FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950202237> ?p ?o ?g. }

• W2950202237 abstract "When integrating computational tools such as automatic segmentation into clinical practice, it is of utmost importance to be able to assess the level of accuracy on new data, and in particular, to detect when an automatic method fails. However, this is difficult to achieve due to absence of ground truth. Segmentation accuracy on clinical data might be different from what is found through cross-validation because validation data is often used during incremental method development, which can lead to overfitting and unrealistic performance expectations. Before deployment, performance is quantified using different metrics, for which the predicted segmentation is compared to a reference segmentation, often obtained manually by an expert. But little is known about the real performance after deployment when a reference is unavailable. In this paper, we introduce the concept of reverse classification accuracy (RCA) as a framework for predicting the performance of a segmentation method on new data. In RCA we take the predicted segmentation from a new image to train a reverse classifier which is evaluated on a set of reference images with available ground truth. The hypothesis is that if the predicted segmentation is of good quality, then the reverse classifier will perform well on at least some of the reference images. We validate our approach on multi-organ segmentation with different classifiers and segmentation methods. Our results indicate that it is indeed possible to predict the quality of individual segmentations, in the absence of ground truth. Thus, RCA is ideal for integration into automatic processing pipelines in clinical routine and as part of large-scale image analysis studies." @default.
• W2950202237 created "2019-06-27" @default.
• W2950202237 creator A5001104721 @default.
• W2950202237 creator A5006461848 @default.
• W2950202237 creator A5007222325 @default.
• W2950202237 creator A5028134411 @default.
• W2950202237 creator A5032615563 @default.
• W2950202237 creator A5036364347 @default.
• W2950202237 creator A5054775841 @default.
• W2950202237 creator A5059823739 @default.
• W2950202237 date "2017-02-11" @default.
• W2950202237 modified "2023-10-16" @default.
• W2950202237 title "Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth" @default.
• W2950202237 cites W130387664 @default.
• W2950202237 cites W1544165511 @default.
• W2950202237 cites W1555759181 @default.
• W2950202237 cites W1667869507 @default.
• W2950202237 cites W1909740415 @default.
• W2950202237 cites W1981710537 @default.
• W2950202237 cites W1987869189 @default.
• W2950202237 cites W1993947467 @default.
• W2950202237 cites W2008043556 @default.
• W2950202237 cites W2008106311 @default.
• W2950202237 cites W2020860763 @default.
• W2950202237 cites W2037758579 @default.
• W2950202237 cites W2050167119 @default.
• W2950202237 cites W2053721339 @default.
• W2950202237 cites W2058224795 @default.
• W2950202237 cites W2082704080 @default.
• W2950202237 cites W2092572597 @default.
• W2950202237 cites W2101608218 @default.
• W2950202237 cites W2104276184 @default.
• W2950202237 cites W2111498234 @default.
• W2950202237 cites W2121189958 @default.
• W2950202237 cites W2148347694 @default.
• W2950202237 cites W2158519562 @default.
• W2950202237 cites W2309471314 @default.
• W2950202237 cites W2911964244 @default.
• W2950202237 cites W53843897 @default.
• W2950202237 cites W57246982 @default.
• W2950202237 doi "https://doi.org/10.48550/arxiv.1702.03407" @default.
• W2950202237 hasPublicationYear "2017" @default.
• W2950202237 type Work @default.
• W2950202237 sameAs 2950202237 @default.
• W2950202237 citedByCount "1" @default.
• W2950202237 countsByYear W29502022372017 @default.
• W2950202237 crossrefType "posted-content" @default.
• W2950202237 hasAuthorship W2950202237A5001104721 @default.
• W2950202237 hasAuthorship W2950202237A5006461848 @default.
• W2950202237 hasAuthorship W2950202237A5007222325 @default.
• W2950202237 hasAuthorship W2950202237A5028134411 @default.
• W2950202237 hasAuthorship W2950202237A5032615563 @default.
• W2950202237 hasAuthorship W2950202237A5036364347 @default.
• W2950202237 hasAuthorship W2950202237A5054775841 @default.
• W2950202237 hasAuthorship W2950202237A5059823739 @default.
• W2950202237 hasBestOaLocation W29502022371 @default.
• W2950202237 hasConcept C124101348 @default.
• W2950202237 hasConcept C124504099 @default.
• W2950202237 hasConcept C146849305 @default.
• W2950202237 hasConcept C153180895 @default.
• W2950202237 hasConcept C154945302 @default.
• W2950202237 hasConcept C22019652 @default.
• W2950202237 hasConcept C41008148 @default.
• W2950202237 hasConcept C50644808 @default.
• W2950202237 hasConcept C65885262 @default.
• W2950202237 hasConcept C89600930 @default.
• W2950202237 hasConcept C95623464 @default.
• W2950202237 hasConceptScore W2950202237C124101348 @default.
• W2950202237 hasConceptScore W2950202237C124504099 @default.
• W2950202237 hasConceptScore W2950202237C146849305 @default.
• W2950202237 hasConceptScore W2950202237C153180895 @default.
• W2950202237 hasConceptScore W2950202237C154945302 @default.
• W2950202237 hasConceptScore W2950202237C22019652 @default.
• W2950202237 hasConceptScore W2950202237C41008148 @default.
• W2950202237 hasConceptScore W2950202237C50644808 @default.
• W2950202237 hasConceptScore W2950202237C65885262 @default.
• W2950202237 hasConceptScore W2950202237C89600930 @default.
• W2950202237 hasConceptScore W2950202237C95623464 @default.
• W2950202237 hasLocation W29502022371 @default.
• W2950202237 hasLocation W29502022372 @default.
• W2950202237 hasOpenAccess W2950202237 @default.
• W2950202237 hasPrimaryLocation W29502022371 @default.
• W2950202237 hasRelatedWork W134976887 @default.
• W2950202237 hasRelatedWork W1582206143 @default.
• W2950202237 hasRelatedWork W158826679 @default.
• W2950202237 hasRelatedWork W178995947 @default.
• W2950202237 hasRelatedWork W2021143974 @default.
• W2950202237 hasRelatedWork W2118381968 @default.
• W2950202237 hasRelatedWork W2549765251 @default.
• W2950202237 hasRelatedWork W2742991909 @default.
• W2950202237 hasRelatedWork W2892474421 @default.
• W2950202237 hasRelatedWork W3203023927 @default.
• W2950202237 isParatext "false" @default.
• W2950202237 isRetracted "false" @default.
• W2950202237 magId "2950202237" @default.
• W2950202237 workType "article" @default.