Loading…

A Real-Time Multifunctional Framework for Guidewire Morphological and Positional Analysis in Interventional X-Ray Fluoroscopy

In endovascular and cardiovascular surgery, real-time guidewire morphological and positional analysis is an important prerequisite for robot-assisted intervention, which can aid in reducing the radiation dose, contrast agent, and procedure time. Nevertheless, this task often comes with the challenge...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cognitive and developmental systems 2021-09, Vol.13 (3), p.657-667
Main Authors: Zhou, Yan-Jie, Xie, Xiao-Liang, Zhou, Xiao-Hu, Liu, Shi-Qi, Bian, Gui-Bin, Hou, Zeng-Guang
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3
cites cdi_FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3
container_end_page 667
container_issue 3
container_start_page 657
container_title IEEE transactions on cognitive and developmental systems
container_volume 13
creator Zhou, Yan-Jie
Xie, Xiao-Liang
Zhou, Xiao-Hu
Liu, Shi-Qi
Bian, Gui-Bin
Hou, Zeng-Guang
description In endovascular and cardiovascular surgery, real-time guidewire morphological and positional analysis is an important prerequisite for robot-assisted intervention, which can aid in reducing the radiation dose, contrast agent, and procedure time. Nevertheless, this task often comes with the challenge of the deformable elongated structure with low contrast in noisy X-ray fluoroscopy. In this article, a real-time multifunctional framework is proposed for fully automatic guidewire morphological and positional analysis, namely, guidewire segmentation, endpoint localization, and angle measurement. In the first stage, the proposed fast attention recurrent network (FAR-Net) achieves real-time and accurate guidewire segmentation. In the second stage, the endpoint localization and angle measurement algorithm robustly obtain subpixel-level endpoint and angle of the guidewire tip. Quantitative and qualitative evaluations on the MSGSeg data set consisting of 180 X-ray sequences from 30 patients demonstrate that the proposed framework significantly outperforms simpler baselines as well as the best previously published result for this task. The proposed approach reached {F_{1}} -Score of 0.938, mean distance error of 0.596 pixels, endpoint localization and angle measurement accuracy of 97.8% and 95.3%, and an inference rate of approximately 13 FPS. The proposed framework not only addresses the issues of extreme class imbalance and misclassified examples but also meets the real-time requirements, achieving state-of-the-art performance. The proposed approach is promising for integration into robotic navigation frameworks to various intravascular applications, enabling robotic-assisted intervention.
doi_str_mv 10.1109/TCDS.2020.3023952
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TCDS_2020_3023952</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9197674</ieee_id><sourcerecordid>2571224301</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3</originalsourceid><addsrcrecordid>eNo9kE1LAzEQhhdRsGh_gHgJeN6aj_3KsVRbCxWlVvAWpklWU7ebNdm17MH_bkpLLzPDzPMOL28U3RA8IgTz-9Xk4W1EMcUjhinjKT2LBpTlPC444-enmeLLaOj9BmNMMpYXST6I_sZoqaGKV2ar0XNXtabsatkaW0OFpg62emfdNyqtQ7POKL0zLnDWNV-2sp9GBgpqhV6tN0fROJTeG49MjeZ1q92vro-nj3gJPZpWnXXWS9v019FFCZXXw2O_it6nj6vJU7x4mc0n40UsKWdtnGlQsuQFJgngsFoDA4oZ5ylIoKDWmCdKrWkic5aQQmaqSAupOVEpACWSXUV3h7-Nsz-d9q3Y2M4FS17QNCeUJgyTQJEDJYM973QpGme24HpBsNgHLfZBi33Q4hh00NweNEZrfeI54XmWJ-wfk4F75Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2571224301</pqid></control><display><type>article</type><title>A Real-Time Multifunctional Framework for Guidewire Morphological and Positional Analysis in Interventional X-Ray Fluoroscopy</title><source>IEEE Xplore (Online service)</source><creator>Zhou, Yan-Jie ; Xie, Xiao-Liang ; Zhou, Xiao-Hu ; Liu, Shi-Qi ; Bian, Gui-Bin ; Hou, Zeng-Guang</creator><creatorcontrib>Zhou, Yan-Jie ; Xie, Xiao-Liang ; Zhou, Xiao-Hu ; Liu, Shi-Qi ; Bian, Gui-Bin ; Hou, Zeng-Guang</creatorcontrib><description>In endovascular and cardiovascular surgery, real-time guidewire morphological and positional analysis is an important prerequisite for robot-assisted intervention, which can aid in reducing the radiation dose, contrast agent, and procedure time. Nevertheless, this