Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery
Intra-operative target pose estimation is fundamental in minimally invasive surgery (MIS) to guiding surgical robots. This task can be fulfilled by the 2-D/3-D rigid registration, which aligns the anatomical structures between intra-operative 2-D fluoroscopy and the pre-operative 3-D computed tomogr...
Saved in:
Published in: | Micromachines (Basel) 2021-07, Vol.12 (7), p.844 |
---|---|
Main Authors: | , , , , , , , |
Format: | Article |
Language: | eng |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
recordid |
cdi_doaj_primary_oai_doaj_org_article_3fadaa4f7207424f9b272aecca33b27b |
---|---|
title |
Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery |
format |
Article |
creator |
An, Zhou Ma, Honghai Liu, Lilu Wang, Yue Lu, Haojian Zhou, Chunlin Xiong, Rong Hu, Jian |
subjects |
2-D/3-D registration Accuracy Algorithms Computed tomography Datasets deep learning Efficiency Failure rates Fluoroscopy Image reconstruction Laparoscopy Machine learning Methods multi-view Optimization reconstruction Registration rigid Robotic surgery Three dimensional imaging |
ispartof |
Micromachines (Basel), 2021-07, Vol.12 (7), p.844 |
description |
Intra-operative target pose estimation is fundamental in minimally invasive surgery (MIS) to guiding surgical robots. This task can be fulfilled by the 2-D/3-D rigid registration, which aligns the anatomical structures between intra-operative 2-D fluoroscopy and the pre-operative 3-D computed tomography (CT) with annotated target information. Although this technique has been researched for decades, it is still challenging to achieve accuracy, robustness and efficiency simultaneously. In this paper, a novel orthogonal-view 2-D/3-D rigid registration framework is proposed which combines the dense reconstruction based on deep learning and the GPU-accelerated 3-D/3-D rigid registration. First, we employ the X2CT-GAN to reconstruct a target CT from two orthogonal fluoroscopy images. After that, the generated target CT and pre-operative CT are input into the 3-D/3-D rigid registration part, which potentially needs a few iterations to converge the global optima. For further efficiency improvement, we make the 3-D/3-D registration algorithm parallel and apply a GPU to accelerate this part. For evaluation, a novel tool is employed to preprocess the public head CT dataset CQ500 and a CT-DRR dataset is presented as the benchmark. The proposed method achieves 1.65 ± 1.41 mm in mean target registration error(mTRE), 20% in the gross failure rate(GFR) and 1.8 s in running time. Our method outperforms the state-of-the-art methods in most test cases. It is promising to apply the proposed method in localization and nano manipulation of micro surgical robot for highly precise MIS. |
language |
eng |
source |
Open Access: PubMed Central; Publicly Available Content Database |
identifier |
ISSN: 2072-666X |
fulltext |
fulltext |
issn |
2072-666X 2072-666X |
url |
http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-05-27T17%3A17%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Robust%20Orthogonal-View%202-D/3-D%20Rigid%20Registration%20for%20Minimally%20Invasive%20Surgery&rft.jtitle=Micromachines%20(Basel)&rft.au=An,%20Zhou&rft.date=2021-07-20&rft.volume=12&rft.issue=7&rft.spage=844&rft.pages=844-&rft.issn=2072-666X&rft.eissn=2072-666X&rft_id=info:doi/10.3390/mi12070844&rft_dat=%3Cproquest_doaj_%3E2559425412%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c449t-283e5545be07d24a19c4ed9f3340596a8e99eb23f239026f2c88bbef4b0be0823%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2554611567&rft_id=info:pmid/34357254 |
container_title |
Micromachines (Basel) |
container_volume |
12 |
container_issue |
7 |
container_start_page |
844 |
container_end_page |
|
fullrecord |
