Merging and Annotating Teeth and Roots from Automated Segmentation of Multimodal Images
This paper aims to combine two different imaging techniques to create an accurate 3D model representation of root canals and dental crowns. We combine Cone-Beam Computed Tomography (CBCT) (root canals) and Intra Oral Scans (IOS) (dental crowns). The Root Canal Segmentation algorithm relies on a U-Ne...
Saved in:
Published in | Multimodal Learning for Clinical Decision Support Vol. 13050; pp. 81 - 92 |
---|---|
Main Authors | , , , , , , , , , , , , , , , , , , , , , , , , |
Format | Book Chapter |
Language | English |
Published |
Switzerland
Springer International Publishing AG
2021
Springer International Publishing |
Series | Lecture Notes in Computer Science |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | This paper aims to combine two different imaging techniques to create an accurate 3D model representation of root canals and dental crowns. We combine Cone-Beam Computed Tomography (CBCT) (root canals) and Intra Oral Scans (IOS) (dental crowns). The Root Canal Segmentation algorithm relies on a U-Net architecture with 2D sliced images from CBCT scans as its input. The segmentation task achieved an F1-score of 0.84. The IOS segmentation (Dental Model Segmentation) algorithm and Universal Labeling and Merging (ULM) algorithm use a multi-view approach for 3D shape analysis. The approach consists of acquiring views of the 3D object from different viewpoints and extract surface features such as the normal vectors. The generated 2D images are then analyzed via a 2D convolutional neural networks (U-Net) for segmentation or classification tasks. The segmentation task on IOS achieved an accuracy of 0.9. The ULM algorithm classifies the jaws between upper and lower and aligns them to a template and labels each crown and root with the ‘Universal Numbering System’ proposed by the ‘American Dental Association’. The ULM task achieve an F1-score of 0.85. Merging and annotation of CBCT and IOS imaging modalities will help guide clinical decision support and quantitative treatment planning for specific teeth, implant placement, root canal treatment, restorative procedures, or biomechanics of tooth movement in orthodontics. |
---|---|
AbstractList | This paper aims to combine two different imaging techniques to create an accurate 3D model representation of root canals and dental crowns. We combine Cone-Beam Computed Tomography (CBCT) (root canals) and Intra Oral Scans (IOS) (dental crowns). The Root Canal Segmentation algorithm relies on a U-Net architecture with 2D sliced images from CBCT scans as its input. The segmentation task achieved an F1-score of 0.84. The IOS segmentation (Dental Model Segmentation) algorithm and Universal Labeling and Merging (ULM) algorithm use a multi-view approach for 3D shape analysis. The approach consists of acquiring views of the 3D object from different viewpoints and extract surface features such as the normal vectors. The generated 2D images are then analyzed via a 2D convolutional neural networks (U-Net) for segmentation or classification tasks. The segmentation task on IOS achieved an accuracy of 0.9. The ULM algorithm classifies the jaws between upper and lower and aligns them to a template and labels each crown and root with the ‘Universal Numbering System’ proposed by the ‘American Dental Association’. The ULM task achieve an F1-score of 0.85. Merging and annotation of CBCT and IOS imaging modalities will help guide clinical decision support and quantitative treatment planning for specific teeth, implant placement, root canal treatment, restorative procedures, or biomechanics of tooth movement in orthodontics. |
