Matches in SemOpenAlex for { <https://semopenalex.org/work/W2005322791> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W2005322791 abstract "Systematic validation of tumor segmentation technique is very important in ensuring the accuracy and reproducibilityof tumor segmentation algorithm in clinical applications. In this paper, we present a new method forevaluating 3D tumor segmentation using Artificial Neural Network (ANN) and combined objective metrics. Inour evaluation method, a three-layer feed-forwarding backpropagation ANN is first trained to simulate radiologist'ssubjective rating using a set of objective metrics. The trained neural network is then used to evaluate thetumor segmentation on a five-point scale in a way similar to expert's evaluation. The accuracy of segmentationevaluation is quantified using average correct rank and frequency of the reference rating in the top ranks ofsimulated score list. Experimental results from 93 lesions showed that our evaluation method performs betterthan individual metrics. The optimal combination of metrics from normalized volume difference, volume overlap,Root Mean Square symmetric surface distance and maximum symmetric surface distance showed the smallestaverage correct rank (1.43) and highest frequency of the reference rating in the top two places of simulated ratinglist (93.55%). Our results also demonstrate that the ANN based non-linear combination method showed betterevaluation accuracy than linear combination method in all performance measures. Our evaluation techniquehas the potential to facilitate large scale segmentation validation study by predicting radiologists rating, and toassist development of new tumor segmentation algorithms. It can also be extended to validation of segmentationalgorithms for other applications." @default.
- W2005322791 created "2016-06-24" @default.
- W2005322791 creator A5037425961 @default.
- W2005322791 creator A5043879150 @default.
- W2005322791 date "2011-03-03" @default.
- W2005322791 modified "2023-09-23" @default.
- W2005322791 title "Application of artificial neural network in simulating subjective evaluation of tumor segmentation" @default.
- W2005322791 doi "https://doi.org/10.1117/12.877892" @default.
- W2005322791 hasPublicationYear "2011" @default.
- W2005322791 type Work @default.
- W2005322791 sameAs 2005322791 @default.
- W2005322791 citedByCount "0" @default.
- W2005322791 crossrefType "proceedings-article" @default.
- W2005322791 hasAuthorship W2005322791A5037425961 @default.
- W2005322791 hasAuthorship W2005322791A5043879150 @default.
- W2005322791 hasConcept C105795698 @default.
- W2005322791 hasConcept C114614502 @default.
- W2005322791 hasConcept C124504099 @default.
- W2005322791 hasConcept C139945424 @default.
- W2005322791 hasConcept C153180895 @default.
- W2005322791 hasConcept C154945302 @default.
- W2005322791 hasConcept C155032097 @default.
- W2005322791 hasConcept C164226766 @default.
- W2005322791 hasConcept C33923547 @default.
- W2005322791 hasConcept C41008148 @default.
- W2005322791 hasConcept C50644808 @default.
- W2005322791 hasConcept C89600930 @default.
- W2005322791 hasConceptScore W2005322791C105795698 @default.
- W2005322791 hasConceptScore W2005322791C114614502 @default.
- W2005322791 hasConceptScore W2005322791C124504099 @default.
- W2005322791 hasConceptScore W2005322791C139945424 @default.
- W2005322791 hasConceptScore W2005322791C153180895 @default.
- W2005322791 hasConceptScore W2005322791C154945302 @default.
- W2005322791 hasConceptScore W2005322791C155032097 @default.
- W2005322791 hasConceptScore W2005322791C164226766 @default.
- W2005322791 hasConceptScore W2005322791C33923547 @default.
- W2005322791 hasConceptScore W2005322791C41008148 @default.
- W2005322791 hasConceptScore W2005322791C50644808 @default.
- W2005322791 hasConceptScore W2005322791C89600930 @default.
- W2005322791 hasLocation W20053227911 @default.
- W2005322791 hasOpenAccess W2005322791 @default.
- W2005322791 hasPrimaryLocation W20053227911 @default.
- W2005322791 hasRelatedWork W1484132471 @default.
- W2005322791 hasRelatedWork W1576177170 @default.
- W2005322791 hasRelatedWork W1830460666 @default.
- W2005322791 hasRelatedWork W2023798383 @default.
- W2005322791 hasRelatedWork W2035422235 @default.
- W2005322791 hasRelatedWork W2070340558 @default.
- W2005322791 hasRelatedWork W2085381944 @default.
- W2005322791 hasRelatedWork W2170059565 @default.
- W2005322791 hasRelatedWork W2304155747 @default.
- W2005322791 hasRelatedWork W2328749028 @default.
- W2005322791 hasRelatedWork W2371689167 @default.
- W2005322791 hasRelatedWork W2966311710 @default.
- W2005322791 hasRelatedWork W2998544540 @default.
- W2005322791 hasRelatedWork W3003985975 @default.
- W2005322791 hasRelatedWork W3006166274 @default.
- W2005322791 hasRelatedWork W3121120848 @default.
- W2005322791 hasRelatedWork W3146309404 @default.
- W2005322791 hasRelatedWork W3166254419 @default.
- W2005322791 hasRelatedWork W54626961 @default.
- W2005322791 hasRelatedWork W2842429567 @default.
- W2005322791 isParatext "false" @default.
- W2005322791 isRetracted "false" @default.
- W2005322791 magId "2005322791" @default.
- W2005322791 workType "article" @default.