Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study
•Segmentation algorithms do not work well on unhealthy lungs as COVID-19 ones.•An Atlas for segmentation of COVID-19 lungs’ patients was developed and validated.•Lung histograms parameters could impact the clinical management of COVID-19 patients.•Lung densitometry characterization method integrated...
Gespeichert in:
| Veröffentlicht in: | Physica medica 2022-08, Vol.100, p.142-152 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 152 |
|---|---|
| container_issue | |
| container_start_page | 142 |
| container_title | Physica medica |
| container_volume | 100 |
| creator | Mori, Martina Alborghetti, Lisa Palumbo, Diego Broggi, Sara Raspanti, Davide Rovere Querini, Patrizia Del Vecchio, Antonella De Cobelli, Francesco Fiorino, Claudio |
| description | •Segmentation algorithms do not work well on unhealthy lungs as COVID-19 ones.•An Atlas for segmentation of COVID-19 lungs’ patients was developed and validated.•Lung histograms parameters could impact the clinical management of COVID-19 patients.•Lung densitometry characterization method integrated to segmentation was implemented.
To develop and validate an automated segmentation tool for COVID-19 lung CTs. To combine it with densitometry information in identifying Aerated, Intermediate and Consolidated Volumes in admission (CT1) and follow up CT (CT3).
An Atlas was trained on manually segmented CT1 of 250 patients and validated on 10 CT1 of the training group, 10 new CT1 and 10 CT3, by comparing DICE index between automatic (AUTO), automatic-corrected (AUTOMAN) and manual (MAN) contours. A previously developed automatic method was applied on HU lung density histograms to quantify Aerated, Intermediate and Consolidated Volumes. Volumes of subregions in validation CT1 and CT3 were quantified for each method.
In validation CT1/CT3, manual correction of automatic contours was not necessary in 40% of cases. Mean DICE values for both lungs were 0.94 for AUTOVsMAN and 0.96 for AUTOMANVsMAN. Differences between Aerated and Intermediate Volumes quantified with AUTOVsMAN contours were always |
| doi_str_mv | 10.1016/j.ejmp.2022.06.018 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9250926</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1120179722020117</els_id><sourcerecordid>2691049290</sourcerecordid><originalsourceid>FETCH-LOGICAL-c383t-d6d45854b64391346ddbecc16e865ddb390f38e57d24c3335ed401a36dc6c73b3</originalsourceid><addsrcrecordid>eNp9Uctu1DAUjRCIPuAHWHnJggQ_EidGCKmaUqhUqZuC2FmOfSfjkeME2xk0fBMfiUepKrFh5WOfh6_uKYo3BFcEE_5-X8F-nCuKKa0wrzDpnhXnpKV1SQT58TxjQnFJWtGeFRcx7jFmlDbNy-KMNR0TnLfnxZ-r5FQsexXBILf4AUUYRvBJJTt5pKextz5Tv2zaIbWkacyERgZ8tPkCKRyR3qmgdIJgf68u69Hm_vvtdZ4Dzfkpx8UP6CEo660f3qGDctasUuUN2toQE1Lz7Kx-ClDITX6waTHWK4diBsdXxYutchFeP56Xxbebzw-br-Xd_ZfbzdVdqVnHUmm4qZuuqXteM0FYzY3pQWvCoeNNxkzgLeugaQ2tNWOsAVNjohg3muuW9eyy-LTmzks_gtF5_qCcnIMdVTjKSVn5L-PtTg7TQQraYEF5Dnj7GBCmnwvEJEcbNTinPExLlJQLgmtBBc5Sukp1mGIMsH36hmB5qlnu5almeapZYi5zzdn0cTVB3sLBQpBR5y1rMDaATtJM9n_2v5fotSQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2691049290</pqid></control><display><type>article</type><title>Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study</title><source>Elsevier ScienceDirect Journals</source><creator>Mori, Martina ; Alborghetti, Lisa ; Palumbo, Diego ; Broggi, Sara ; Raspanti, Davide ; Rovere Querini, Patrizia ; Del Vecchio, Antonella ; De Cobelli, Francesco ; Fiorino, Claudio</creator><creatorcontrib>Mori, Martina ; Alborghetti, Lisa ; Palumbo, Diego ; Broggi, Sara ; Raspanti, Davide ; Rovere Querini, Patrizia ; Del Vecchio, Antonella ; De Cobelli, Francesco ; Fiorino, Claudio</creatorcontrib><description>•Segmentation algorithms do not work well on unhealthy lungs as COVID-19 ones.•An Atlas for segmentation of COVID-19 lungs’ patients was developed and validated.•Lung histograms parameters could impact the clinical management of COVID-19 patients.•Lung densitometry characterization method integrated to segmentation was implemented.