Author | Rios, Hector Yatabe, Marilia Benavides, Erika Ruellas, Antonio Soroushmehr, Reza Zhang, Winston Bianchi, Jonas Gurgel, Marcela Soki, Fabiana Del Castillo, Aron Aliaga Prieto, Juan Najarian, Kayvan Massaro, Camila Aristizabal, Juan Fernando Cevidanes, Lucia Rey, Diego Le, Celia Bert, Loris Neiva, Gisele Gryak, Jonathan Styner, Martin Ioshida, Marcos Alvarez, Maria Antonia Turkestani, Najla Al Deleat-Besson, Romain |
Author_xml | – sequence: 1 givenname: Romain surname: Deleat-Besson fullname: Deleat-Besson, Romain – sequence: 2 givenname: Celia surname: Le fullname: Le, Celia – sequence: 3 givenname: Winston surname: Zhang fullname: Zhang, Winston – sequence: 4 givenname: Najla Al surname: Turkestani fullname: Turkestani, Najla Al – sequence: 5 givenname: Lucia surname: Cevidanes fullname: Cevidanes, Lucia email: luciacev@umich.edu – sequence: 6 givenname: Jonas surname: Bianchi fullname: Bianchi, Jonas – sequence: 7 givenname: Antonio surname: Ruellas fullname: Ruellas, Antonio – sequence: 8 givenname: Marcela surname: Gurgel fullname: Gurgel, Marcela – sequence: 9 givenname: Camila surname: Massaro fullname: Massaro, Camila – sequence: 10 givenname: Aron Aliaga surname: Del Castillo fullname: Del Castillo, Aron Aliaga – sequence: 11 givenname: Marcos surname: Ioshida fullname: Ioshida, Marcos – sequence: 12 givenname: Marilia surname: Yatabe fullname: Yatabe, Marilia – sequence: 13 givenname: Erika surname: Benavides fullname: Benavides, Erika – sequence: 14 givenname: Hector surname: Rios fullname: Rios, Hector – sequence: 15 givenname: Fabiana surname: Soki fullname: Soki, Fabiana – sequence: 16 givenname: Gisele surname: Neiva fullname: Neiva, Gisele – sequence: 17 givenname: Kayvan surname: Najarian fullname: Najarian, Kayvan – sequence: 18 givenname: Jonathan surname: Gryak fullname: Gryak, Jonathan – sequence: 19 givenname: Martin surname: Styner fullname: Styner, Martin – sequence: 20 givenname: Juan Fernando surname: Aristizabal fullname: Aristizabal, Juan Fernando – sequence: 21 givenname: Diego surname: Rey fullname: Rey, Diego – sequence: 22 givenname: Maria Antonia surname: Alvarez fullname: Alvarez, Maria Antonia – sequence: 23 givenname: Loris surname: Bert fullname: Bert, Loris – sequence: 24 givenname: Reza surname: Soroushmehr fullname: Soroushmehr, Reza – sequence: 25 givenname: Juan surname: Prieto fullname: Prieto, Juan |
BookMark | eNpVkMtOwzAQRQ0URFv6BWz8AwY_4theVhUvqRUSFLG0nMRJC4kdYvf_cVo2rGbmztzRzJmBifPOAnBL8B3BWNwrIRFDmGEklcwEolqegUVSWdKOEj0HU5ITghjL1MW_Xs4nYJpyipTI2BWYESqJ4jxX2TVYhPCFMaaCco7VFHxu7NDsXQONq-DSOR9NHMuttXF3FN-8jwHWg-_g8hB9Z6Kt4LttOuvGWe-gr-Hm0MZ95yvTwpfONDbcgMvatMEu_uIcfDw-bFfPaP369LJarlFPMxxRYdNxSohc4TJTkjHJhSGyYJUslCRWiYrRiihSkzIvuJRlZivOWFUaJZg0bA7IaW_oh3S3HXTh_XfQBOuRpE5cNNOJhj5i04lk8tCTpx_8z8GGqO1oKtNDg2nLnemjHYLOhRRUES2pVpj9AoNucm4 |
