Matches in SemOpenAlex for { <https://semopenalex.org/work/W2792866074> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2792866074 abstract "Learning diagnostic labels from image content has been the standard in computer-aided diagnosis. Most computer-aided diagnosis systems use low-level image features extracted directly from image content to train and test machine learning classifiers for diagnostic label prediction. When the ground truth for the diagnostic labels is not available, reference truth is generated from the experts diagnostic interpretations of the image/region of interest. More specifically, when the label is uncertain, e.g. when multiple experts label an image and their interpretations are different, techniques to handle the label variability are necessary.In this paper, we compare three consensus techniques that are typically used to encode the variability in the experts labeling of the medical data: mean, median and mode, and their effects on simple classifiers that can handle deterministic labels (decision trees) and probabilistic vectors of labels (belief decision trees). Given that the NIH/NCI Lung Image Database Consortium (LIDC) data provides interpretations for lung nodules by up to four radiologists, we leverage the LIDC data to evaluate and compare these consensus approaches when creating computer-aided diagnosis systems for lung nodules.First, low-level image features of nodules are extracted and paired with their radiologists semantic ratings (1= most likely benign, , 5 = most likely malignant); second, machine learning multi-class classifiers that handle deterministic labels (decision trees) and probabilistic vectors of labels (belief decision trees) are built to predict the lung nodules semantic ratings. We show that the mean-based consensus generates the most robust classi- fier overall when compared to the median- and mode-based consensus. Lastly, the results of this study show that, when building CAD systems with uncertain diagnostic interpretation, it is important to evaluate different strategies for encoding and predicting the diagnostic label." @default.
- W2792866074 created "2018-03-29" @default.
- W2792866074 creator A5001027068 @default.
- W2792866074 creator A5005267835 @default.
- W2792866074 creator A5018105059 @default.
- W2792866074 creator A5074195912 @default.
- W2792866074 date "2018-02-27" @default.
- W2792866074 modified "2023-09-22" @default.
- W2792866074 title "An evaluation of consensus techniques for diagnostic interpretation" @default.
- W2792866074 cites W1833718570 @default.
- W2792866074 cites W1970852662 @default.
- W2792866074 cites W1972243481 @default.
- W2792866074 cites W1974122280 @default.
- W2792866074 cites W1992802125 @default.
- W2792866074 cites W2136325898 @default.
- W2792866074 cites W2607444182 @default.
- W2792866074 cites W2614956705 @default.
- W2792866074 cites W2996665071 @default.
- W2792866074 doi "https://doi.org/10.1117/12.2293778" @default.
- W2792866074 hasPublicationYear "2018" @default.
- W2792866074 type Work @default.
- W2792866074 sameAs 2792866074 @default.
- W2792866074 citedByCount "0" @default.
- W2792866074 crossrefType "proceedings-article" @default.
- W2792866074 hasAuthorship W2792866074A5001027068 @default.
- W2792866074 hasAuthorship W2792866074A5005267835 @default.
- W2792866074 hasAuthorship W2792866074A5018105059 @default.
- W2792866074 hasAuthorship W2792866074A5074195912 @default.
- W2792866074 hasConcept C115961682 @default.
- W2792866074 hasConcept C119857082 @default.
- W2792866074 hasConcept C146849305 @default.
- W2792866074 hasConcept C153083717 @default.
- W2792866074 hasConcept C153180895 @default.
- W2792866074 hasConcept C154945302 @default.
- W2792866074 hasConcept C31601959 @default.
- W2792866074 hasConcept C41008148 @default.
- W2792866074 hasConcept C49937458 @default.
- W2792866074 hasConcept C75294576 @default.
- W2792866074 hasConcept C84525736 @default.
- W2792866074 hasConceptScore W2792866074C115961682 @default.
- W2792866074 hasConceptScore W2792866074C119857082 @default.
- W2792866074 hasConceptScore W2792866074C146849305 @default.
- W2792866074 hasConceptScore W2792866074C153083717 @default.
- W2792866074 hasConceptScore W2792866074C153180895 @default.
- W2792866074 hasConceptScore W2792866074C154945302 @default.
- W2792866074 hasConceptScore W2792866074C31601959 @default.
- W2792866074 hasConceptScore W2792866074C41008148 @default.
- W2792866074 hasConceptScore W2792866074C49937458 @default.
- W2792866074 hasConceptScore W2792866074C75294576 @default.
- W2792866074 hasConceptScore W2792866074C84525736 @default.
- W2792866074 hasLocation W27928660741 @default.
- W2792866074 hasOpenAccess W2792866074 @default.
- W2792866074 hasPrimaryLocation W27928660741 @default.
- W2792866074 hasRelatedWork W1482934285 @default.
- W2792866074 hasRelatedWork W1532011399 @default.
- W2792866074 hasRelatedWork W1585184399 @default.
- W2792866074 hasRelatedWork W1590870108 @default.
- W2792866074 hasRelatedWork W2010537640 @default.
- W2792866074 hasRelatedWork W2015281176 @default.
- W2792866074 hasRelatedWork W2090136295 @default.
- W2792866074 hasRelatedWork W2096854571 @default.
- W2792866074 hasRelatedWork W2184345909 @default.
- W2792866074 hasRelatedWork W2273159907 @default.
- W2792866074 hasRelatedWork W2610879212 @default.
- W2792866074 hasRelatedWork W2891133539 @default.
- W2792866074 hasRelatedWork W2899810345 @default.
- W2792866074 hasRelatedWork W2911982216 @default.
- W2792866074 hasRelatedWork W3021746463 @default.
- W2792866074 hasRelatedWork W3082326673 @default.
- W2792866074 hasRelatedWork W3098394437 @default.
- W2792866074 hasRelatedWork W3176461355 @default.
- W2792866074 hasRelatedWork W3193605466 @default.
- W2792866074 hasRelatedWork W3206450851 @default.
- W2792866074 isParatext "false" @default.
- W2792866074 isRetracted "false" @default.
- W2792866074 magId "2792866074" @default.
- W2792866074 workType "article" @default.