Comparing classification methods for diffuse reflectance spectra to improve tissue specific laser surgery.
Identifieur interne : 000597 ( PubMed/Corpus ); précédent : 000596; suivant : 000598Comparing classification methods for diffuse reflectance spectra to improve tissue specific laser surgery.
Auteurs : Alexander Engelhardt ; Rajesh Kanawade ; Christian Knipfer ; Matthias Schmid ; Florian Stelzle ; Werner AdlerSource :
- BMC medical research methodology [ 1471-2288 ] ; 2014.
English descriptors
- KwdEn :
- Algorithms, Artificial Intelligence, Computer Simulation, Discriminant Analysis, Facial Nerve Injuries (prevention & control), Feedback, Humans, Laser Therapy (methods), Nerve Tissue (injuries), Optical Imaging (methods), Principal Component Analysis, Spectrum Analysis (methods), Surgery, Oral (methods).
- MESH :
- injuries : Nerve Tissue.
- methods : Laser Therapy, Optical Imaging, Spectrum Analysis, Surgery, Oral.
- prevention & control : Facial Nerve Injuries.
- Algorithms, Artificial Intelligence, Computer Simulation, Discriminant Analysis, Feedback, Humans, Principal Component Analysis.
Abstract
In the field of oral and maxillofacial surgery, newly developed laser scalpels have multiple advantages over traditional metal scalpels. However, they lack haptic feedback. This is dangerous near e.g. nerve tissue, which has to be preserved during surgery. One solution to this problem is to train an algorithm that analyzes the reflected light spectra during surgery and can classify these spectra into different tissue types, in order to ultimately send a warning or temporarily switch off the laser when critical tissue is about to be ablated. Various machine learning algorithms are available for this task, but a detailed analysis is needed to assess the most appropriate algorithm.
DOI: 10.1186/1471-2288-14-91
PubMed: 25030085
Links to Exploration step
pubmed:25030085Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Comparing classification methods for diffuse reflectance spectra to improve tissue specific laser surgery.</title><author><name sortKey="Engelhardt, Alexander" sort="Engelhardt, Alexander" uniqKey="Engelhardt A" first="Alexander" last="Engelhardt">Alexander Engelhardt</name></author><author><name sortKey="Kanawade, Rajesh" sort="Kanawade, Rajesh" uniqKey="Kanawade R" first="Rajesh" last="Kanawade">Rajesh Kanawade</name></author><author><name sortKey="Knipfer, Christian" sort="Knipfer, Christian" uniqKey="Knipfer C" first="Christian" last="Knipfer">Christian Knipfer</name></author><author><name sortKey="Schmid, Matthias" sort="Schmid, Matthias" uniqKey="Schmid M" first="Matthias" last="Schmid">Matthias Schmid</name></author><author><name sortKey="Stelzle, Florian" sort="Stelzle, Florian" uniqKey="Stelzle F" first="Florian" last="Stelzle">Florian Stelzle</name></author><author><name sortKey="Adler, Werner" sort="Adler, Werner" uniqKey="Adler W" first="Werner" last="Adler">Werner Adler</name><affiliation><nlm:affiliation>Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander University Erlangen-Nuremberg, Waldstrasse 6, 91054 Erlangen, Germany. werner.adler@fau.de.</nlm:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2014">2014</date><idno type="doi">10.1186/1471-2288-14-91</idno><idno type="RBID">pubmed:25030085</idno><idno type="pmid">25030085</idno><idno type="wicri:Area/PubMed/Corpus">000597</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Comparing classification methods for diffuse reflectance spectra to improve tissue specific laser surgery.</title><author><name sortKey="Engelhardt, Alexander" sort="Engelhardt, Alexander" uniqKey="Engelhardt A" first="Alexander" last="Engelhardt">Alexander Engelhardt</name></author><author><name sortKey="Kanawade, Rajesh" sort="Kanawade, Rajesh" uniqKey="Kanawade R" first="Rajesh" last="Kanawade">Rajesh Kanawade</name></author><author><name sortKey="Knipfer, Christian" sort="Knipfer, Christian" uniqKey="Knipfer C" first="Christian" last="Knipfer">Christian Knipfer</name></author><author><name sortKey="Schmid, Matthias" sort="Schmid, Matthias" uniqKey="Schmid M" first="Matthias" last="Schmid">Matthias Schmid</name></author><author><name sortKey="Stelzle, Florian" sort="Stelzle, Florian" uniqKey="Stelzle F" first="Florian" last="Stelzle">Florian Stelzle</name></author><author><name sortKey="Adler, Werner" sort="Adler, Werner" uniqKey="Adler W" first="Werner" last="Adler">Werner Adler</name><affiliation><nlm:affiliation>Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander University Erlangen-Nuremberg, Waldstrasse 6, 91054 Erlangen, Germany. werner.adler@fau.de.