ContentType | Book Chapter |
Copyright | Springer Nature Switzerland AG 2021 |
Copyright_xml | – notice: Springer Nature Switzerland AG 2021 |
DBID | FFUUA |
DEWEY | 616.07540285 |
DOI | 10.1007/978-3-030-89847-2_8 |
DatabaseName | ProQuest Ebook Central - Book Chapters - Demo use only |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Applied Sciences Computer Science Dentistry |
EISBN | 9783030898472 3030898474 |
EISSN | 1611-3349 |
Editor | Madabhushi, Anant Dong, Bin Greenspan, Hayit Syeda-Mahmood, Tanveer Li, Quanzheng Li, Xiang Leahy, Richard Wang, Hongzhi |
Editor_xml | – sequence: 1 fullname: Madabhushi, Anant – sequence: 1 givenname: Tanveer orcidid: 0000-0003-0059-3208 surname: Syeda-Mahmood fullname: Syeda-Mahmood, Tanveer email: stf@us.ibm.com – sequence: 2 fullname: Dong, Bin – sequence: 2 givenname: Xiang orcidid: 0000-0002-9851-6376 surname: Li fullname: Li, Xiang email: xli60@mgh.harvard.edu – sequence: 3 fullname: Greenspan, Hayit – sequence: 3 givenname: Anant orcidid: 0000-0002-5741-0399 surname: Madabhushi fullname: Madabhushi, Anant email: anant.madabhushi@case.edu – sequence: 4 fullname: Syeda-Mahmood, Tanveer – sequence: 4 givenname: Hayit orcidid: 0000-0001-6908-7552 surname: Greenspan fullname: Greenspan, Hayit email: hayit@eng.tau.ac.il – sequence: 5 fullname: Li, Quanzheng – sequence: 5 givenname: Quanzheng orcidid: 0000-0002-9651-5820 surname: Li fullname: Li, Quanzheng email: li.quanzheng@mgh.harvard.edu – sequence: 6 fullname: Li, Xiang – sequence: 6 givenname: Richard surname: Leahy fullname: Leahy, Richard email: leahy@sipi.usc.edu – sequence: 7 fullname: Leahy, Richard – sequence: 7 givenname: Bin surname: Dong fullname: Dong, Bin email: dongbin@math.pku.edu.cn – sequence: 8 fullname: Wang, Hongzhi – sequence: 8 givenname: Hongzhi orcidid: 0000-0003-3608-8932 surname: Wang fullname: Wang, Hongzhi email: hongzhiw@us.ibm.com |
EndPage | 92 |
ExternalDocumentID | EBC6787291_82_90 |
GroupedDBID | 38. AABBV AABLV ABNDO ACNBG ACWLQ AEDXK AEJLV AEKFX AELOD AIYYB ALMA_UNASSIGNED_HOLDINGS BAHJK BBABE CZZ DBWEY FFUUA I4C IEZ OCUHQ ORHYB SBO TGIZN TPJZQ TSXQS Z7R Z7U Z7X Z7Z Z83 Z87 Z88 -DT -~X 29L 2HA 2HV ACGFS ADCXD EJD F5P LAS LDH P2P RSU ~02 |
ID | FETCH-LOGICAL-p240t-be128977690c49833857a18b3d8b981e97d32d191f1c6b588c4ed533dca9738a3 |
ISBN | 9783030898465 3030898466 |
ISSN | 0302-9743 |
IngestDate | Tue Oct 01 20:03:43 EDT 2024 Thu Jul 25 23:52:59 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
LCCallNum | TA1501-1820 |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-p240t-be128977690c49833857a18b3d8b981e97d32d191f1c6b588c4ed533dca9738a3 |
Notes | Supported by NIDCR R01 DE024450. |
OCLC | 1281955694 |
PQID | EBC6787291_82_90 |
PageCount | 12 |
ParticipantIDs | springer_books_10_1007_978_3_030_89847_2_8 proquest_ebookcentralchapters_6787291_82_90 |
PublicationCentury | 2000 |
PublicationDate | 2021 20211020 |
PublicationDateYYYYMMDD | 2021-01-01 2021-10-20 |
PublicationDate_xml | – year: 2021 text: 2021 |
PublicationDecade | 2020 |
PublicationPlace | Switzerland |
PublicationPlace_xml | – name: Switzerland – name: Cham |
PublicationSeriesSubtitle | Image Processing, Computer Vision, Pattern Recognition, and Graphics |
PublicationSeriesTitle | Lecture Notes in Computer Science |