task often comes with the challenge of the deformable elongated structure with low contrast in noisy X-ray fluoroscopy. In this article, a real-time multifunctional framework is proposed for fully automatic guidewire morphological and positional analysis, namely, guidewire segmentation, endpoint localization, and angle measurement. In the first stage, the proposed fast attention recurrent network (FAR-Net) achieves real-time and accurate guidewire segmentation. In the second stage, the endpoint localization and angle measurement algorithm robustly obtain subpixel-level endpoint and angle of the guidewire tip. Quantitative and qualitative evaluations on the MSGSeg data set consisting of 180 X-ray sequences from 30 patients demonstrate that the proposed framework significantly outperforms simpler baselines as well as the best previously published result for this task. The proposed approach reached &lt;inline-formula&gt; &lt;tex-math notation="LaTeX"&gt;{F_{1}} &lt;/tex-math&gt;&lt;/inline-formula&gt;-Score of 0.938, mean distance error of 0.596 pixels, endpoint localization and angle measurement accuracy of 97.8% and 95.3%, and an inference rate of approximately 13 FPS. The proposed framework not only addresses the issues of extreme class imbalance and misclassified examples but also meets the real-time requirements, achieving state-of-the-art performance. The proposed approach is promising for integration into robotic navigation frameworks to various intravascular applications, enabling robotic-assisted intervention.</description><identifier>ISSN: 2379-8920</identifier><identifier>EISSN: 2379-8939</identifier><identifier>DOI: 10.1109/TCDS.2020.3023952</identifier><identifier>CODEN: ITCDA4</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Catheters ; Contrast agents ; Convolution ; Decoding ; Deep learning ; Elongated structure ; Feature extraction ; Fluoroscopy ; Formability ; guidewire ; Localization ; Morphology ; Pixels ; Qualitative analysis ; Radiation dosage ; Real time ; Real-time systems ; robot-assisted intervention ; Robots ; Segmentation ; segmentation and localization ; Task analysis ; X-ray fluoroscopy</subject><ispartof>IEEE transactions on cognitive and developmental systems, 2021-09, Vol.13 (3), p.657-667</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3</citedby><cites>FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3</cites><orcidid>0000-0002-6227-4811 ; 0000-0001-7191-4449 ; 0000-0002-7602-4848 ; 0000-0003-4708-2245 ; 0000-0002-1534-5840</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9197674$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,54796</link.rule.ids></links><search><creatorcontrib>Zhou, Yan-Jie</creatorcontrib><creatorcontrib>Xie, Xiao-Liang</creatorcontrib><creatorcontrib>Zhou, Xiao-Hu</creatorcontrib><creatorcontrib>Liu, Shi-Qi</creatorcontrib><creatorcontrib>Bian, Gui-Bin</creatorcontrib><creatorcontrib>Hou, Zeng-Guang</creatorcontrib><title>A Real-Time Multifunctional Framework for Guidewire Morphological and Positional Analysis in Interventional X-Ray Fluoroscopy</title><title>IEEE transactions on cognitive and developmental systems</title><addtitle>TCDS</addtitle><description>In endovascular and cardiovascular surgery, real-time guidewire morphological and positional analysis is an important prerequisite for robot-assisted intervention, which can aid in reducing the radiation dose, contrast agent, and procedure time. Nevertheless, this task often comes with the challenge of the deformable elongated structure with low contrast in noisy X-ray fluoroscopy. In this article, a real-time multifunctional framework is proposed for fully automatic guidewire morphological and positional analysis, namely, guidewire segmentation, endpoint localization, and angle measurement. In the first stage, the proposed fast attention recurrent network (FAR-Net) achieves real-time and accurate guidewire segmentation. In the second stage, the endpoint localization and angle measurement algorithm robustly obtain subpixel-level endpoint and angle of the guidewire tip. Quantitative and qualitative evaluations on the MSGSeg data set consisting of 180 X-ray sequences from 30 patients demonstrate that the proposed framework significantly outperforms simpler baselines as well as the