</nlm:affiliation></affiliation></author></analytic><series><title level="j">BMC medical research methodology</title><idno type="eISSN">1471-2288</idno><imprint><date when="2014" type="published">2014</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term><term>Artificial Intelligence</term><term>Computer Simulation</term><term>Discriminant Analysis</term><term>Facial Nerve Injuries (prevention & control)</term><term>Feedback</term><term>Humans</term><term>Laser Therapy (methods)</term><term>Nerve Tissue (injuries)</term><term>Optical Imaging (methods)</term><term>Principal Component Analysis</term><term>Spectrum Analysis (methods)</term><term>Surgery, Oral (methods)</term></keywords><keywords scheme="MESH" qualifier="injuries" xml:lang="en"><term>Nerve Tissue</term></keywords><keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Laser Therapy</term><term>Optical Imaging</term><term>Spectrum Analysis</term><term>Surgery, Oral</term></keywords><keywords scheme="MESH" qualifier="prevention & control" xml:lang="en"><term>Facial Nerve Injuries</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Algorithms</term><term>Artificial Intelligence</term><term>Computer Simulation</term><term>Discriminant Analysis</term><term>Feedback</term><term>Humans</term><term>Principal Component Analysis</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In the field of oral and maxillofacial surgery, newly developed laser scalpels have multiple advantages over traditional metal scalpels. However, they lack haptic feedback. This is dangerous near e.g. nerve tissue, which has to be preserved during surgery. One solution to this problem is to train an algorithm that analyzes the reflected light spectra during surgery and can classify these spectra into different tissue types, in order to ultimately send a warning or temporarily switch off the laser when critical tissue is about to be ablated. Various machine learning algorithms are available for this task, but a detailed analysis is needed to assess the most appropriate algorithm.</div></front></TEI><pubmed><MedlineCitation Owner="NLM" Status="MEDLINE"><PMID Version="1">25030085</PMID><DateCreated><Year>2014</Year><Month>08</Month><Day>19</Day></DateCreated><DateCompleted><Year>2015</Year><Month>04</Month><Day>16</Day></DateCompleted><DateRevised><Year>2015</Year><Month>08</Month><Day>05</Day></DateRevised><Article PubModel="Electronic"><Journal><ISSN IssnType="Electronic">1471-2288</ISSN><JournalIssue CitedMedium="Internet"><Volume>14</Volume><PubDate><Year>2014</Year></PubDate></JournalIssue><Title>BMC medical research methodology</Title><ISOAbbreviation>BMC Med Res Methodol</ISOAbbreviation></Journal><ArticleTitle>Comparing classification methods for diffuse reflectance spectra to improve tissue specific laser surgery.</ArticleTitle><Pagination><MedlinePgn>91</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.1186/1471-2288-14-91</ELocationID><Abstract><AbstractText Label="BACKGROUND" NlmCategory="BACKGROUND">In the field of oral and maxillofacial surgery, newly developed laser scalpels have multiple advantages over traditional metal scalpels. However, they lack haptic feedback. This is dangerous near e.g. nerve tissue, which has to be preserved during surgery. One solution to this problem is to train an algorithm that analyzes the reflected light spectra during surgery and can classify these spectra into different tissue types, in order to ultimately send a warning or temporarily switch off the laser when critical tissue is about to be ablated. Various machine learning algorithms are available for this task, but a detailed analysis is needed to assess the most appropriate algorithm.</AbstractText><AbstractText Label="METHODS" NlmCategory="METHODS">In this study, a small data set is used to simulate many larger data sets according to a multivariate Gaussian distribution. Various machine learning algorithms are then trained and evaluated on these data sets. The algorithms' performance is subsequently evaluated and compared by averaged confusion matrices and ultimately by boxplots of misclassification rates. The results are validated on the smaller, experimental data set.</AbstractText><AbstractText Label="RESULTS" NlmCategory="RESULTS">Most classifiers have a median misclassification rate below 0.25 in the simulated data. The most notable performance was observed for the Penalized Discriminant Analysis, with a misclassifiaction rate of 0.00 in the simulated data, and an average misclassification rate of 0.02 in a 10-fold cross validation on the original data.</AbstractText><AbstractText Label="CONCLUSION" NlmCategory="CONCLUSIONS">The results suggest a Penalized Discriminant Analysis is the most promising approach, most probably because it considers the functional, correlated nature of the reflectance spectra.The results of this study improve the accuracy of real-time tissue discrimination and are an essential step towards improving the safety of oral laser surgery.