PublicationSeriesTitleAlternate | Lect.Notes Computer |
PublicationSubtitle | 11th International Workshop, ML-CDS 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings |
PublicationTitle | Multimodal Learning for Clinical Decision Support |
PublicationYear | 2021 |
Publisher | Springer International Publishing AG Springer International Publishing |
Publisher_xml | – name: Springer International Publishing AG – name: Springer International Publishing |
RelatedPersons | Hartmanis, Juris Gao, Wen Bertino, Elisa Woeginger, Gerhard Goos, Gerhard Steffen, Bernhard Yung, Moti |
RelatedPersons_xml | – sequence: 1 givenname: Gerhard surname: Goos fullname: Goos, Gerhard – sequence: 2 givenname: Juris surname: Hartmanis fullname: Hartmanis, Juris – sequence: 3 givenname: Elisa surname: Bertino fullname: Bertino, Elisa – sequence: 4 givenname: Wen surname: Gao fullname: Gao, Wen – sequence: 5 givenname: Bernhard orcidid: 0000-0001-9619-1558 surname: Steffen fullname: Steffen, Bernhard – sequence: 6 givenname: Gerhard orcidid: 0000-0001-8816-2693 surname: Woeginger fullname: Woeginger, Gerhard – sequence: 7 givenname: Moti orcidid: 0000-0003-0848-0873 surname: Yung fullname: Yung, Moti |
SSID | ssj0002725509 ssj0002792 |
Score | 2.0920835 |
Snippet | This paper aims to combine two different imaging techniques to create an accurate 3D model representation of root canals and dental crowns. We combine... |
SourceID | springer proquest |
SourceType | Publisher |
StartPage | 81 |
SubjectTerms | Deep learning Dental crown segmentation Dentistry Merging Root canal segmentation Universal label |
Title | Merging and Annotating Teeth and Roots from Automated Segmentation of Multimodal Images |
URI | http://ebookcentral.proquest.com/lib/SITE_ID/reader.action?docID=6787291&ppg=90 http://link.springer.com/10.1007/978-3-030-89847-2_8 |
Volume | 13050 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwELZ4SKjqAcpDPFrkQ09FQUmch33cbhco6vZQLYWbFT_CaRPEhkt_PePYTjYRF3qxEiuJRv6c8czY3wxCX2FF0KmQSUCJBAdFpDQodKkCmZUyZTSJbDKd-e_s5i65fUgffKFxxy5pxKX89yav5H9QhT7A1bBk34Fs91HogGvAF1pAGNqR8TsMs9oKQ-Yo4LJWJhLt4xvmzODUcx1_uPI5F6ZyZ-2C8G52zPXzo6cnTqqqNhvycLvQ2lHd_tR1s7Lkk8lLU4NdayxT_bh0XKXWylwT4ecSFNMghhBHoxiCjyGOopBrgbDJ9cDvJCbLDSBpyzx0ihR0R_imWl4_iQGvBubdPIg57Vchv_Nui4eOcmDPvk9hUQU_IOI05izcRJs5Ax22PZnd_vrbxdTiHBykkBkKjxcws0mWeoG7zFM2ufBInoGfMdoaby2OxR76aFgo2NBDQMRPaENX-2jX-QzYaeTVPtqZu8MRB-jegYoBP9yDiltQ284WVGxAxR2oeB1UXJe4BxVbUA_R3dVsMb0JXN2M4AnssyYQGowOsOszFsqEUUJomhcRFURRwWikWa5IrMBRLyOZwd9JZaIVmP1KFgx-zYIcoa2qrvQxwqVQSoaRMlmDElLAKi2hpUSxIhOCpSfowo8Xb3f33ZFiaUdnxQewnaBvfki5eXjFfdJsgIITDlDwFgoOUJy-69Nn6EM_sT-jreb5RX8Bc7ER526WvAKU12lO |
link.rule.ids | 785,786,790,799,27958 |
linkProvider | Library Specific Holdings |
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%3Abook&rft.genre=bookitem&rft.title=Multimodal+Learning+for+Clinical+Decision+Support&rft.atitle=Merging+and+Annotating+Teeth+and+Roots+from+Automated+Segmentation+of+Multimodal+Images&rft.date=2021-01-01&rft.pub=Springer+International+Publishing+AG&rft.isbn=9783030898465&rft.volume=13050&rft_id=info:doi/10.1007%2F978-3-030-89847-2_8&rft.externalDBID=90&rft.externalDocID=EBC6787291_82_90 |
thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Febookcentral.proquest.com%2Fcovers%2F6787291-l.jpg |