Loading…

Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients

•Atlas-based method for contouring heart substructures on breast radiotherapy CT.•Excellent agreement between automatic and manual contours for most patients.•Dice similarity coefficient for LAD was low (0.06) because a narrow, long structure.•Doses derived from automatic and manual contours agree w...

Full description

Saved in:
Bibliographic Details
Published in:Physics and imaging in radiation oncology 2021-07, Vol.19, p.138-144
Main Authors: Jung, Jae Won, Mille, Matthew M., Ky, Bonnie, Kenworthy, Walter, Lee, Choonik, Yeom, Yeon Soo, Kwag, Aaron, Bosch, Walter, MacDonald, Shannon, Cahlon, Oren, Bekelman, Justin E., Lee, Choonsik
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-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3
cites cdi_FETCH-LOGICAL-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3
container_end_page 144
container_issue
container_start_page 138
container_title Physics and imaging in radiation oncology
container_volume 19
creator Jung, Jae Won
Mille, Matthew M.
Ky, Bonnie
Kenworthy, Walter
Lee, Choonik
Yeom, Yeon Soo
Kwag, Aaron
Bosch, Walter
MacDonald, Shannon
Cahlon, Oren
Bekelman, Justin E.
Lee, Choonsik
description •Atlas-based method for contouring heart substructures on breast radiotherapy CT.•Excellent agreement between automatic and manual contours for most patients.•Dice similarity coefficient for LAD was low (0.06) because a narrow, long structure.•Doses derived from automatic and manual contours agree within observer variability.•For left breast treatment, right ventricle and LAD dose most senstive to contour shift. Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research. We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose. The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively. Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications.
doi_str_mv 10.1016/j.phro.2021.08.005
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_147ccc395194418b9200d1177a23db5c</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S2405631621000506</els_id><doaj_id>oai_doaj_org_article_147ccc395194418b9200d1177a23db5c</doaj_id><sourcerecordid>2569620280</sourcerecordid><originalsourceid>FETCH-LOGICAL-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3</originalsourceid><addsrcrecordid>eNp9kk1r3DAQhk1paUKaP5BD0bGXdfVh-QNKIYSkDQR6ac5iJI13tdiWK8kLe-pfr7ZOQ3LpSWLmnUczmrcorhgtGWX1530574IvOeWspG1JqXxTnPOKyk0tWP32xf2suIxxTynlTSekoO-LM1FVrWxYd178vp7nwRlIzk_E9wQmAkvyYw4YEnE74pTW5Ihp5y3pfSB4gGHJ0WlLDATrIEtTWExaAhLrI0YS0KA7oCX6SHRAiIkEsM6nHQaYj2TO5RkdPxTvehgiXj6dF8Xj3e3Pm--bhx_f7m-uHzZGcpY2DHlvwDS2BglS5EFAtgaZrmzVgObMIgrecIp9BVSjkZpDp4U2lnc1R3FR3K9c62Gv5uBGCEflwam_AR-2CkKeeUDFqsYYIzrJuqpire44pZaxpgEurJYms76urHnRI1qT5wgwvIK-zkxup7b-oFrRNW1HM-DTEyD4XwvGpEYXDQ4DTOiXqLisc9OUtycpX6Um-BgD9s_PMKpORlB5mmwEdTKCoq3KRshFH182-Fzyb-1Z8GUVYP7yg8OgosnrMGhdXlzKf-L-x_8DwB7JDQ</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2569620280</pqid></control><display><type>article</type><title>Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients</title><source>Open Access: PubMed Central</source><creator>Jung, Jae Won ; Mille, Matthew M. ; Ky, Bonnie ; Kenworthy, Walter ; Lee, Choonik ; Yeom, Yeon Soo ; Kwag, Aaron ; Bosch, Walter ; MacDonald, Shannon ; Cahlon, Oren ; Bekelman, Justin E. ; Lee, Choonsik</creator><creatorcontrib>Jung, Jae Won ; Mille, Matthew M. ; Ky, Bonnie ; Kenworthy, Walter ; Lee, Choonik ; Yeom, Yeon Soo ; Kwag, Aaron ; Bosch, Walter ; MacDonald, Shannon ; Cahlon, Oren ; Bekelman, Justin E. ; Lee, Choonsik ; on behalf of the RadComp Consortium ; RadComp Consortium</creatorcontrib><description>•Atlas-based method for contouring heart substructures on breast radiotherapy CT.•Excellent agreement between automatic and manual contours for most patients.•Dice similarity coefficient for LAD was low (0.06) because a narrow, long structure.•Doses derived from automatic and manual contours agree within observer variability.•For left breast treatment, right ventricle and LAD dose most senstive to contour shift. Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research. We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose. The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively. Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications.</description><identifier>ISSN: 2405-6316</identifier><identifier>EISSN: 2405-6316</identifier><identifier>DOI: 10.1016/j.phro.2021.08.005</identifier><identifier>PMID: 34485719</identifier><language>eng</language><publisher>Netherlands: Elsevier B.V</publisher><subject>Automatic segmentation ; Breast cancer ; Cardiac structures ; Late effects ; Original ; Radiotherapy</subject><ispartof>Physics and imaging in radiation oncology, 2021-07, Vol.19, p.138-144</ispartof><rights>2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3</citedby><cites>FETCH-LOGICAL-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8397890/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8397890/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,724,777,781,882,27905,27906,53772,53774</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/34485719$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Jung, Jae Won</creatorcontrib><creatorcontrib>Mille, Matthew M.</creatorcontrib><creatorcontrib>Ky, Bonnie</creatorcontrib><creatorcontrib>Kenworthy, Walter</creatorcontrib><creatorcontrib>Lee, Choonik</creatorcontrib><creatorcontrib>Yeom, Yeon Soo</creatorcontrib><creatorcontrib>Kwag, Aaron</creatorcontrib><creatorcontrib>Bosch, Walter</creatorcontrib><creatorcontrib>MacDonald, Shannon</creatorcontrib><creatorcontrib>Cahlon, Oren</creatorcontrib><creatorcontrib>Bekelman, Justin E.</creatorcontrib><creatorcontrib>Lee, Choonsik</creatorcontrib><creatorcontrib>on behalf of the RadComp Consortium</creatorcontrib><creatorcontrib>RadComp Consortium</creatorcontrib><title>Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients</title><title>Physics and imaging in radiation oncology</title><addtitle>Phys Imaging Radiat Oncol</addtitle><description>•Atlas-based method for contouring heart substructures on breast radiotherapy CT.•Excellent agreement between automatic and manual contours for most patients.•Dice similarity coefficient for LAD was low (0.06) because a narrow, long structure.•Doses derived from automatic and manual contours agree within observer variability.•For left breast treatment, right ventricle and LAD dose most senstive to contour shift. Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research. We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose. The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively. Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications.</description><subject>Automatic segmentation</subject><subject>Breast cancer</subject><subject>Cardiac structures</subject><subject>Late effects</subject><subject>Original</subject><subject>Radiotherapy</subject><issn>2405-6316</issn><issn>2405-6316</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNp9kk1r3DAQhk1paUKaP5BD0bGXdfVh-QNKIYSkDQR6ac5iJI13tdiWK8kLe-pfr7ZOQ3LpSWLmnUczmrcorhgtGWX1530574IvOeWspG1JqXxTnPOKyk0tWP32xf2suIxxTynlTSekoO-LM1FVrWxYd178vp7nwRlIzk_E9wQmAkvyYw4YEnE74pTW5Ihp5y3pfSB4gGHJ0WlLDATrIEtTWExaAhLrI0YS0KA7oCX6SHRAiIkEsM6nHQaYj2TO5RkdPxTvehgiXj6dF8Xj3e3Pm--bhx_f7m-uHzZGcpY2DHlvwDS2BglS5EFAtgaZrmzVgObMIgrecIp9BVSjkZpDp4U2lnc1R3FR3K9c62Gv5uBGCEflwam_AR-2CkKeeUDFqsYYIzrJuqpire44pZaxpgEurJYms76urHnRI1qT5wgwvIK-zkxup7b-oFrRNW1HM-DTEyD4XwvGpEYXDQ4DTOiXqLisc9OUtycpX6Um-BgD9s_PMKpORlB5mmwEdTKCoq3KRshFH182-Fzyb-1Z8GUVYP7yg8OgosnrMGhdXlzKf-L-x_8DwB7JDQ</recordid><startdate>20210701</startdate><enddate>20210701</enddate><creator>Jung, Jae Won</creator><creator>Mille, Matthew M.</creator><creator>Ky, Bonnie</creator><creator>Kenworthy, Walter</creator><creator>Lee, Choonik</creator><creator>Yeom, Yeon Soo</creator><creator>Kwag, Aaron</creator><creator>Bosch, Walter</creator><creator>MacDonald, Shannon</creator><creator>Cahlon, Oren</creator><creator>Bekelman, Justin E.</creator><creator>Lee, Choonsik</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>6I.