Mask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis
3D visualization diagnosis for pulmonary nodule detection and segmentation is becoming a promising topic in the field of surgical researches and applications. Aiming at assisting radiologists to diagnose pulmonary nodules more accurately, the methods of detection and segmentation for pulmonary nodul...
Gespeichert in:
Veröffentlicht in: | IEEE access 2020, Vol.8, p.44400-44409 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 44409 |
---|---|
container_issue | |
container_start_page | 44400 |
container_title | IEEE access |
container_volume | 8 |
creator | Cai, Linqin Long, Tao Dai, Yuhan Huang, Yuting |
description | 3D visualization diagnosis for pulmonary nodule detection and segmentation is becoming a promising topic in the field of surgical researches and applications. Aiming at assisting radiologists to diagnose pulmonary nodules more accurately, the methods of detection and segmentation for pulmonary nodule 3D visualization diagnosis were proposed based on Mask Region-Convolutional Neural Network (Mask R-CNN) and ray-casting volume rendering algorithm. The Mask R-CNN used resnet50 as the backbone and applied Feature Pyramid Network (FPN) to fully explore multiscale feature maps. And then, Region Proposal Network (RPN) was used to propose candidate bounding boxes. Furthermore, the mask matrices and the raw medical image sequences were multiplied to obtain sequences of predicted pulmonary nodules. Finally, ray-casting volume rendering algorithm was applied to generate the 3D models of pulmonary nodules. The proposed methods are tested and evaluated on publicly available LUNA16 dataset and the independent dataset from Ali TianChi challenge. Experimental results show that Mask R-CNN of weighted loss reaches sensitivities of 88.1% and 88.7% at 1 and 4 false positives per scan, respectively. Meanwhile, we can obtain AP@50 score of 0.882 using Mask R-CNN with weighted loss on labelme_LUNA16 dataset, which outperforms many existing state-of-the-art approaches of detection and segmentation of pulmonary nodules. |
doi_str_mv | 10.1109/ACCESS.2020.2976432 |
format | Article |
fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_proquest_journals_2454746392</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9016227</ieee_id><doaj_id>oai_doaj_org_article_adb42fd779d94fd890f78c210b602701</doaj_id><sourcerecordid>2454746392</sourcerecordid><originalsourceid>FETCH-LOGICAL-c458t-5ceb6edbee6e996f4977d6aef98472e0173f8163f3fcc97374f8703d4f8328993</originalsourceid><addsrcrecordid>eNpNUctOwzAQjBBIIOALuETinOJX7PgIKY9KUBAFLhwsN15XLmkMdnKAr8cQVLGXXY1mZkeaLDvBaIIxkmfndX25WEwIImhCpOCMkp3sgGAuC1pSvvvv3s-OY1yjNFWCSnGQvd7p-JY_FvV8XlzoCCafQg9N73yX687kC1htoOv1L2B9yB-GduM7HT7zuTdDCzmd5i8uDrp1XyNr6vSq89HFo2zP6jbC8d8-zJ6vLp_qm-L2_npWn98WDSurvigbWHIwSwAOUnLLpBCGa7CyYoIAwoLaFJdaaptGCiqYrQSiJi1KKinpYTYbfY3Xa_Ue3CbFU1479Qv4sFI69K5pQWmzZMQaIaSRzJpKIiuqhmC05IgIhJPX6ej1HvzHALFXaz-ELsVXhJVMME4lSSw6sprgYwxgt18xUj-lqLEU9VOK-islqU5GlQOArUIizAkR9Bvdg4bq</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2454746392</pqid></control><display><type>article</type><title>Mask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Cai, Linqin ; Long, Tao ; Dai, Yuhan ; Huang, Yuting</creator><creatorcontrib>Cai, Linqin ; Long, Tao ; Dai, Yuhan ; Huang, Yuting</creatorcontrib><description>3D visualization diagnosis for pulmonary nodule detection and segmentation is becoming a promising topic in the field of surgical researches and applications. Aiming at assisting radiologists to diagnose pulmonary nodules more accurately, the methods of detection and segmentation for pulmonary nodule 3D visualization diagnosis were proposed based on Mask Region-Convolutional Neural Network (Mask R-CNN) and ray-casting volume rendering algorithm. The Mask R-CNN used resnet50 as the backbone and applied Feature Pyramid Network (FPN) to fully explore multiscale feature maps. And then, Region Proposal Network (RPN) was used to propose candidate bounding boxes. Furthermore, the mask matrices and the raw medical image sequences were multiplied to obtain sequences of predicted pulmonary nodules. Finally, ray-casting volume rendering algorithm was applied to generate the 3D models of pulmonary nodules. The proposed methods are tested and evaluated on publicly available LUNA16 dataset and the independent dataset from Ali TianChi challenge. Experimental results show that Mask R-CNN of weighted loss reaches sensitivities of 88.1% and 88.7% at 1 and 4 false positives per scan, respectively. Meanwhile, we can obtain AP@50 score of 0.882 using Mask R-CNN with weighted loss on labelme_LUNA16 dataset, which outperforms many existing state-of-the-art approaches of detection and segmentation of pulmonary nodules.