<record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_3fadaa4f7207424f9b272aecca33b27b</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_3fadaa4f7207424f9b272aecca33b27b</doaj_id><sourcerecordid>2559425412</sourcerecordid><originalsourceid>FETCH-LOGICAL-c449t-283e5545be07d24a19c4ed9f3340596a8e99eb23f239026f2c88bbef4b0be0823</originalsourceid><addsrcrecordid>eNpdUV1L5DAUDbKior74Cwq-LAvVNB9t8yIsuuqAizJ-4FtI0puaodO4STsy_96MI66ah5tD7snh3HMROijwEaUCH89dQXCFa8Y20E5CJC_L8vHHJ7yN9mOc4XSqSqSyhbYpo7winO2gm6nXYxyy6zA8-db3qssfHLxkJD87pvlZNnWta7IptC4OQQ3O95n1IfvrejdXXbfMJv1CRbeA7HYMLYTlHtq0qouw_37vovvzP3enl_nV9cXk9PdVbhgTQ05qCpwzrgFXDWGqEIZBIyylDHNRqhqEAE2oJWlIUlpi6lprsEzj9KUmdBdN1rqNVzP5HJKdsJReOfn24EMrVRic6UBSqxqlmK1SJIwwKzSpiAJjFKUJ6qR1stZ6HvUcGgN9mrX7Ivq107sn2fqFrCmmolyZ-fkuEPy_EeIg5y4a6DrVgx-jJJwLlvIuVtTDb9SZH0PK_Y3FyqLgZZVYv9YsE3yMAeyHmQLL1d7l_73TV3SOnXA</addsrcrecordid><sourcetype>Open Website</sourcetype><isCDI>true</isCDI><recordtype>article</recordtype><pqid>2554611567</pqid></control><display><type>article</type><title>Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery</title><source>Open Access: PubMed Central</source><source>Publicly Available Content Database</source><creator>An, Zhou ; Ma, Honghai ; Liu, Lilu ; Wang, Yue ; Lu, Haojian ; Zhou, Chunlin ; Xiong, Rong ; Hu, Jian</creator><creatorcontrib>An, Zhou ; Ma, Honghai ; Liu, Lilu ; Wang, Yue ; Lu, Haojian ; Zhou, Chunlin ; Xiong, Rong ; Hu, Jian</creatorcontrib><description>Intra-operative target pose estimation is fundamental in minimally invasive surgery (MIS) to guiding surgical robots. This task can be fulfilled by the 2-D/3-D rigid registration, which aligns the anatomical structures between intra-operative 2-D fluoroscopy and the pre-operative 3-D computed tomography (CT) with annotated target information. Although this technique has been researched for decades, it is still challenging to achieve accuracy, robustness and efficiency simultaneously. In this paper, a novel orthogonal-view 2-D/3-D rigid registration framework is proposed which combines the dense reconstruction based on deep learning and the GPU-accelerated 3-D/3-D rigid registration. First, we employ the X2CT-GAN to reconstruct a target CT from two orthogonal fluoroscopy images. After that, the generated target CT and pre-operative CT are input into the 3-D/3-D rigid registration part, which potentially needs a few iterations to converge the global optima. For further efficiency improvement, we make the 3-D/3-D registration algorithm parallel and apply a GPU to accelerate this part. For evaluation, a novel tool is employed to preprocess the public head CT dataset CQ500 and a CT-DRR dataset is presented as the benchmark. The proposed method achieves 1.65 ± 1.41 mm in mean target registration error(mTRE), 20% in the gross failure rate(GFR) and 1.8 s in running time. Our method outperforms the state-of-the-art methods in most test cases. It is promising to apply the proposed method in localization and nano manipulation of micro surgical robot for highly precise MIS.</description><identifier>ISSN: 2072-666X</identifier><identifier>EISSN: 2072-666X</identifier><identifier>DOI: 10.3390/mi12070844</identifier><identifier>PMID: 34357254</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>2-D/3-D registration ; Accuracy ; Algorithms ; Computed tomography ; Datasets ; deep learning ; Efficiency ; Failure rates ; Fluoroscopy ; Image reconstruction ; Laparoscopy ; Machine learning ; Methods ; multi-view ; Optimization ; reconstruction ; Registration ; rigid ; Robotic surgery ; Three dimensional imaging</subject><ispartof>Micromachines (Basel), 2021-07, Vol.12 (7), p.844</ispartof><rights>2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c449t-283e5545be07d24a19c4ed9f3340596a8e99eb23f239026f2c88bbef4b0be0823</citedby><cites>FETCH-LOGICAL-c449t-283e5545be07d24a19c4ed9f3340596a8e99eb23f239026f2c88bbef4b0be0823</cites><orcidid>0000-0002-1393-3040 ; 0000-0003-2937-0702</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2554611567/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2554611567?