To develop and validate an automated segmentation tool for COVID-19 lung CTs. To combine it with densitometry information in identifying Aerated, Intermediate and Consolidated Volumes in admission (CT1) and follow up CT (CT3).
An Atlas was trained on manually segmented CT1 of 250 patients and validated on 10 CT1 of the training group, 10 new CT1 and 10 CT3, by comparing DICE index between automatic (AUTO), automatic-corrected (AUTOMAN) and manual (MAN) contours. A previously developed automatic method was applied on HU lung density histograms to quantify Aerated, Intermediate and Consolidated Volumes. Volumes of subregions in validation CT1 and CT3 were quantified for each method.
In validation CT1/CT3, manual correction of automatic contours was not necessary in 40% of cases. Mean DICE values for both lungs were 0.94 for AUTOVsMAN and 0.96 for AUTOMANVsMAN. Differences between Aerated and Intermediate Volumes quantified with AUTOVsMAN contours were always < 6%. Consolidated Volumes showed larger differences (mean: −95 ± 72 cc). If considering AUTOMANVsMAN volumes, differences got further smaller for Aerated and Intermediate, and were drastically reduced for consolidated Volumes (mean: −36 ± 25 cc). The average time for manual correction of automatic lungs contours on CT1 was 5 ± 2 min.
An Atlas for automatic segmentation of lungs in COVID-19 patients was developed and validated. Combined with a previously developed method for lung densitometry characterization, it provides a fast, operator-independent way to extract relevant quantitative parameters with minimal manual intervention.</description><identifier>ISSN: 1120-1797</identifier><identifier>EISSN: 1724-191X</identifier><identifier>DOI: 10.1016/j.ejmp.2022.06.018</identifier><identifier>PMID: 35839667</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Automatic segmentation Atlas-based ; Covid-19 ; Lung segmentation ; Original Paper ; Quantitative imaging computed tomography</subject><ispartof>Physica medica, 2022-08, Vol.100, p.142-152</ispartof><rights>2022 Associazione Italiana di Fisica Medica e Sanitaria</rights><rights>2022 Associazione Italiana di Fisica Medica e Sanitaria. Published by Elsevier Ltd. All rights reserved. 2022 Associazione Italiana di Fisica Medica e Sanitaria</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c383t-d6d45854b64391346ddbecc16e865ddb390f38e57d24c3335ed401a36dc6c73b3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S1120179722020117$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,776,780,881,3537,27901,27902,65306</link.rule.ids></links><search><creatorcontrib>Mori, Martina</creatorcontrib><creatorcontrib>Alborghetti, Lisa</creatorcontrib><creatorcontrib>Palumbo, Diego</creatorcontrib><creatorcontrib>Broggi, Sara</creatorcontrib><creatorcontrib>Raspanti, Davide</creatorcontrib><creatorcontrib>Rovere Querini, Patrizia</creatorcontrib><creatorcontrib>Del Vecchio, Antonella</creatorcontrib><creatorcontrib>De Cobelli, Francesco</creatorcontrib><creatorcontrib>Fiorino, Claudio</creatorcontrib><title>Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study</title><title>Physica medica</title><description>•Segmentation algorithms do not work well on unhealthy lungs as COVID-19 ones.•An Atlas for segmentation of COVID-19 lungs’ patients was developed and validated.•Lung histograms parameters could impact the clinical management of COVID-19 patients.•Lung densitometry characterization method integrated to segmentation was implemented.
To develop and validate an automated segmentation tool for COVID-19 lung CTs. To combine it with densitometry information in identifying Aerated, Intermediate and Consolidated Volumes in admission (CT1) and follow up CT (CT3).
