Lightweight deep learning methods for panoramic dental X-ray image segmentation

Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightwei...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural computing & applications 2023-04, Vol.35 (11), p.8295-8306
Hauptverfasser: Lin, Songyue, Hao, Xuejiang, Liu, Yan, Yan, Dong, Liu, Jianwei, Zhong, Mingjun
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 8306
container_issue 11
container_start_page 8295
container_title Neural computing & applications
container_volume 35
creator Lin, Songyue
Hao, Xuejiang
Liu, Yan
Yan, Dong
Liu, Jianwei
Zhong, Mingjun
description Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightweight deep learning methods for dental X-ray image segmentation for the purpose of deployment on edge devices, such as dental X-ray imaging systems. A novel lightweight neural network scheme using knowledge distillation is proposed in this paper. The proposed lightweight method and a number of existing lightweight deep learning methods were trained on a panoramic dental X-ray image data set. These lightweight methods were evaluated and compared by using several accuracy metrics. The proposed lightweight method only requires 0.33 million parameters ( ∼ 7.5 megabytes) for the trained model, while it achieved the best performance in terms of IoU (0.804) and Dice (0.89) comparing to other lightweight methods. This work shows that the proposed method for dental X-ray image segmentation requires small memory storage, while it achieved comparative performance. The method could be deployed on edge devices and could potentially assist clinicians to alleviate their daily workflow and improve the quality of their analysis.
doi_str_mv 10.1007/s00521-022-08102-7
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2789009861</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2789009861</sourcerecordid><originalsourceid>FETCH-LOGICAL-c363t-5d61047b394d9b92c2e5e5e22ffae5e89e86a6b0f1fc93a40980972eed303da53</originalsourceid><addsrcrecordid>eNp9UE1Lw0AQXUTBWv0DnhY8r85-ZJM9SlErFHpR8LZsk0ma0mTjbor037s1gjcZmAcz770ZHiG3HO45QP4QATLBGQjBoOAgWH5GZlxJySRkxTmZgVFprZW8JFcx7gBA6SKbkfWqbbbjF546rRAHukcX-rZvaIfj1leR1j7QwfU-uK4tE6cf3Z5-sOCOtO1cgzRi052mY-v7a3JRu33Em1-ck_fnp7fFkq3WL6-LxxUrpZYjyyrNQeUbaVRlNkaUArNUQtS1S1gYLLTTG6h5XRrpFJgCTC4QKwmycpmck7vJdwj-84BxtDt_CH06aUVeGEgCzRNLTKwy-BgD1nYI6edwtBzsKTg7BWdTcPYnOJsnkZxEMZH7BsOf9T-qb9j-cN8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2789009861</pqid></control><display><type>article</type><title>Lightweight deep learning methods for panoramic dental X-ray image segmentation</title><source>SpringerNature Journals</source><creator>Lin, Songyue ; Hao, Xuejiang ; Liu, Yan ; Yan, Dong ; Liu, Jianwei ; Zhong, Mingjun</creator><creatorcontrib>Lin, Songyue ; Hao, Xuejiang ; Liu, Yan ; Yan, Dong ; Liu, Jianwei ; Zhong, Mingjun</creatorcontrib><description>Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightweight deep learning methods for dental X-ray image segmentation for the purpose of deployment on edge devices, such as dental X-ray imaging systems. A novel lightweight neural network scheme using knowledge distillation is proposed in this paper. The proposed lightweight method and a number of existing lightweight deep learning methods were trained on a panoramic dental X-ray image data set. These lightweight methods were evaluated and compared by using several accuracy metrics. The proposed lightweight method only requires 0.33 million parameters ( ∼ 7.5 megabytes) for the trained model, while it achieved the best performance in terms of IoU (0.804) and Dice (0.89) comparing to other lightweight methods. This work shows that the proposed method for dental X-ray image segmentation requires small memory storage, while it achieved comparative performance. The method could be deployed on edge devices and could potentially assist clinicians to alleviate their daily workflow and improve the quality of their analysis.