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2020.2976432</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Artificial neural networks ; Cancer ; Datasets ; deep learning ; detection and segmentation ; Diagnosis ; Feature extraction ; Feature maps ; Image segmentation ; Lung ; Medical diagnostic imaging ; Medical imaging ; Nodules ; Pulmonary nodule ; ray-casting rendering ; Rendering ; Three dimensional models ; Three-dimensional displays ; Visualization</subject><ispartof>IEEE access, 2020, Vol.8, p.44400-44409</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c458t-5ceb6edbee6e996f4977d6aef98472e0173f8163f3fcc97374f8703d4f8328993</citedby><cites>FETCH-LOGICAL-c458t-5ceb6edbee6e996f4977d6aef98472e0173f8163f3fcc97374f8703d4f8328993</cites><orcidid>0000-0002-6859-9932 ; 0000-0002-4472-9608 ; 0000-0002-5663-8113 ; 0000-0001-9300-4809</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9016227$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Cai, Linqin</creatorcontrib><creatorcontrib>Long, Tao</creatorcontrib><creatorcontrib>Dai, Yuhan</creatorcontrib><creatorcontrib>Huang, Yuting</creatorcontrib><title>Mask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis</title><title>IEEE access</title><addtitle>Access</addtitle><description>3D visualization diagnosis for pulmonary nodule detection and segmentation is becoming a promising topic in the field of surgical researches and applications. Aiming at assisting radiologists to diagnose pulmonary nodules more accurately, the methods of detection and segmentation for pulmonary nodule 3D visualization diagnosis were proposed based on Mask Region-Convolutional Neural Network (Mask R-CNN) and ray-casting volume rendering algorithm. The Mask R-CNN used resnet50 as the backbone and applied Feature Pyramid Network (FPN) to fully explore multiscale feature maps. And then, Region Proposal Network (RPN) was used to propose candidate bounding boxes. Furthermore, the mask matrices and the raw medical image sequences were multiplied to obtain sequences of predicted pulmonary nodules. Finally, ray-casting volume rendering algorithm was applied to generate the 3D models of pulmonary nodules. The proposed methods are tested and evaluated on publicly available LUNA16 dataset and the independent dataset from Ali TianChi challenge. Experimental results show that Mask R-CNN of weighted loss reaches sensitivities of 88.1% and 88.7% at 1 and 4 false positives per scan, respectively. Meanwhile, we can obtain AP@50 score of 0.882 using Mask R-CNN with weighted loss on labelme_LUNA16 dataset, which outperforms many existing state-of-the-art approaches of detection and segmentation of pulmonary nodules.</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Cancer</subject><subject>Datasets</subject><subject>deep learning</subject><subject>detection and segmentation</subject><subject>Diagnosis</subject><subject>Feature extraction</subject><subject>Feature maps</subject><subject>Image segmentation</subject><subject>Lung</subject><subject>Medical diagnostic imaging</subject><subject>Medical imaging</subject><subject>Nodules</subject><subject>Pulmonary nodule</subject><subject>ray-casting rendering</subject><subject>Rendering</subject><subject>Three dimensional models</subject><subject>Three-dimensional displays</subject><subject>Visualization</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUctOwzAQjBBIIOALuETinOJX7PgIKY9KUBAFLhwsN15XLmkMdnKAr8cQVLGXXY1mZkeaLDvBaIIxkmfndX25WEwIImhCpOCMkp3sgGAuC1pSvvvv3s-OY1yjNFWCSnGQvd7p-JY_FvV8XlzoCCafQg9N73yX687kC1htoOv1L2B9yB-GduM7HT7zuTdDCzmd5i8uDrp1XyNr6vSq89HFo2zP6jbC8d8-zJ6vLp_qm-L2_npWn98WDSurvigbWHIwSwAOUnLLpBCGa7CyYoIAwoLaFJdaaptGCiqYrQSiJi1KKinpYTYbfY3Xa_Ue3CbFU1479Qv4sFI69K5pQWmzZMQaIaSRzJpKIiuqhmC05IgIhJPX6ej1HvzHALFXaz-ELsVXhJVMME4lSSw6sprgYwxgt18xUj-lqLEU9VOK-islqU5GlQOArUIizAkR9Bvdg4bq</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Cai, Linqin</creator><creator>Long, Tao</creator><creator>Dai, Yuhan</creator><creator>Huang, Yuting</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-6859-9932</orcidid><orcidid>https://orcid.org/0000-0002-4472-9608</orcidid><orcidid>https://orcid.org/0000-0002-5663-8113</orcidid><orcidid>https://orcid.org/0000-0001-9300-4809</orcidid></search><sort><creationdate>2020</creationdate><title>Mask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis</title><author>Cai, Linqin ; Long, Tao ; Dai, Yuhan ; Huang, Yuting</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c458t-5ceb6edbee6e996f4977d6aef98472e0173f8163f3fcc97374f8703d4f8328993</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Cancer</topic><topic>Datasets</topic><topic>deep learning</topic><topic>detection and segmentation</topic><topic>Diagnosis</topic><topic>Feature extraction</topic><topic>Feature maps</topic><topic>Image segmentation</topic><topic>Lung</topic><topic>Medical diagnostic imaging</topic><topic>Medical imaging</topic><topic>Nodules</topic><topic>Pulmonary nodule</topic><topic>ray-casting rendering</topic><topic>Rendering</topic><topic>Three dimensional models</topic><topic>Three-dimensional displays</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cai, Linqin</creatorcontrib><creatorcontrib>Long, Tao</creatorcontrib><creatorcontrib>Dai, Yuhan</creatorcontrib><creatorcontrib>Huang, Yuting</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cai, Linqin</au><au>Long, Tao</au><au>Dai, Yuhan</au><au>Huang, Yuting</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Mask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2020</date><risdate>2020</risdate><volume>8</volume><spage>44400</spage><epage>44409</epage><pages>44400-44409</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>3D visualization diagnosis for pulmonary nodule detection and segmentation is becoming a promising topic in the field of surgical researches and applications. Aiming at assisting radiologists to diagnose pulmonary nodules more accurately, the methods of detection and segmentation for pulmonary nodule 3D visualization diagnosis were proposed based on Mask Region-Convolutional Neural Network (Mask R-CNN) and ray-casting volume rendering algorithm. The Mask R-CNN used resnet50 as the backbone and applied Feature Pyramid Network (FPN) to fully explore multiscale feature maps. And then, Region Proposal Network (RPN) was used to propose candidate bounding boxes. Furthermore, the mask matrices and the raw medical image sequences were multiplied to obtain sequences of predicted pulmonary nodules. Finally, ray-casting volume rendering algorithm was applied to generate the 3D models of pulmonary nodules. The proposed methods are tested and evaluated on publicly available LUNA16 dataset and the independent dataset from Ali TianChi challenge. Experimental results show that Mask R-CNN of weighted loss reaches sensitivities of 88.1% and 88.7% at 1 and 4 false positives per scan, respectively. Meanwhile, we can obtain AP@50 score of 0.882 using Mask R-CNN with weighted loss on labelme_LUNA16 dataset, which outperforms many existing state-of-the-art approaches of detection and segmentation of pulmonary nodules.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2020.2976432</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-6859-9932</orcidid><orcidid>https://orcid.org/0000-0002-4472-9608</orcidid><orcidid>https://orcid.org/0000-0002-5663-8113</orcidid><orcidid>https://orcid.org/0000-0001-9300-4809</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2169-3536 |
ispartof | IEEE access, 2020, Vol.8, p.44400-44409 |
issn | 2169-3536 2169-3536 |
language | eng |
recordid | cdi_proquest_journals_2454746392 |
source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals |
subjects | Algorithms Artificial neural networks Cancer Datasets deep learning detection and segmentation Diagnosis Feature extraction Feature maps Image segmentation Lung Medical diagnostic imaging Medical imaging Nodules Pulmonary nodule ray-casting rendering Rendering Three dimensional models Three-dimensional displays Visualization |
title | Mask R-CNN-Based Detection and Segmentation for Pulmonary Nodule 3D Visualization Diagnosis |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T13%3A08%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Mask%20R-CNN-Based%20Detection%20and%20Segmentation%20for%20Pulmonary%20Nodule%203D%20Visualization%20Diagnosis&rft.jtitle=IEEE%20access&rft.au=Cai,%20Linqin&rft.date=2020&rft.volume=8&rft.spage=44400&rft.epage=44409&rft.pages=44400-44409&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2020.2976432&rft_dat=%3Cproquest_ieee_%3E2454746392%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2454746392&rft_id=info:pmid/&rft_ieee_id=9016227&rft_doaj_id=oai_doaj_org_article_adb42fd779d94fd890f78c210b602701&rfr_iscdi=true |