best previously published result for this task. The proposed approach reached &lt;inline-formula&gt; &lt;tex-math notation="LaTeX"&gt;{F_{1}} &lt;/tex-math&gt;&lt;/inline-formula&gt;-Score of 0.938, mean distance error of 0.596 pixels, endpoint localization and angle measurement accuracy of 97.8% and 95.3%, and an inference rate of approximately 13 FPS. The proposed framework not only addresses the issues of extreme class imbalance and misclassified examples but also meets the real-time requirements, achieving state-of-the-art performance. The proposed approach is promising for integration into robotic navigation frameworks to various intravascular applications, enabling robotic-assisted intervention.</description><subject>Algorithms</subject><subject>Catheters</subject><subject>Contrast agents</subject><subject>Convolution</subject><subject>Decoding</subject><subject>Deep learning</subject><subject>Elongated structure</subject><subject>Feature extraction</subject><subject>Fluoroscopy</subject><subject>Formability</subject><subject>guidewire</subject><subject>Localization</subject><subject>Morphology</subject><subject>Pixels</subject><subject>Qualitative analysis</subject><subject>Radiation dosage</subject><subject>Real time</subject><subject>Real-time systems</subject><subject>robot-assisted intervention</subject><subject>Robots</subject><subject>Segmentation</subject><subject>segmentation and localization</subject><subject>Task analysis</subject><subject>X-ray fluoroscopy</subject><issn>2379-8920</issn><issn>2379-8939</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNo9kE1LAzEQhhdRsGh_gHgJeN6aj_3KsVRbCxWlVvAWpklWU7ebNdm17MH_bkpLLzPDzPMOL28U3RA8IgTz-9Xk4W1EMcUjhinjKT2LBpTlPC444-enmeLLaOj9BmNMMpYXST6I_sZoqaGKV2ar0XNXtabsatkaW0OFpg62emfdNyqtQ7POKL0zLnDWNV-2sp9GBgpqhV6tN0fROJTeG49MjeZ1q92vro-nj3gJPZpWnXXWS9v019FFCZXXw2O_it6nj6vJU7x4mc0n40UsKWdtnGlQsuQFJgngsFoDA4oZ5ylIoKDWmCdKrWkic5aQQmaqSAupOVEpACWSXUV3h7-Nsz-d9q3Y2M4FS17QNCeUJgyTQJEDJYM973QpGme24HpBsNgHLfZBi33Q4hh00NweNEZrfeI54XmWJ-wfk4F75Q</recordid><startdate>20210901</startdate><enddate>20210901</enddate><creator>Zhou, Yan-Jie</creator><creator>Xie, Xiao-Liang</creator><creator>Zhou, Xiao-Hu</creator><creator>Liu, Shi-Qi</creator><creator>Bian, Gui-Bin</creator><creator>Hou, Zeng-Guang</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-6227-4811</orcidid><orcidid>https://orcid.org/0000-0001-7191-4449</orcidid><orcidid>https://orcid.org/0000-0002-7602-4848</orcidid><orcidid>https://orcid.org/0000-0003-4708-2245</orcidid><orcidid>https://orcid.org/0000-0002-1534-5840</orcidid></search><sort><creationdate>20210901</creationdate><title>A Real-Time Multifunctional Framework for Guidewire Morphological and Positional Analysis in Interventional X-Ray Fluoroscopy</title><author>Zhou, Yan-Jie ; Xie, Xiao-Liang ; Zhou, Xiao-Hu ; Liu, Shi-Qi ; Bian, Gui-Bin ; Hou, Zeng-Guang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Catheters</topic><topic>Contrast agents</topic><topic>Convolution</topic><topic>Decoding</topic><topic>Deep learning</topic><topic>Elongated structure</topic><topic>Feature extraction</topic><topic>Fluoroscopy</topic><topic>Formability</topic><topic>guidewire</topic><topic>Localization</topic><topic>Morphology</topic><topic>Pixels</topic><topic>Qualitative analysis</topic><topic>Radiation dosage</topic><topic>Real time</topic><topic>Real-time systems</topic><topic>robot-assisted intervention</topic><topic>Robots</topic><topic>Segmentation</topic><topic>segmentation and localization</topic><topic>Task analysis</topic><topic>X-ray fluoroscopy</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Yan-Jie</creatorcontrib><creatorcontrib>Xie, Xiao-Liang</creatorcontrib><creatorcontrib>Zhou, Xiao-Hu</creatorcontrib><creatorcontrib>Liu, Shi-Qi</creatorcontrib><creatorcontrib>Bian, Gui-Bin</creatorcontrib><creatorcontrib>Hou, Zeng-Guang</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Xplore (Online service)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology 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><jtitle>IEEE transactions on cognitive and developmental systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhou, Yan-Jie</au><au>Xie, Xiao-Liang</au><au>Zhou, Xiao-Hu</au><au>Liu, Shi-Qi</au><au>Bian, Gui-Bin</au><au>Hou, Zeng-Guang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Real-Time