</description><identifier>ISSN: 0941-0643</identifier><identifier>EISSN: 1433-3058</identifier><identifier>DOI: 10.1007/s00521-022-08102-7</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Algorithms ; Artificial Intelligence ; Cloud computing ; Computational Biology/Bioinformatics ; Computational Science and Engineering ; Computer Science ; Data Mining and Knowledge Discovery ; Deep learning ; Distillation ; Image Processing and Computer Vision ; Image segmentation ; Lightweight ; Machine learning ; Neural networks ; Original Article ; Probability and Statistics in Computer Science ; Teaching methods ; Workflow ; X ray imagery</subject><ispartof>Neural computing &amp; applications, 2023-04, Vol.35 (11), p.8295-8306</ispartof><rights>The Author(s) 2022</rights><rights>The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c363t-5d61047b394d9b92c2e5e5e22ffae5e89e86a6b0f1fc93a40980972eed303da53</citedby><cites>FETCH-LOGICAL-c363t-5d61047b394d9b92c2e5e5e22ffae5e89e86a6b0f1fc93a40980972eed303da53</cites><orcidid>0000-0002-1525-1270</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00521-022-08102-7$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00521-022-08102-7$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Lin, Songyue</creatorcontrib><creatorcontrib>Hao, Xuejiang</creatorcontrib><creatorcontrib>Liu, Yan</creatorcontrib><creatorcontrib>Yan, Dong</creatorcontrib><creatorcontrib>Liu, Jianwei</creatorcontrib><creatorcontrib>Zhong, Mingjun</creatorcontrib><title>Lightweight deep learning methods for panoramic dental X-ray image segmentation</title><title>Neural computing &amp; applications</title><addtitle>Neural Comput &amp; Applic</addtitle><description>Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightweight deep learning methods for dental X-ray image segmentation for the purpose of deployment on edge devices, such as dental X-ray imaging systems. A novel lightweight neural network scheme using knowledge distillation is proposed in this paper. The proposed lightweight method and a number of existing lightweight deep learning methods were trained on a panoramic dental X-ray image data set. These lightweight methods were evaluated and compared by using several accuracy metrics. The proposed lightweight method only requires 0.33 million parameters ( ∼ 7.5 megabytes) for the trained model, while it achieved the best performance in terms of IoU (0.804) and Dice (0.89) comparing to other lightweight methods. This work shows that the proposed method for dental X-ray image segmentation requires small memory storage, while it achieved comparative performance. The method could be deployed on edge devices and could potentially assist clinicians to alleviate their daily workflow and improve the quality of their analysis.</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Cloud computing</subject><subject>Computational Biology/Bioinformatics</subject><subject>Computational Science and Engineering</subject><subject>Computer Science</subject><subject>Data Mining and Knowledge Discovery</subject><subject>Deep learning</subject><subject>Distillation</subject><subject>Image Processing and Computer Vision</subject><subject>Image segmentation</subject><subject>Lightweight</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Original Article</subject><subject>Probability and Statistics in Computer Science</subject><subject>Teaching methods</subject><subject>Workflow</subject><subject>X ray imagery</subject><issn>0941-0643</issn><issn>1433-3058</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNp9UE1Lw0AQXUTBWv0DnhY8r85-ZJM9SlErFHpR8LZsk0ma0mTjbor037s1gjcZmAcz770ZHiG3HO45QP4QATLBGQjBoOAgWH5GZlxJySRkxTmZgVFprZW8JFcx7gBA6SKbkfWqbbbjF546rRAHukcX-rZvaIfj1leR1j7QwfU-uK4tE6cf3Z5-sOCOtO1cgzRi052mY-v7a3JRu33Em1-ck_fnp7fFkq3WL6-LxxUrpZYjyyrNQeUbaVRlNkaUArNUQtS1S1gYLLTTG6h5XRrpFJgCTC4QKwmycpmck7vJdwj-84BxtDt_CH06aUVeGEgCzRNLTKwy-BgD1nYI6edwtBzsKTg7BWdTcPYnOJsnkZxEMZH7BsOf9T-qb9j-cN8</recordid><startdate>20230401</startdate><enddate>20230401</enddate><creator>Lin, Songyue</creator><creator>Hao, Xuejiang</creator><creator>Liu, Yan</creator><creator>Yan, Dong</creator><creator>Liu, Jianwei</creator><creator>Zhong, Mingjun</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0002-1525-1270</orcidid></search><sort><creationdate>20230401</creationdate><title>Lightweight deep learning methods for panoramic dental X-ray image segmentation</title><author>Lin, Songyue ; Hao, Xuejiang ; Liu, Yan ; Yan, Dong ; Liu, Jianwei ; Zhong, Mingjun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c363t-5d61047b394d9b92c2e5e5e22ffae5e89e86a6b0f1fc93a40980972eed303da53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Cloud