Automatic Scoring of Virtual Mastoidectomies Using Expert Examples
Identifieur interne : 002C97 ( Main/Exploration ); précédent : 002C96; suivant : 002C98Automatic Scoring of Virtual Mastoidectomies Using Expert Examples
Auteurs : Thomas Kerwin ; Gregory Wiet ; Don Stredney ; Han-Wei ShenSource :
- International Journal of Computer Assisted Radiology and Surgery [ 1861-6410 ] ; 2011.
Abstract
Automatic scoring of resident performance on a virtual mastoidectomy simulation system is needed to achieve consistent and efficient evaluations. By not requiring immediate expert intervention, the system provides a completely objective assessment of performance as well as a self-driven user assessment mechanism.
An iconic temporal bone with surgically important regions defined into a fully partitioned segmented dataset was created. Comparisons between expert-drilled bones and student-drilled bones were computed based on gradations with both Euclidean and Earth Mover’s Distance. Using the features derived from these comparisons, a decision tree was constructed. This decision tree was used to determine scores of resident surgical performance. The algorithm was applied on multiple expert comparison bones and the scores averaged to provide reliability metric.
The reliability metrics for the multi-grade scoring system are better in some cases than previously reported binary classification metrics. The two scoring methods given provide a trade-off between accuracy and speed.
Comparison of virtually drilled bones with expert examples on a voxel level provides sufficient information to score them and provide several specific quality metrics. By merging scores from different expert examples, two related metrics were developed; one is slightly faster and less accurate, while a second is more accurate but takes more processing time.
Url:
DOI: 10.1007/s11548-011-0566-4
PubMed: 21538158
PubMed Central: 3403744
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: 001807
- to stream Pmc, to step Curation: 001807
- to stream Pmc, to step Checkpoint: 001C36
- to stream Ncbi, to step Merge: 001A21
- to stream Ncbi, to step Curation: 001A21
- to stream Ncbi, to step Checkpoint: 001A21
- to stream Main, to step Merge: 002D36
- to stream Main, to step Curation: 002C97
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Automatic Scoring of Virtual Mastoidectomies Using Expert Examples</title>
<author><name sortKey="Kerwin, Thomas" sort="Kerwin, Thomas" uniqKey="Kerwin T" first="Thomas" last="Kerwin">Thomas Kerwin</name>
</author>
<author><name sortKey="Wiet, Gregory" sort="Wiet, Gregory" uniqKey="Wiet G" first="Gregory" last="Wiet">Gregory Wiet</name>
</author>
<author><name sortKey="Stredney, Don" sort="Stredney, Don" uniqKey="Stredney D" first="Don" last="Stredney">Don Stredney</name>
</author>
<author><name sortKey="Shen, Han Wei" sort="Shen, Han Wei" uniqKey="Shen H" first="Han-Wei" last="Shen">Han-Wei Shen</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PMC</idno>
<idno type="pmid">21538158</idno>
<idno type="pmc">3403744</idno>
<idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3403744</idno>
<idno type="RBID">PMC:3403744</idno>
<idno type="doi">10.1007/s11548-011-0566-4</idno>
<date when="2011">2011</date>
<idno type="wicri:Area/Pmc/Corpus">001807</idno>
<idno type="wicri:Area/Pmc/Curation">001807</idno>
<idno type="wicri:Area/Pmc/Checkpoint">001C36</idno>
<idno type="wicri:Area/Ncbi/Merge">001A21</idno>
<idno type="wicri:Area/Ncbi/Curation">001A21</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">001A21</idno>
<idno type="wicri:doubleKey">1861-6410:2011:Kerwin T:automatic:scoring:of</idno>
<idno type="wicri:Area/Main/Merge">002D36</idno>
<idno type="wicri:Area/Main/Curation">002C97</idno>
<idno type="wicri:Area/Main/Exploration">002C97</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Automatic Scoring of Virtual Mastoidectomies Using Expert Examples</title>
<author><name sortKey="Kerwin, Thomas" sort="Kerwin, Thomas" uniqKey="Kerwin T" first="Thomas" last="Kerwin">Thomas Kerwin</name>
</author>
<author><name sortKey="Wiet, Gregory" sort="Wiet, Gregory" uniqKey="Wiet G" first="Gregory" last="Wiet">Gregory Wiet</name>
</author>
<author><name sortKey="Stredney, Don" sort="Stredney, Don" uniqKey="Stredney D" first="Don" last="Stredney">Don Stredney</name>
</author>
<author><name sortKey="Shen, Han Wei" sort="Shen, Han Wei" uniqKey="Shen H" first="Han-Wei" last="Shen">Han-Wei Shen</name>
</author>
</analytic>
<series><title level="j">International Journal of Computer Assisted Radiology and Surgery</title>
<idno type="ISSN">1861-6410</idno>
<idno type="eISSN">1861-6429</idno>
<imprint><date when="2011">2011</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en"><sec id="S1"><title>Purpose</title>
<p id="P1">Automatic scoring of resident performance on a virtual mastoidectomy simulation system is needed to achieve consistent and efficient evaluations. By not requiring immediate expert intervention, the system provides a completely objective assessment of performance as well as a self-driven user assessment mechanism.</p>
</sec>
<sec id="S2"><title>Methods</title>
<p id="P2">An iconic temporal bone with surgically important regions defined into a fully partitioned segmented dataset was created. Comparisons between expert-drilled bones and student-drilled bones were computed based on gradations with both Euclidean and Earth Mover’s Distance. Using the features derived from these comparisons, a decision tree was constructed. This decision tree was used to determine scores of resident surgical performance. The algorithm was applied on multiple expert comparison bones and the scores averaged to provide reliability metric.</p>
</sec>
<sec id="S3"><title>Results</title>
<p id="P3">The reliability metrics for the multi-grade scoring system are better in some cases than previously reported binary classification metrics. The two scoring methods given provide a trade-off between accuracy and speed.</p>
</sec>
<sec id="S4"><title>Conclusions</title>
<p id="P4">Comparison of virtually drilled bones with expert examples on a voxel level provides sufficient information to score them and provide several specific quality metrics. By merging scores from different expert examples, two related metrics were developed; one is slightly faster and less accurate, while a second is more accurate but takes more processing time.</p>
</sec>
</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Kerwin, Thomas" sort="Kerwin, Thomas" uniqKey="Kerwin T" first="Thomas" last="Kerwin">Thomas Kerwin</name>
<name sortKey="Shen, Han Wei" sort="Shen, Han Wei" uniqKey="Shen H" first="Han-Wei" last="Shen">Han-Wei Shen</name>
<name sortKey="Stredney, Don" sort="Stredney, Don" uniqKey="Stredney D" first="Don" last="Stredney">Don Stredney</name>
<name sortKey="Wiet, Gregory" sort="Wiet, Gregory" uniqKey="Wiet G" first="Gregory" last="Wiet">Gregory Wiet</name>
</noCountry>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/HapticV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002C97 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002C97 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= HapticV1 |flux= Main |étape= Exploration |type= RBID |clé= PMC:3403744 |texte= Automatic Scoring of Virtual Mastoidectomies Using Expert Examples }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:21538158" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \ | NlmPubMed2Wicri -a HapticV1
![]() | This area was generated with Dilib version V0.6.23. | ![]() |