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,315,734,787,791,892,25799,27985,27986,37077,37078,44955,54176,54178,76120</link.rule.ids></links><search><creatorcontrib>An, Zhou</creatorcontrib><creatorcontrib>Ma, Honghai</creatorcontrib><creatorcontrib>Liu, Lilu</creatorcontrib><creatorcontrib>Wang, Yue</creatorcontrib><creatorcontrib>Lu, Haojian</creatorcontrib><creatorcontrib>Zhou, Chunlin</creatorcontrib><creatorcontrib>Xiong, Rong</creatorcontrib><creatorcontrib>Hu, Jian</creatorcontrib><title>Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery</title><title>Micromachines (Basel)</title><description>Intra-operative target pose estimation is fundamental in minimally invasive surgery (MIS) to guiding surgical robots. This task can be fulfilled by the 2-D/3-D rigid registration, which aligns the anatomical structures between intra-operative 2-D fluoroscopy and the pre-operative 3-D computed tomography (CT) with annotated target information. Although this technique has been researched for decades, it is still challenging to achieve accuracy, robustness and efficiency simultaneously. In this paper, a novel orthogonal-view 2-D/3-D rigid registration framework is proposed which combines the dense reconstruction based on deep learning and the GPU-accelerated 3-D/3-D rigid registration. First, we employ the X2CT-GAN to reconstruct a target CT from two orthogonal fluoroscopy images. After that, the generated target CT and pre-operative CT are input into the 3-D/3-D rigid registration part, which potentially needs a few iterations to converge the global optima. For further efficiency improvement, we make the 3-D/3-D registration algorithm parallel and apply a GPU to accelerate this part. For evaluation, a novel tool is employed to preprocess the public head CT dataset CQ500 and a CT-DRR dataset is presented as the benchmark. The proposed method achieves 1.65 ± 1.41 mm in mean target registration error(mTRE), 20% in the gross failure rate(GFR) and 1.8 s in running time. Our method outperforms the state-of-the-art methods in most test cases. It is promising to apply the proposed method in localization and nano manipulation of micro surgical robot for highly precise MIS.</description><subject>2-D/3-D registration</subject><subject>Accuracy</subject><subject>Algorithms</subject><subject>Computed tomography</subject><subject>Datasets</subject><subject>deep learning</subject><subject>Efficiency</subject><subject>Failure rates</subject><subject>Fluoroscopy</subject><subject>Image reconstruction</subject><subject>Laparoscopy</subject><subject>Machine learning</subject><subject>Methods</subject><subject>multi-view</subject><subject>Optimization</subject><subject>reconstruction</subject><subject>Registration</subject><subject>rigid</subject><subject>Robotic surgery</subject><subject>Three dimensional imaging</subject><issn>2072-666X</issn><issn>2072-666X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpdUV1L5DAUDbKior74Cwq-LAvVNB9t8yIsuuqAizJ-4FtI0puaodO4STsy_96MI66ah5tD7snh3HMROijwEaUCH89dQXCFa8Y20E5CJC_L8vHHJ7yN9mOc4XSqSqSyhbYpo7winO2gm6nXYxyy6zA8-db3qssfHLxkJD87pvlZNnWta7IptC4OQQ3O95n1IfvrejdXXbfMJv1CRbeA7HYMLYTlHtq0qouw_37vovvzP3enl_nV9cXk9PdVbhgTQ05qCpwzrgFXDWGqEIZBIyylDHNRqhqEAE2oJWlIUlpi6lprsEzj9KUmdBdN1rqNVzP5HJKdsJReOfn24EMrVRic6UBSqxqlmK1SJIwwKzSpiAJjFKUJ6qR1stZ6HvUcGgN9mrX7Ivq107sn2fqFrCmmolyZ-fkuEPy_EeIg5y4a6DrVgx-jJJwLlvIuVtTDb9SZH0PK_Y3FyqLgZZVYv9YsE3yMAeyHmQLL1d7l_73TV3SOnXA</recordid><startdate>20210720</startdate><enddate>20210720</enddate><creator>An, Zhou</creator><creator>Ma, Honghai</creator><creator>Liu, Lilu</creator><creator>Wang, Yue</creator><creator>Lu, Haojian</creator><creator>Zhou, Chunlin</creator><creator>Xiong, Rong</creator><creator>Hu, Jian</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>L7M</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-1393-3040</orcidid><orcidid>https://orcid.org/0000-0003-2937-0702</orcidid></search><sort><creationdate>20210720</creationdate><title>Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery</title><author>An, Zhou ; Ma, Honghai ; Liu, Lilu ; Wang, Yue ; Lu, Haojian ; Zhou, Chunlin ; Xiong, Rong ; Hu, Jian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c449t-283e5545be07d24a19c4ed9f3340596a8e99eb23f239026f2c88bbef4b0be0823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>2-D/3-D registration</topic><topic>Accuracy</topic><topic>Algorithms</topic><topic>Computed tomography</topic><topic>Datasets</topic><topic>deep learning</topic><topic>Efficiency</topic><topic>Failure rates</topic><topic>Fluoroscopy</topic><topic>Image reconstruction</topic><topic>Laparoscopy</topic><topic>Machine learning</topic><topic>Methods</topic><topic>multi-view</topic><topic>Optimization</topic><topic>reconstruction</topic><topic>Registration</topic><topic>rigid</topic><topic>Robotic surgery</topic><topic>Three dimensional imaging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>An, Zhou</creatorcontrib><creatorcontrib>Ma, Honghai</creatorcontrib><creatorcontrib>Liu, Lilu</creatorcontrib><creatorcontrib>Wang, Yue</creatorcontrib><creatorcontrib>Lu, Haojian</creatorcontrib><creatorcontrib>Zhou, Chunlin</creatorcontrib><creatorcontrib>Xiong, Rong</creatorcontrib><creatorcontrib>Hu, Jian</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Engineering Research Database</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering collection</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>Open Access: DOAJ - Directory of Open Access Journals</collection><jtitle>Micromachines (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>An, Zhou</au><au>Ma, Honghai</au><au>Liu, Lilu</au><au>Wang, Yue</au><au>Lu, Haojian</au><au>Zhou, Chunlin</au><au>Xiong, Rong</au><au>Hu, Jian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robust Orthogonal-View 2-D/3-D Rigid Registration for Minimally Invasive Surgery</atitle><jtitle>Micromachines (Basel)</jtitle><date>2021-07-20</date><risdate>2021</risdate><volume>12</volume><issue>7</issue><spage>844</spage><pages>844-</pages><issn>2072-666X</issn><eissn>2072-666X</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>Intra-operative target pose estimation is fundamental in minimally invasive surgery (MIS) to guiding surgical robots. This task can be fulfilled by the 2-D/3-D rigid registration, which aligns the anatomical structures between intra-operative 2-D fluoroscopy and the pre-operative 3-D computed tomography (CT) with annotated target information. Although this technique has been researched for decades, it is still challenging to achieve accuracy, robustness and efficiency simultaneously. In this paper, a novel orthogonal-view 2-D/3-D rigid registration framework is proposed which combines the dense reconstruction based on deep learning and the GPU-accelerated 3-D/3-D rigid registration. First, we employ the X2CT-GAN to reconstruct a target CT from two orthogonal fluoroscopy images. After that, the generated target CT and pre-operative CT are input into the 3-D/3-D rigid registration part, which potentially needs a few iterations to converge the global optima. For further efficiency improvement, we make the 3-D/3-D registration algorithm parallel and apply a GPU to accelerate this part. For evaluation, a novel tool is employed to preprocess the public head CT dataset CQ500 and a CT-DRR dataset is presented as the benchmark. The proposed method achieves 1.65 ± 1.41 mm in mean target registration error(mTRE), 20% in the gross failure rate(GFR) and 1.8 s in running time. Our method outperforms the state-of-the-art methods in most test cases. It is promising to apply the proposed method in localization and nano manipulation of micro surgical robot for highly precise MIS.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>34357254</pmid><doi>10.3390/mi12070844</doi><orcidid>https://orcid.org/0000-0002-1393-3040</orcidid><orcidid>https://orcid.org/0000-0003-2937-0702</orcidid><oa>free_for_read</oa></addata></record> |