FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2142456468> ?p ?o ?g. }

• W2142456468 endingPage "994" @default.
• W2142456468 startingPage "983" @default.
• W2142456468 abstract "It is well known in the pattern recognition community that the accuracy of classifications obtained by combining decisions made by independent classifiers can be substantially higher than the accuracy of the individual classifiers. We have previously shown this to be true for atlas-based segmentation of biomedical images. The conventional method for combining individual classifiers weights each classifier equally (vote or sum rule fusion). In this paper, we propose two methods that estimate the performances of the individual classifiers and combine the individual classifiers by weighting them according to their estimated performance. The two methods are multiclass extensions of an expectation-maximization (EM) algorithm for ground truth estimation of binary classification based on decisions of multiple experts (Warfield et al., 2004). The first method performs parameter estimation independently for each class with a subsequent integration step. The second method considers all classes simultaneously. We demonstrate the efficacy of these performance-based fusion methods by applying them to atlas-based segmentations of three-dimensional confocal microscopy images of bee brains. In atlas-based image segmentation, multiple classifiers arise naturally by applying different registration methods to the same atlas, or the same registration method to different atlases, or both. We perform a validation study designed to quantify the success of classifier combination methods in atlas-based segmentation. By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images. In a second evaluation study, multiple actual atlas-based segmentations are combined and their accuracies computed by comparing them to a manual segmentation. We demonstrate in both evaluation studies that segmentations produced by combining multiple individual registration-based segmentations are more accurate for the two classifier fusion methods we propose, which weight the individual classifiers according to their EM-based performance estimates, than for simple sum rule fusion, which weights each classifier equally." @default.
• W2142456468 created "2016-06-24" @default.
• W2142456468 creator A5004244390 @default.
• W2142456468 creator A5040484638 @default.
• W2142456468 creator A5073481761 @default.
• W2142456468 date "2004-08-01" @default.
• W2142456468 modified "2023-09-24" @default.
• W2142456468 title "Performance-Based Classifier Combination in Atlas-Based Image Segmentation Using Expectation-Maximization Parameter Estimation" @default.
• W2142456468 cites W1570980525 @default.
• W2142456468 cites W1773005811 @default.
• W2142456468 cites W1985690171 @default.
• W2142456468 cites W1987029684 @default.
• W2142456468 cites W1995622889 @default.
• W2142456468 cites W2004987553 @default.
• W2142456468 cites W2025653905 @default.
• W2142456468 cites W2034432063 @default.
• W2142456468 cites W2035964780 @default.
• W2142456468 cites W2039861336 @default.
• W2142456468 cites W2049247209 @default.
• W2142456468 cites W2060637508 @default.
• W2142456468 cites W2096619076 @default.
• W2142456468 cites W2098154993 @default.
• W2142456468 cites W2101118184 @default.
• W2142456468 cites W2102734279 @default.
• W2142456468 cites W2102849263 @default.
• W2142456468 cites W2103796117 @default.
• W2142456468 cites W2106761770 @default.
• W2142456468 cites W2113576511 @default.
• W2142456468 cites W2122558050 @default.
• W2142456468 cites W2124565667 @default.
• W2142456468 cites W2125504089 @default.
• W2142456468 cites W2126297944 @default.
• W2142456468 cites W2136148445 @default.
• W2142456468 cites W2137789542 @default.
• W2142456468 cites W2140717492 @default.
• W2142456468 cites W2141304179 @default.
• W2142456468 cites W2146440428 @default.
• W2142456468 cites W2148347694 @default.
• W2142456468 cites W2158275940 @default.
• W2142456468 cites W2164568552 @default.
• W2142456468 cites W4319308513 @default.
• W2142456468 doi "https://doi.org/10.1109/tmi.2004.830803" @default.
• W2142456468 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/15338732" @default.
• W2142456468 hasPublicationYear "2004" @default.
• W2142456468 type Work @default.
• W2142456468 sameAs 2142456468 @default.
• W2142456468 citedByCount "228" @default.
• W2142456468 countsByYear W21424564682012 @default.
• W2142456468 countsByYear W21424564682013 @default.
• W2142456468 countsByYear W21424564682014 @default.
• W2142456468 countsByYear W21424564682015 @default.
• W2142456468 countsByYear W21424564682016 @default.
• W2142456468 countsByYear W21424564682017 @default.
• W2142456468 countsByYear W21424564682018 @default.
• W2142456468 countsByYear W21424564682019 @default.
• W2142456468 countsByYear W21424564682020 @default.
• W2142456468 countsByYear W21424564682021 @default.
• W2142456468 countsByYear W21424564682022 @default.
• W2142456468 countsByYear W21424564682023 @default.
• W2142456468 crossrefType "journal-article" @default.
• W2142456468 hasAuthorship W2142456468A5004244390 @default.
• W2142456468 hasAuthorship W2142456468A5040484638 @default.
• W2142456468 hasAuthorship W2142456468A5073481761 @default.
• W2142456468 hasConcept C106135958 @default.
• W2142456468 hasConcept C115961682 @default.
• W2142456468 hasConcept C124504099 @default.
• W2142456468 hasConcept C126255220 @default.
• W2142456468 hasConcept C126838900 @default.
• W2142456468 hasConcept C146849305 @default.
• W2142456468 hasConcept C151730666 @default.
• W2142456468 hasConcept C153180895 @default.
• W2142456468 hasConcept C154945302 @default.
• W2142456468 hasConcept C183115368 @default.
• W2142456468 hasConcept C2776330181 @default.
• W2142456468 hasConcept C2776673561 @default.
• W2142456468 hasConcept C33923547 @default.
• W2142456468 hasConcept C41008148 @default.
• W2142456468 hasConcept C71924100 @default.
• W2142456468 hasConcept C75294576 @default.
• W2142456468 hasConcept C86803240 @default.
• W2142456468 hasConcept C89600930 @default.
• W2142456468 hasConcept C95623464 @default.
• W2142456468 hasConceptScore W2142456468C106135958 @default.
• W2142456468 hasConceptScore W2142456468C115961682 @default.
• W2142456468 hasConceptScore W2142456468C124504099 @default.
• W2142456468 hasConceptScore W2142456468C126255220 @default.
• W2142456468 hasConceptScore W2142456468C126838900 @default.
• W2142456468 hasConceptScore W2142456468C146849305 @default.
• W2142456468 hasConceptScore W2142456468C151730666 @default.
• W2142456468 hasConceptScore W2142456468C153180895 @default.
• W2142456468 hasConceptScore W2142456468C154945302 @default.
• W2142456468 hasConceptScore W2142456468C183115368 @default.
• W2142456468 hasConceptScore W2142456468C2776330181 @default.
• W2142456468 hasConceptScore W2142456468C2776673561 @default.
• W2142456468 hasConceptScore W2142456468C33923547 @default.
• W2142456468 hasConceptScore W2142456468C41008148 @default.
• W2142456468 hasConceptScore W2142456468C71924100 @default.
• W2142456468 hasConceptScore W2142456468C75294576 @default.

• next