An Atlas was trained on manually segmented CT1 of 250 patients and validated on 10 CT1 of the training group, 10 new CT1 and 10 CT3, by comparing DICE index between automatic (AUTO), automatic-corrected (AUTOMAN) and manual (MAN) contours. A previously developed automatic method was applied on HU lung density histograms to quantify Aerated, Intermediate and Consolidated Volumes. Volumes of subregions in validation CT1 and CT3 were quantified for each method.
In validation CT1/CT3, manual correction of automatic contours was not necessary in 40% of cases. Mean DICE values for both lungs were 0.94 for AUTOVsMAN and 0.96 for AUTOMANVsMAN. Differences between Aerated and Intermediate Volumes quantified with AUTOVsMAN contours were always < 6%. Consolidated Volumes showed larger differences (mean: −95 ± 72 cc). If considering AUTOMANVsMAN volumes, differences got further smaller for Aerated and Intermediate, and were drastically reduced for consolidated Volumes (mean: −36 ± 25 cc). The average time for manual correction of automatic lungs contours on CT1 was 5 ± 2 min.
An Atlas for automatic segmentation of lungs in COVID-19 patients was developed and validated. Combined with a previously developed method for lung densitometry characterization, it provides a fast, operator-independent way to extract relevant quantitative parameters with minimal manual intervention.</description><subject>Automatic segmentation Atlas-based</subject><subject>Covid-19</subject><subject>Lung segmentation</subject><subject>Original Paper</subject><subject>Quantitative imaging computed tomography</subject><issn>1120-1797</issn><issn>1724-191X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp9Uctu1DAUjRCIPuAHWHnJggQ_EidGCKmaUqhUqZuC2FmOfSfjkeME2xk0fBMfiUepKrFh5WOfh6_uKYo3BFcEE_5-X8F-nCuKKa0wrzDpnhXnpKV1SQT58TxjQnFJWtGeFRcx7jFmlDbNy-KMNR0TnLfnxZ-r5FQsexXBILf4AUUYRvBJJTt5pKextz5Tv2zaIbWkacyERgZ8tPkCKRyR3qmgdIJgf68u69Hm_vvtdZ4Dzfkpx8UP6CEo660f3qGDctasUuUN2toQE1Lz7Kx-ClDITX6waTHWK4diBsdXxYutchFeP56Xxbebzw-br-Xd_ZfbzdVdqVnHUmm4qZuuqXteM0FYzY3pQWvCoeNNxkzgLeugaQ2tNWOsAVNjohg3muuW9eyy-LTmzks_gtF5_qCcnIMdVTjKSVn5L-PtTg7TQQraYEF5Dnj7GBCmnwvEJEcbNTinPExLlJQLgmtBBc5Sukp1mGIMsH36hmB5qlnu5almeapZYi5zzdn0cTVB3sLBQpBR5y1rMDaATtJM9n_2v5fotSQ</recordid><startdate>20220801</startdate><enddate>20220801</enddate><creator>Mori, Martina</creator><creator>Alborghetti, Lisa</creator><creator>Palumbo, Diego</creator><creator>Broggi, Sara</creator><creator>Raspanti, Davide</creator><creator>Rovere Querini, Patrizia</creator><creator>Del Vecchio, Antonella</creator><creator>De Cobelli, Francesco</creator><creator>Fiorino, Claudio</creator><general>Elsevier Ltd</general><general>Associazione Italiana di Fisica Medica e Sanitaria. Published by Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20220801</creationdate><title>Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study</title><author>Mori, Martina ; Alborghetti, Lisa ; Palumbo, Diego ; Broggi, Sara ; Raspanti, Davide ; Rovere Querini, Patrizia ; Del Vecchio, Antonella ; De Cobelli, Francesco ; Fiorino, Claudio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c383t-d6d45854b64391346ddbecc16e865ddb390f38e57d24c3335ed401a36dc6c73b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Automatic segmentation Atlas-based</topic><topic>Covid-19</topic><topic>Lung segmentation</topic><topic>Original Paper</topic><topic>Quantitative imaging computed tomography</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mori, Martina</creatorcontrib><creatorcontrib>Alborghetti, Lisa</creatorcontrib><creatorcontrib>Palumbo, Diego</creatorcontrib><creatorcontrib>Broggi, Sara</creatorcontrib><creatorcontrib>Raspanti, Davide</creatorcontrib><creatorcontrib>Rovere Querini, Patrizia</creatorcontrib><creatorcontrib>Del Vecchio, Antonella</creatorcontrib><creatorcontrib>De