computing</topic><topic>Computational Biology/Bioinformatics</topic><topic>Computational Science and Engineering</topic><topic>Computer Science</topic><topic>Data Mining and Knowledge Discovery</topic><topic>Deep learning</topic><topic>Distillation</topic><topic>Image Processing and Computer Vision</topic><topic>Image segmentation</topic><topic>Lightweight</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Original Article</topic><topic>Probability and Statistics in Computer Science</topic><topic>Teaching methods</topic><topic>Workflow</topic><topic>X ray imagery</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lin, Songyue</creatorcontrib><creatorcontrib>Hao, Xuejiang</creatorcontrib><creatorcontrib>Liu, Yan</creatorcontrib><creatorcontrib>Yan, Dong</creatorcontrib><creatorcontrib>Liu, Jianwei</creatorcontrib><creatorcontrib>Zhong, Mingjun</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Neural computing &amp; applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lin, Songyue</au><au>Hao, Xuejiang</au><au>Liu, Yan</au><au>Yan, Dong</au><au>Liu, Jianwei</au><au>Zhong, Mingjun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Lightweight deep learning methods for panoramic dental X-ray image segmentation</atitle><jtitle>Neural computing &amp; applications</jtitle><stitle>Neural Comput &amp; Applic</stitle><date>2023-04-01</date><risdate>2023</risdate><volume>35</volume><issue>11</issue><spage>8295</spage><epage>8306</epage><pages>8295-8306</pages><issn>0941-0643</issn><eissn>1433-3058</eissn><abstract>Dental X-ray image segmentation is helpful for assisting clinicians to examine tooth conditions and identify dental diseases. Fast and lightweight segmentation algorithms without using cloud computing may be required to be implemented in X-ray imaging systems. This paper aims to investigate lightweight deep learning methods for dental X-ray image segmentation for the purpose of deployment on edge devices, such as dental X-ray imaging systems. A novel lightweight neural network scheme using knowledge distillation is proposed in this paper. The proposed lightweight method and a number of existing lightweight deep learning methods were trained on a panoramic dental X-ray image data set. These lightweight methods were evaluated and compared by using several accuracy metrics. The proposed lightweight method only requires 0.33 million parameters ( ∼ 7.5 megabytes) for the trained model, while it achieved the best performance in terms of IoU (0.804) and Dice (0.89) comparing to other lightweight methods. This work shows that the proposed method for dental X-ray image segmentation requires small memory storage, while it achieved comparative performance. The method could be deployed on edge devices and could potentially assist clinicians to alleviate their daily workflow and improve the quality of their analysis.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s00521-022-08102-7</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-1525-1270</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0941-0643
ispartof Neural computing & applications, 2023-04, Vol.35 (11), p.8295-8306
issn 0941-0643
1433-3058
language eng
recordid cdi_proquest_journals_2789009861
source SpringerNature Journals
subjects Algorithms
Artificial Intelligence
Cloud computing
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Deep learning
Distillation
Image Processing and Computer Vision
Image segmentation
Lightweight
Machine learning
Neural networks
Original Article
Probability and Statistics in Computer Science
Teaching methods
Workflow
X ray imagery
title Lightweight deep learning methods for panoramic dental X-ray image segmentation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A56%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Lightweight%20deep%20learning%20methods%20for%20panoramic%20dental%20X-ray%20image%20segmentation&rft.jtitle=Neural%20computing%20&%20applications&rft.au=Lin,%20Songyue&rft.date=2023-04-01&rft.volume=35&rft.issue=11&rft.spage=8295&rft.epage=8306&rft.pages=8295-8306&rft.issn=0941-0643&rft.eissn=1433-3058&rft_id=info:doi/10.1007/s00521-022-08102-7&rft_dat=%3Cproquest_cross%3E2789009861%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2789009861&rft_id=info:pmid/&rfr_iscdi=true