Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound.
Identifieur interne : 000822 ( PubMed/Corpus ); précédent : 000821; suivant : 000823Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound.
Auteurs : B. Sciolla ; P. Delachartre ; L. Cowell ; T. Dambry ; B. GuibertSource :
- Computers in biology and medicine [ 1879-0534 ] ; 2017.
Abstract
In this article, we propose a segmentation algorithm for skin lesions in 3D high-frequency ultrasound images. The segmentation is done on melanoma and Basal-cell carcinoma tumors, the most common skin cancer types, and could be used for diagnosis and surgical excision planning in a clinical context. Compared with previously proposed algorithms, which tend to underestimate the size of the lesion, we propose two new boundary terms which provide significant improvements of the accuracy. The first is a probabilistic boundary expansion (PBE) term designed to broaden the segmented area at the boundaries, which uses the feature asymmetry criterion. The second is a curvature dependent regularization (CDR), which aims at overcoming the tendency of standard regularization to shrink segmented areas. On a clinical dataset of 12 patients annotated by a dermatologist, the proposed algorithm has a comparable Dice index but increases the sensitivity by 26%. The proposed algorithm improves the sensitivity for all lesions, and the obtained sensitivity is close to that of the intra-observer variability.
DOI: 10.1016/j.compbiomed.2017.06.012
PubMed: 28641234
Links to Exploration step
pubmed:28641234Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound.</title>
<author><name sortKey="Sciolla, B" sort="Sciolla, B" uniqKey="Sciolla B" first="B" last="Sciolla">B. Sciolla</name>
<affiliation><nlm:affiliation>CREATIS, INSA, Lyon, France. Electronic address: bruno.sciolla@creatis.insa-lyon.fr.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Delachartre, P" sort="Delachartre, P" uniqKey="Delachartre P" first="P" last="Delachartre">P. Delachartre</name>
<affiliation><nlm:affiliation>CREATIS, INSA, Lyon, France. Electronic address: philippe.delachartre@creatis.insa-lyon.fr.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Cowell, L" sort="Cowell, L" uniqKey="Cowell L" first="L" last="Cowell">L. Cowell</name>
<affiliation><nlm:affiliation>Melanoma Skin Cancer Clinic, Hamilton Hill, Australia.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Dambry, T" sort="Dambry, T" uniqKey="Dambry T" first="T" last="Dambry">T. Dambry</name>
<affiliation><nlm:affiliation>Atys Medical, Soucieu-En-Jarrest, France.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Guibert, B" sort="Guibert, B" uniqKey="Guibert B" first="B" last="Guibert">B. Guibert</name>
<affiliation><nlm:affiliation>Atys Medical, Soucieu-En-Jarrest, France.</nlm:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2017">2017</date>
<idno type="RBID">pubmed:28641234</idno>
<idno type="pmid">28641234</idno>
<idno type="doi">10.1016/j.compbiomed.2017.06.012</idno>
<idno type="wicri:Area/PubMed/Corpus">000822</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000822</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound.</title>
<author><name sortKey="Sciolla, B" sort="Sciolla, B" uniqKey="Sciolla B" first="B" last="Sciolla">B. Sciolla</name>
<affiliation><nlm:affiliation>CREATIS, INSA, Lyon, France. Electronic address: bruno.sciolla@creatis.insa-lyon.fr.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Delachartre, P" sort="Delachartre, P" uniqKey="Delachartre P" first="P" last="Delachartre">P. Delachartre</name>
<affiliation><nlm:affiliation>CREATIS, INSA, Lyon, France. Electronic address: philippe.delachartre@creatis.insa-lyon.fr.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Cowell, L" sort="Cowell, L" uniqKey="Cowell L" first="L" last="Cowell">L. Cowell</name>
<affiliation><nlm:affiliation>Melanoma Skin Cancer Clinic, Hamilton Hill, Australia.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Dambry, T" sort="Dambry, T" uniqKey="Dambry T" first="T" last="Dambry">T. Dambry</name>
<affiliation><nlm:affiliation>Atys Medical, Soucieu-En-Jarrest, France.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Guibert, B" sort="Guibert, B" uniqKey="Guibert B" first="B" last="Guibert">B. Guibert</name>
<affiliation><nlm:affiliation>Atys Medical, Soucieu-En-Jarrest, France.</nlm:affiliation>
</affiliation>
</author>
</analytic>
<series><title level="j">Computers in biology and medicine</title>
<idno type="eISSN">1879-0534</idno>
<imprint><date when="2017" type="published">2017</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In this article, we propose a segmentation algorithm for skin lesions in 3D high-frequency ultrasound images. The segmentation is done on melanoma and Basal-cell carcinoma tumors, the most common skin cancer types, and could be used for diagnosis and surgical excision planning in a clinical context. Compared with previously proposed algorithms, which tend to underestimate the size of the lesion, we propose two new boundary terms which provide significant improvements of the accuracy. The first is a probabilistic boundary expansion (PBE) term designed to broaden the segmented area at the boundaries, which uses the feature asymmetry criterion. The second is a curvature dependent regularization (CDR), which aims at overcoming the tendency of standard regularization to shrink segmented areas. On a clinical dataset of 12 patients annotated by a dermatologist, the proposed algorithm has a comparable Dice index but increases the sensitivity by 26%. The proposed algorithm improves the sensitivity for all lesions, and the obtained sensitivity is close to that of the intra-observer variability.</div>