Cobelli, Francesco</creatorcontrib><creatorcontrib>Fiorino, Claudio</creatorcontrib><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Physica medica</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mori, Martina</au><au>Alborghetti, Lisa</au><au>Palumbo, Diego</au><au>Broggi, Sara</au><au>Raspanti, Davide</au><au>Rovere Querini, Patrizia</au><au>Del Vecchio, Antonella</au><au>De Cobelli, Francesco</au><au>Fiorino, Claudio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study</atitle><jtitle>Physica medica</jtitle><date>2022-08-01</date><risdate>2022</risdate><volume>100</volume><spage>142</spage><epage>152</epage><pages>142-152</pages><issn>1120-1797</issn><eissn>1724-191X</eissn><abstract>•Segmentation algorithms do not work well on unhealthy lungs as COVID-19 ones.•An Atlas for segmentation of COVID-19 lungs’ patients was developed and validated.•Lung histograms parameters could impact the clinical management of COVID-19 patients.•Lung densitometry characterization method integrated to segmentation was implemented.
To develop and validate an automated segmentation tool for COVID-19 lung CTs. To combine it with densitometry information in identifying Aerated, Intermediate and Consolidated Volumes in admission (CT1) and follow up CT (CT3).
An Atlas was trained on manually segmented CT1 of 250 patients and validated on 10 CT1 of the training group, 10 new CT1 and 10 CT3, by comparing DICE index between automatic (AUTO), automatic-corrected (AUTOMAN) and manual (MAN) contours. A previously developed automatic method was applied on HU lung density histograms to quantify Aerated, Intermediate and Consolidated Volumes. Volumes of subregions in validation CT1 and CT3 were quantified for each method.
In validation CT1/CT3, manual correction of automatic contours was not necessary in 40% of cases. Mean DICE values for both lungs were 0.94 for AUTOVsMAN and 0.96 for AUTOMANVsMAN. Differences between Aerated and Intermediate Volumes quantified with AUTOVsMAN contours were always < 6%. Consolidated Volumes showed larger differences (mean: −95 ± 72 cc). If considering AUTOMANVsMAN volumes, differences got further smaller for Aerated and Intermediate, and were drastically reduced for consolidated Volumes (mean: −36 ± 25 cc). The average time for manual correction of automatic lungs contours on CT1 was 5 ± 2 min.
An Atlas for automatic segmentation of lungs in COVID-19 patients was developed and validated. Combined with a previously developed method for lung densitometry characterization, it provides a fast, operator-independent way to extract relevant quantitative parameters with minimal manual intervention.</abstract><pub>Elsevier Ltd</pub><pmid>35839667</pmid><doi>10.1016/j.ejmp.2022.06.018</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1120-1797 |
| ispartof | Physica medica, 2022-08, Vol.100, p.142-152 |
| issn | 1120-1797 1724-191X |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9250926 |
| source | Elsevier ScienceDirect Journals |
| subjects | Automatic segmentation Atlas-based Covid-19 Lung segmentation Original Paper Quantitative imaging computed tomography |
| title | Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T13%3A54%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Atlas-based%20lung%20segmentation%20combined%20with%20automatic%20densitometry%20characterization%20in%20COVID-19%20patients:%20Training,%20validation%20and%20first%20application%20in%20a%20longitudinal%20study&rft.jtitle=Physica%20medica&rft.au=Mori,%20Martina&rft.date=2022-08-01&rft.volume=100&rft.spage=142&rft.epage=152&rft.pages=142-152&rft.issn=1120-1797&rft.eissn=1724-191X&rft_id=info:doi/10.1016/j.ejmp.2022.06.018&rft_dat=%3Cproquest_pubme%3E2691049290%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2691049290&rft_id=info:pmid/35839667&rft_els_id=S1120179722020117&rfr_iscdi=true |