 2020; 2020 contributor: fullname: Yang – start-page: 4700 year: 2017 end-page: 4708 ident: bib0026 article-title: Densely connected convolutional networks publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition contributor: fullname: Weinberger – volume: 34 start-page: 22 year: 2004 end-page: 33 ident: bib0007 article-title: The complete periodontal examination publication-title: Periodontol 2000 contributor: fullname: Armitage – volume: 77 start-page: 106 year: 2018 end-page: 111 ident: bib0022 article-title: Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm publication-title: J. Dent. contributor: fullname: Choi – volume: 63 start-page: 1072 year: 1992 end-page: 1077 ident: bib0004 article-title: Measurement of attachment level in clinical trials: probing methods publication-title: J. Periodontol. contributor: fullname: Pihlstrom – start-page: 70 year: 2017 end-page: 74 ident: bib0032 article-title: Classification of dental diseases using CNN and transfer learning publication-title: 2017 5th International Symposium on Computational and Business Intelligence (ISCBI) contributor: fullname: Mitra – year: 2017 ident: bib0021 article-title: Tooth labeling in cone-beam CT using deep convolutional neural network for forensic identification publication-title: Med. Imaging 2017: Comput.-Aided Diagnosis; 2017: Int. Soc. Opt. Photonics contributor: fullname: Katsumata – year: 2012 ident: bib0002 article-title: Gingival recession: review and strategies in treatment of recession publication-title: Case Rep. Dentistry contributor: fullname: Sagar – volume: 18 start-page: 549 year: 2014 ident: bib0006 article-title: Cementoenamel junction: an insight publication-title: J. Indian Soc. Periodontol. contributor: fullname: Haneet – volume: 100 start-page: 232 year: 2021 end-page: 244 ident: bib0020 article-title: Application of artificial intelligence in dentistry publication-title: J. Dent. Res. contributor: fullname: Gu – volume: 99 start-page: 249 year: 2020 end-page: 256 ident: bib0033 article-title: Automated skeletal classification with lateral cephalometry based on artificial intelligence publication-title: J. Dent. Res. contributor: fullname: Choi – volume: 25 start-page: 2336 year: 2018 end-page: 2348 ident: bib0038 article-title: 3D tooth segmentation and labeling using deep convolutional neural networks publication-title: IEEE Trans. Vis. Comput. Graph. contributor: fullname: Zheng – volume: 99 start-page: 769 year: 2020 end-page: 774 ident: bib0018 article-title: Artificial intelligence in dentistry: chances and challenges publication-title: J. Dent. Res. contributor: fullname: Krois – volume: 11 start-page: 125 year: 2020 ident: bib0029 article-title: Albumentations: fast and flexible image augmentations publication-title: Information contributor: fullname: Kalinin – volume: 42 start-page: 333 issue: 1 year: 2016 ident: 10.1016/j.jdent.2021.103752_bib0014 article-title: Imaging the cemento-enamel junction using a 20-MHz ultrasonic transducer publication-title: Ultrasound Med. Biol. doi: 10.1016/j.ultrasmedbio.2015.09.012 contributor: fullname: Nguyen – volume: 91 issue: 1089 year: 2018 ident: 10.1016/j.jdent.2021.103752_bib0016 article-title: Deep learning beyond cats and dogs: recent advances in diagnosing breast cancer with deep neural networks publication-title: Br. J. Radiol. contributor: fullname: Burt – volume: 25 start-page: 2336 issue: 7 year: 2018 ident: 10.1016/j.jdent.2021.103752_bib0038 article-title: 3D tooth segmentation and labeling using deep convolutional neural networks publication-title: IEEE Trans. Vis. Comput. Graph. doi: 10.1109/TVCG.2018.2839685 contributor: fullname: Xu – start-page: 13001 year: 2020 ident: 10.1016/j.jdent.2021.103752_bib0030 article-title: Random erasing data augmentation contributor: fullname: Zhong – volume: 17 start-page: 273 issue: 3 year: 2015 ident: 10.1016/j.jdent.2021.103752_bib0012 article-title: Computer-assisted identification of the gingival sulcus and periodontal epithelial junction on high-frequency ultrasound images publication-title: Med. Ultrasonogr. doi: 10.11152/mu.2013.2066.173.rch contributor: fullname: Chifor – ident: 10.1016/j.jdent.2021.103752_bib0015 – volume: 100 start-page: 232 issue: 3 year: 2021 ident: 10.1016/j.jdent.2021.103752_bib0020 article-title: Application of artificial intelligence in dentistry publication-title: J. Dent. Res. doi: 10.1177/0022034520969115 contributor: fullname: Shan – year: 2021 ident: 10.1016/j.jdent.2021.103752_bib0024 article-title: Detecting white spot lesions on dental photography using deep learning: a pilot study publication-title: J. Dent. doi: 10.1016/j.jdent.2021.103615 contributor: fullname: Askar – year: 2009 ident: 10.1016/j.jdent.2021.103752_bib0037 contributor: fullname: Portney – volume: 47 issue: 6 year: 2018 ident: 10.1016/j.jdent.2021.103752_bib0009 article-title: Updates on ultrasound research in implant dentistry: a systematic review of potential clinical indications publication-title: Dentomaxillofacial Radiol. doi: 10.1259/dmfr.20180076 contributor: fullname: Bhaskar – start-page: 464 year: 2017 ident: 10.1016/j.jdent.2021.103752_bib0034 article-title: Cyclical learning rates for training neural networks contributor: fullname: Smith – volume: 99 start-page: 769 issue: 7 year: 2020 ident: 10.1016/j.jdent.2021.103752_bib0018 article-title: Artificial intelligence in dentistry: chances and challenges publication-title: J. Dent. Res. doi: 10.1177/0022034520915714 contributor: fullname: Fa – volume: 49 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.jdent.2021.103752_bib0017 article-title: An overview of deep learning in the field of dentistry publication-title: Imaging Sci. Dentistry doi: 10.5624/isd.2019.49.1.1 contributor: fullname: Hwang – start-page: 4700 year: 2017 ident: 10.1016/j.jdent.2021.103752_bib0026 article-title: Densely connected convolutional networks contributor: fullname: Huang – volume: 92 start-page: S20 issue: Suppl No 3 year: 2019 ident: 10.1016/j.jdent.2021.103752_bib0013 article-title: Periodontal evaluation using a non-invasive imaging method (ultrasonography) publication-title: Med. Pharmacy Rep. doi: 10.15386/mpr-1521 contributor: fullname: Chifor – year: 2012 ident: 10.1016/j.jdent.2021.103752_bib0002 article-title: Gingival recession: review and strategies in treatment of recession publication-title: Case Rep. Dentistry doi: 10.1155/2012/563421 contributor: fullname: Pradeep – volume: 39 start-page: 20 issue: 1 year: 2018 ident: 10.1016/j.jdent.2021.103752_bib0008 article-title: Risks and benefits of probing around natural teeth and dental implants publication-title: Compendium of Continuing Education in Dentistry (Jamesburg, NJ: 1995) contributor: fullname: Froum – start-page: 1251 year: 2017 ident: 10.1016/j.jdent.2021.103752_bib0028 article-title: Xception: deep learning with depthwise separable convolutions contributor: fullname: Chollet – volume: 77 start-page: 106 year: 2018 ident: 10.1016/j.jdent.2021.103752_bib0022 article-title: Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm publication-title: J. Dent. doi: 10.1016/j.jdent.2018.07.015 contributor: fullname: Lee – start-page: 70 year: 2017 ident: 10.1016/j.jdent.2021.103752_bib0032 article-title: Classification of dental diseases using CNN and transfer learning contributor: fullname: Prajapati – volume: 48 issue: 1 year: 2019 ident: 10.1016/j.jdent.2021.103752_bib0039 article-title: Osteoporosis detection in panoramic radiographs using a deep convolutional neural network-based computer-assisted diagnosis system: a preliminary study publication-title: Dentomaxillofacial Radiol. doi: 10.1259/dmfr.20170344 contributor: fullname: Lee – volume: 107 year: 2021 ident: 10.1016/j.jdent.2021.103752_bib0019 article-title: Artificial intelligence in dental research: checklist for authors, reviewers, readers publication-title: J. Dent. doi: 10.1016/j.jdent.2021.103610 contributor: fullname: Schwendicke – ident: 10.1016/j.jdent.2021.103752_bib0031 – volume: 99 start-page: 1054 issue: 9 year: 2020 ident: 10.1016/j.jdent.2021.103752_bib0010 article-title: Alveolar bone segmentation in intraoral ultrasonographs with machine learning publication-title: J. Dent. Res. doi: 10.1177/0022034520920593 contributor: fullname: Nguyen – volume: 9 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.jdent.2021.103752_bib0023 article-title: Deep learning for the radiographic detection of periodontal bone loss publication-title: Sci. Rep. doi: 10.1038/s41598-019-44839-3 contributor: fullname: Krois – volume: 18 start-page: 549 issue: 5 year: 2014 ident: 10.1016/j.jdent.2021.103752_bib0006 article-title: Cementoenamel junction: an insight publication-title: J. Indian Soc. Periodontol. doi: 10.4103/0972-124X.142437 contributor: fullname: Vandana – volume: 34 start-page: 22 issue: 1 year: 2004 ident: 10.1016/j.jdent.2021.103752_bib0007 article-title: The complete periodontal examination publication-title: Periodontol 2000 doi: 10.1046/j.0906-6713.2002.003422.x contributor: fullname: Armitage – volume: 91 start-page: 914 issue: 10 year: 2012 ident: 10.1016/j.jdent.2021.103752_bib0003 article-title: Prevalence of periodontitis in adults in the United States: 2009 and 2010 publication-title: J. Dent. Res. doi: 10.1177/0022034512457373 contributor: fullname: Eke – volume: 44 start-page: 2874 issue: 10 year: 2016 ident: 10.1016/j.jdent.2021.103752_bib0011 article-title: High-resolution ultrasonic imaging of dento-periodontal tissues using a multi-element phased array system publication-title: Ann. Biomed. Eng. doi: 10.1007/s10439-016-1634-2 contributor: fullname: Nguyen – volume: 11 start-page: 583 issue: 9 year: 1984 ident: 10.1016/j.jdent.2021.103752_bib0001 article-title: Depth of alveolar bone dehiscences in relation to gingival recessions publication-title: J. Clin. Periodontol. doi: 10.1111/j.1600-051X.1984.tb00911.x contributor: fullname: Löst – year: 2017 ident: 10.1016/j.jdent.2021.103752_bib0021 article-title: Tooth labeling in cone-beam CT using deep convolutional neural network for forensic identification publication-title: Med. Imaging 2017: Comput.-Aided Diagnosis; 2017: Int. Soc. Opt. Photonics contributor: fullname: Miki – volume: 63 start-page: 1072 year: 1992 ident: 10.1016/j.jdent.2021.103752_bib0004 article-title: Measurement of attachment level in clinical trials: probing methods publication-title: J. Periodontol. doi: 10.1902/jop.1992.63.12s.1072 contributor: fullname: Pihlstrom – volume: 23 start-page: 903 issue: 7 year: 2004 ident: 10.1016/j.jdent.2021.103752_bib0025 article-title: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2004.828354 contributor: fullname: Warfield – volume: 17 start-page: 101 issue: 1 year: 1998 ident: 10.1016/j.jdent.2021.103752_bib0035 article-title: Sample size and optimal designs for reliability studies publication-title: Stat. Med. doi: 10.1002/(SICI)1097-0258(19980115)17:1<101::AID-SIM727>3.0.CO;2-E contributor: fullname: Walter – volume: 89 start-page: S173 year: 2018 ident: 10.1016/j.jdent.2021.103752_bib0005 article-title: Periodontitis: consensus report of workgroup 2 of the 2017 world workshop on the classification of periodontal and peri-implant diseases and conditions publication-title: J. Periodontol. doi: 10.1002/JPER.17-0721 contributor: fullname: Papapanou – start-page: 770 year: 2016 ident: 10.1016/j.jdent.2021.103752_bib0027 article-title: Deep residual learning for image recognition contributor: fullname: He – volume: 11 start-page: 125 issue: 2 year: 2020 ident: 10.1016/j.jdent.2021.103752_bib0029 article-title: Albumentations: fast and flexible image augmentations publication-title: Information doi: 10.3390/info11020125 contributor: fullname: Buslaev – volume: 99 start-page: 249 issue: 3 year: 2020 ident: 10.1016/j.jdent.2021.103752_bib0033 article-title: Automated skeletal classification with lateral cephalometry based on artificial intelligence publication-title: J. Dent. Res. doi: 10.1177/0022034520901715 contributor: fullname: Yu – volume: 11 start-page: 475 issue: 7 year: 1984 ident: 10.1016/j.jdent.2021.103752_bib0036 article-title: Reproducibility of probing attachment level measurements publication-title: J. Clin. Periodontol. doi: 10.1111/j.1600-051X.1984.tb01347.x contributor: fullname: Badersten |
SSID | ssj0004029 |
Score | 2.4605696 |
Snippet | Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs).