Multifunctional Framework for Guidewire Morphological and Positional Analysis in Interventional X-Ray Fluoroscopy</atitle><jtitle>IEEE transactions on cognitive and developmental systems</jtitle><stitle>TCDS</stitle><date>2021-09-01</date><risdate>2021</risdate><volume>13</volume><issue>3</issue><spage>657</spage><epage>667</epage><pages>657-667</pages><issn>2379-8920</issn><eissn>2379-8939</eissn><coden>ITCDA4</coden><abstract>In endovascular and cardiovascular surgery, real-time guidewire morphological and positional analysis is an important prerequisite for robot-assisted intervention, which can aid in reducing the radiation dose, contrast agent, and procedure time. Nevertheless, this task often comes with the challenge of the deformable elongated structure with low contrast in noisy X-ray fluoroscopy. In this article, a real-time multifunctional framework is proposed for fully automatic guidewire morphological and positional analysis, namely, guidewire segmentation, endpoint localization, and angle measurement. In the first stage, the proposed fast attention recurrent network (FAR-Net) achieves real-time and accurate guidewire segmentation. In the second stage, the endpoint localization and angle measurement algorithm robustly obtain subpixel-level endpoint and angle of the guidewire tip. Quantitative and qualitative evaluations on the MSGSeg data set consisting of 180 X-ray sequences from 30 patients demonstrate that the proposed framework significantly outperforms simpler baselines as well as the best previously published result for this task. The proposed approach reached &lt;inline-formula&gt; &lt;tex-math notation="LaTeX"&gt;{F_{1}} &lt;/tex-math&gt;&lt;/inline-formula&gt;-Score of 0.938, mean distance error of 0.596 pixels, endpoint localization and angle measurement accuracy of 97.8% and 95.3%, and an inference rate of approximately 13 FPS. The proposed framework not only addresses the issues of extreme class imbalance and misclassified examples but also meets the real-time requirements, achieving state-of-the-art performance. The proposed approach is promising for integration into robotic navigation frameworks to various intravascular applications, enabling robotic-assisted intervention.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TCDS.2020.3023952</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-6227-4811</orcidid><orcidid>https://orcid.org/0000-0001-7191-4449</orcidid><orcidid>https://orcid.org/0000-0002-7602-4848</orcidid><orcidid>https://orcid.org/0000-0003-4708-2245</orcidid><orcidid>https://orcid.org/0000-0002-1534-5840</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 2379-8920
ispartof IEEE transactions on cognitive and developmental systems, 2021-09, Vol.13 (3), p.657-667
issn 2379-8920
2379-8939
language eng
recordid cdi_crossref_primary_10_1109_TCDS_2020_3023952
source IEEE Xplore (Online service)
subjects Algorithms
Catheters
Contrast agents
Convolution
Decoding
Deep learning
Elongated structure
Feature extraction
Fluoroscopy
Formability
guidewire
Localization
Morphology
Pixels
Qualitative analysis
Radiation dosage
Real time
Real-time systems
robot-assisted intervention
Robots
Segmentation
segmentation and localization
Task analysis
X-ray fluoroscopy
title A Real-Time Multifunctional Framework for Guidewire Morphological and Positional Analysis in Interventional X-Ray Fluoroscopy
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T13%3A38%3A05IST&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=A%20Real-Time%20Multifunctional%20Framework%20for%20Guidewire%20Morphological%20and%20Positional%20Analysis%20in%20Interventional%20X-Ray%20Fluoroscopy&rft.jtitle=IEEE%20transactions%20on%20cognitive%20and%20developmental%20systems&rft.au=Zhou,%20Yan-Jie&rft.date=2021-09-01&rft.volume=13&rft.issue=3&rft.spage=657&rft.epage=667&rft.pages=657-667&rft.issn=2379-8920&rft.eissn=2379-8939&rft.coden=ITCDA4&rft_id=info:doi/10.1109/TCDS.2020.3023952&rft_dat=%3Cproquest_cross%3E2571224301%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c293t-6eadcf98014a0c29ba3a203995aca2adb094ddb24c73418c6d858ce91d5aa21c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2571224301&rft_id=info:pmid/&rft_ieee_id=9197674&rfr_iscdi=true