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Engelhardt</LastName><ForeName>Alexander</ForeName><Initials>A</Initials></Author><Author ValidYN="Y"><LastName>Kanawade</LastName><ForeName>Rajesh</ForeName><Initials>R</Initials></Author><Author ValidYN="Y"><LastName>Knipfer</LastName><ForeName>Christian</ForeName><Initials>C</Initials></Author><Author ValidYN="Y"><LastName>Schmid</LastName><ForeName>Matthias</ForeName><Initials>M</Initials></Author><Author ValidYN="Y"><LastName>Stelzle</LastName><ForeName>Florian</ForeName><Initials>F</Initials></Author><Author ValidYN="Y"><LastName>Adler</LastName><ForeName>Werner</ForeName><Initials>W</Initials><AffiliationInfo><Affiliation>Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander University Erlangen-Nuremberg, Waldstrasse 6, 91054 Erlangen, Germany. werner.adler@fau.de.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType><PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2014</Year><Month>07</Month><Day>16</Day></ArticleDate></Article><MedlineJournalInfo><Country>England</Country><MedlineTA>BMC Med Res Methodol</MedlineTA><NlmUniqueID>100968545</NlmUniqueID><ISSNLinking>1471-2288</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><CommentsCorrectionsList><CommentsCorrections RefType="Cites"><RefSource>Ann Surg Oncol. 2004 Jan;11(1):65-70</RefSource><PMID Version="1">14699036</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Scand J Dent Res. 1987 Feb;95(1):65-73</RefSource><PMID Version="1">3470901</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Lasers Surg Med. 2005 Jun;36(5):356-64</RefSource><PMID Version="1">15856507</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>J Transl Med. 2012;10:123</RefSource><PMID Version="1">22704127</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>J Transl Med. 2011;9:20</RefSource><PMID Version="1">21310023</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Surg Innov. 2012 Dec;19(4):385-93</RefSource><PMID Version="1">22344924</PMID></CommentsCorrections><CommentsCorrections RefType="Cites"><RefSource>Lasers Surg Med. 2010 Apr;42(4):319-25</RefSource><PMID Version="1">20432281</PMID></CommentsCorrections></CommentsCorrectionsList><MeshHeadingList><MeshHeading><DescriptorName MajorTopicYN="N" UI="D000465">Algorithms</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D001185">Artificial Intelligence</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D003198">Computer Simulation</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D016002">Discriminant Analysis</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D020220">Facial Nerve Injuries</DescriptorName><QualifierName MajorTopicYN="Y" UI="Q000517">prevention & control</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D005246">Feedback</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D006801">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D053685">Laser Therapy</DescriptorName><QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D009417">Nerve Tissue</DescriptorName><QualifierName MajorTopicYN="N" UI="Q000293">injuries</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D061848">Optical Imaging</DescriptorName><QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D025341">Principal Component Analysis</DescriptorName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D013057">Spectrum Analysis</DescriptorName><QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName></MeshHeading><MeshHeading><DescriptorName MajorTopicYN="N" UI="D013515">Surgery, Oral</DescriptorName><QualifierName MajorTopicYN="Y" UI="Q000379">methods</QualifierName></MeshHeading></MeshHeadingList><OtherID Source="NLM">PMC4136948</OtherID></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2014</Year><Month>2</Month><Day>27</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2014</Year><Month>7</Month><Day>9</Day></PubMedPubDate><PubMedPubDate PubStatus="aheadofprint"><Year>2014</Year><Month>7</Month><Day>16</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2014</Year><Month>7</Month><Day>18</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2014</Year><Month>7</Month><Day>18</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2015</Year><Month>4</Month><Day>17</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pii">1471-2288-14-91</ArticleId><ArticleId IdType="doi">10.1186/1471-2288-14-91</ArticleId><ArticleId IdType="pubmed">25030085</ArticleId><ArticleId IdType="pmc">PMC4136948</ArticleId></ArticleIdList></PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/HapticV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000597 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000597 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= HapticV1
|flux= PubMed
|étape= Corpus
|type= RBID
|clé= pubmed:25030085
|texte= Comparing classification methods for diffuse reflectance spectra to improve tissue specific laser surgery.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:25030085" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a HapticV1
| This area was generated with Dilib version V0.6.23. |  |