Three CNNs... ObjectiveOur goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks... |
SourceID | proquest crossref elsevier |
SourceType | Aggregation Database Publisher |
StartPage | 103752 |
SubjectTerms | Algorithms Alveolar bone Artificial intelligence Artificial neural networks Cementoenamel junction (CEJ) Computation Conditional probability Convolutional neural networks (CNNs) Deep learning Dentistry Disease Labels Learning algorithms Localization Machine learning Medical equipment Medical imaging Neural networks Older people Periodontium Radiation Scanners Ultrasonic imaging Ultrasound Ultrasound imaging |
Title | Localization of cementoenamel junction in intraoral ultrasonographs with machine learning |
URI | https://dx.doi.org/10.1016/j.jdent.2021.103752 https://www.proquest.com/docview/2570437754 |
Volume | 112 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3JTsMwELVKe4ALYhWFUvnAkVC8JE6OVaEUinoAKsrJslMHteqmLle-HY_jCIEEB6Qou6PoOZkZW2_eIHRBQATcuomAJYoH3AxFoPSQBlk2BDkqQ7V2bIte1Onzh0E4KKFWkQsDtEpv-3Ob7qy1P9PwaDYWo1Hj-RqU1gWhFGSEBORSV6w74ryMKs37bqf3lR557YqVwf0BNCjEhxzNawz5sHacSInLPw_pbw7qh6l2_qe9h3Z94Iib-bvto5KZHaDtGyD7QL22Q_T2CG7Jp1XieYZTN_M3NzM1NRM8tg7MXRnBsl4qSM3Hm4ndsyF3Lly9wjAti6eOYGmwryjxfoT67duXVifwhROClDGyDpgimQq57Zw4TViaCE014SFVIiapSWKTMpExk2kuDGNacU1TTXlkYzthe4uxY1SezWfmBOEkTqLURIpEitmRXKQz2-vcxIpFSikmquiyQEsucn0MWRDHxtKBKwFcmYNbRVGBqPzWzdJa8L8b1gr8pf_LVhIq8HEGGn6n_33uGdqBo5w1VkPl9XJjzm2YsdZ1tHX1Qew6bt_V_ScF2-7Ta_cTwJfV3g |
link.rule.ids | 315,786,790,4521,24144,27955,27956,33406,45618,45712 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PT8IwFG4IHPBi_BlR1B48usDabt2OBCUgyEVI8NS0ozMQGATG_29f18VoogeTHbZ1W5bvbe-9Nt_7HkIPPoiAmzDh0Vgyj-k596SaEy9N5yBHpYlSlm0xDvtT9jILZhXULWthgFbpfH_h0623dmdaDs3WdrFovbVBaZ37hICMEIda6hqD4yqqdQbD_virPLJtm5XB9R5cUIoPWZrXEuphzTyR-Lb-PCC_BagfrtrGn94JOnaJI-4U73aKKjo7Q_UnIPtAv7Zz9D6CsOTKKvEmxYld-dvoTK71Ci9NALMjC9jynYTSfHxYmT2TchfC1XsMy7J4bQmWGruOEh8XaNp7nnT7nmuc4CWU-rlHpZ_KgBnjRElMk5gronwWEMkjP9FxpBPKU6pTxbimVEmmSKIIC01ux421KL1E1WyT6SuE4ygOEx1KP5TUzORClRqrMx1JGkopKW-gxxItsS30MURJHFsKC64AcEUBbgOFJaLim5mF8eB_39gs8RfuL9sL6MDHKGj4Xf_3ufeo3p-8jsRoMB7eoCMYKRhkTVTNdwd9a1KOXN25T-oTO0PVRQ |
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=Localization+of+cementoenamel+junction+in+intraoral+ultrasonographs+with+machine+learning&rft.jtitle=Journal+of+dentistry&rft.au=Nguyen%2C+Kim-Cuong+T.&rft.au=Le%2C+Binh+M.&rft.au=Li%2C+Mengxun&rft.au=Almeida%2C+Fabiana+T.&rft.date=2021-09-01&rft.issn=0300-5712&rft.volume=112&rft.spage=103752&rft_id=info:doi/10.1016%2Fj.jdent.2021.103752&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jdent_2021_103752 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0300-5712&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0300-5712&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0300-5712&client=summon |