</scope><scope>AAFTH</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20210701</creationdate><title>Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients</title><author>Jung, Jae Won ; Mille, Matthew M. ; Ky, Bonnie ; Kenworthy, Walter ; Lee, Choonik ; Yeom, Yeon Soo ; Kwag, Aaron ; Bosch, Walter ; MacDonald, Shannon ; Cahlon, Oren ; Bekelman, Justin E. ; Lee, Choonsik</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Automatic segmentation</topic><topic>Breast cancer</topic><topic>Cardiac structures</topic><topic>Late effects</topic><topic>Original</topic><topic>Radiotherapy</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jung, Jae Won</creatorcontrib><creatorcontrib>Mille, Matthew M.</creatorcontrib><creatorcontrib>Ky, Bonnie</creatorcontrib><creatorcontrib>Kenworthy, Walter</creatorcontrib><creatorcontrib>Lee, Choonik</creatorcontrib><creatorcontrib>Yeom, Yeon Soo</creatorcontrib><creatorcontrib>Kwag, Aaron</creatorcontrib><creatorcontrib>Bosch, Walter</creatorcontrib><creatorcontrib>MacDonald, Shannon</creatorcontrib><creatorcontrib>Cahlon, Oren</creatorcontrib><creatorcontrib>Bekelman, Justin E.</creatorcontrib><creatorcontrib>Lee, Choonsik</creatorcontrib><creatorcontrib>on behalf of the RadComp Consortium</creatorcontrib><creatorcontrib>RadComp Consortium</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>Open Access: DOAJ - Directory of Open Access Journals</collection><jtitle>Physics and imaging in radiation oncology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jung, Jae Won</au><au>Mille, Matthew M.</au><au>Ky, Bonnie</au><au>Kenworthy, Walter</au><au>Lee, Choonik</au><au>Yeom, Yeon Soo</au><au>Kwag, Aaron</au><au>Bosch, Walter</au><au>MacDonald, Shannon</au><au>Cahlon, Oren</au><au>Bekelman, Justin E.</au><au>Lee, Choonsik</au><aucorp>on behalf of the RadComp Consortium</aucorp><aucorp>RadComp Consortium</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients</atitle><jtitle>Physics and imaging in radiation oncology</jtitle><addtitle>Phys Imaging Radiat Oncol</addtitle><date>2021-07-01</date><risdate>2021</risdate><volume>19</volume><spage>138</spage><epage>144</epage><pages>138-144</pages><issn>2405-6316</issn><eissn>2405-6316</eissn><abstract>•Atlas-based method for contouring heart substructures on breast radiotherapy CT.•Excellent agreement between automatic and manual contours for most patients.•Dice similarity coefficient for LAD was low (0.06) because a narrow, long structure.•Doses derived from automatic and manual contours agree within observer variability.•For left breast treatment, right ventricle and LAD dose most senstive to contour shift. Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research. We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose. The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively. Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications.</abstract><cop>Netherlands</cop><pub>Elsevier B.V</pub><pmid>34485719</pmid><doi>10.1016/j.phro.2021.08.005</doi><tpages>7</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2405-6316
ispartof Physics and imaging in radiation oncology, 2021-07, Vol.19, p.138-144
issn 2405-6316
2405-6316
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_147ccc395194418b9200d1177a23db5c
source Open Access: PubMed Central
subjects Automatic segmentation
Breast cancer
Cardiac structures
Late effects
Original
Radiotherapy
title Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T09%3A46%3A52IST&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=Application%20of%20an%20automatic%20segmentation%20method%20for%20evaluating%20cardiac%20structure%20doses%20received%20by%20breast%20radiotherapy%20patients&rft.jtitle=Physics%20and%20imaging%20in%20radiation%20oncology&rft.au=Jung,%20Jae%20Won&rft.aucorp=on%20behalf%20of%20the%20RadComp%20Consortium&rft.date=2021-07-01&rft.volume=19&rft.spage=138&rft.epage=144&rft.pages=138-144&rft.issn=2405-6316&rft.eissn=2405-6316&rft_id=info:doi/10.1016/j.phro.2021.08.005&rft_dat=%3Cproquest_doaj_%3E2569620280%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c521t-1e2fcac7d6a5a53793a58ce1b4d47ab21dee32720ef4a0bec5b2a9b3bcd2962e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2569620280&rft_id=info:pmid/34485719&rfr_iscdi=true