</front>
</TEI>
<pubmed><MedlineCitation Status="In-Process" Owner="NLM"><PMID Version="1">28641234</PMID>
<DateCreated><Year>2017</Year>
<Month>06</Month>
<Day>22</Day>
</DateCreated>
<DateRevised><Year>2017</Year>
<Month>08</Month>
<Day>07</Day>
</DateRevised>
<Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1879-0534</ISSN>
<JournalIssue CitedMedium="Internet"><Volume>87</Volume>
<PubDate><Year>2017</Year>
<Month>Aug</Month>
<Day>01</Day>
</PubDate>
</JournalIssue>
<Title>Computers in biology and medicine</Title>
<ISOAbbreviation>Comput. Biol. Med.</ISOAbbreviation>
</Journal>
<ArticleTitle>Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound.</ArticleTitle>
<Pagination><MedlinePgn>302-310</MedlinePgn>
</Pagination>
<ELocationID EIdType="pii" ValidYN="Y">S0010-4825(17)30176-2</ELocationID>
<ELocationID EIdType="doi" ValidYN="Y">10.1016/j.compbiomed.2017.06.012</ELocationID>
<Abstract><AbstractText>In this article, we propose a segmentation algorithm for skin lesions in 3D high-frequency ultrasound images. The segmentation is done on melanoma and Basal-cell carcinoma tumors, the most common skin cancer types, and could be used for diagnosis and surgical excision planning in a clinical context. Compared with previously proposed algorithms, which tend to underestimate the size of the lesion, we propose two new boundary terms which provide significant improvements of the accuracy. The first is a probabilistic boundary expansion (PBE) term designed to broaden the segmented area at the boundaries, which uses the feature asymmetry criterion. The second is a curvature dependent regularization (CDR), which aims at overcoming the tendency of standard regularization to shrink segmented areas. On a clinical dataset of 12 patients annotated by a dermatologist, the proposed algorithm has a comparable Dice index but increases the sensitivity by 26%. The proposed algorithm improves the sensitivity for all lesions, and the obtained sensitivity is close to that of the intra-observer variability.</AbstractText>
<CopyrightInformation>Copyright © 2017 Elsevier Ltd. All rights reserved.</CopyrightInformation>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Sciolla</LastName>
<ForeName>B</ForeName>
<Initials>B</Initials>
<AffiliationInfo><Affiliation>CREATIS, INSA, Lyon, France. Electronic address: bruno.sciolla@creatis.insa-lyon.fr.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Delachartre</LastName>
<ForeName>P</ForeName>
<Initials>P</Initials>
<AffiliationInfo><Affiliation>CREATIS, INSA, Lyon, France. Electronic address: philippe.delachartre@creatis.insa-lyon.fr.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Cowell</LastName>
<ForeName>L</ForeName>
<Initials>L</Initials>
<AffiliationInfo><Affiliation>Melanoma Skin Cancer Clinic, Hamilton Hill, Australia.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Dambry</LastName>
<ForeName>T</ForeName>
<Initials>T</Initials>
<AffiliationInfo><Affiliation>Atys Medical, Soucieu-En-Jarrest, France.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Guibert</LastName>
<ForeName>B</ForeName>
<Initials>B</Initials>
<AffiliationInfo><Affiliation>Atys Medical, Soucieu-En-Jarrest, France.</Affiliation>
</AffiliationInfo>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic"><Year>2017</Year>
<Month>06</Month>
<Day>15</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>Comput Biol Med</MedlineTA>
<NlmUniqueID>1250250</NlmUniqueID>
<ISSNLinking>0010-4825</ISSNLinking>
</MedlineJournalInfo>
<KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Basal-cell carcinoma</Keyword>
<Keyword MajorTopicYN="N">Curvature-driven dynamics</Keyword>
<Keyword MajorTopicYN="N">Feature asymmetry</Keyword>
<Keyword MajorTopicYN="N">Level-set</Keyword>
<Keyword MajorTopicYN="N">Melanoma</Keyword>
<Keyword MajorTopicYN="N">Segmentation</Keyword>
<Keyword MajorTopicYN="N">Tumor</Keyword>
<Keyword MajorTopicYN="N">Ultrasound</Keyword>
</KeywordList>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="received"><Year>2017</Year>
<Month>04</Month>
<Day>19</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="revised"><Year>2017</Year>
<Month>06</Month>
<Day>12</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="accepted"><Year>2017</Year>
<Month>06</Month>
<Day>12</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed"><Year>2017</Year>
<Month>6</Month>
<Day>24</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2017</Year>
<Month>6</Month>
<Day>24</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2017</Year>
<Month>6</Month>
<Day>23</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="pubmed">28641234</ArticleId>
<ArticleId IdType="pii">S0010-4825(17)30176-2</ArticleId>
<ArticleId IdType="doi">10.1016/j.compbiomed.2017.06.012</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000822 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000822 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Asie |area= AustralieFrV1 |flux= PubMed |étape= Corpus |type= RBID |clé= pubmed:28641234 |texte= Improved boundary segmentation of skin lesions in high-frequency 3D ultrasound. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:28641234" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \ | NlmPubMed2Wicri -a AustralieFrV1
![]() | This area was generated with Dilib version V0.6.33. | ![]() |