Matches in SemOpenAlex for { <https://semopenalex.org/work/W2528603996> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W2528603996 abstract "A study is described that investigates the capacity for mathematical observer models to mimic the performance of human observers in a PET lesion detection task. FDG-PET data from seventeen tuberculosis patients presenting diffuse hyper-metabolic lung lesions were selected for the study, to include a wide range of lesion sizes and contrasts. All subjects were scanned on a simultaneous PET/MR system (Siemens mMR) with one bed position over the lungs, after a 4.8±1.6 mCi injection and 60-minute uptake period. Various noise levels were simulated by randomly discarding events in the PET list mode according to 10 predefined fractions, from 5×10−1 to 5×10−4. Thirty-three lesions were selected in the 17 patients, as well as one background region in each. A lesion detection task including these 550 images ((33 lesions + 17 backgrounds) × (1 original image + 10 simulated noise levels)) was developed and presented to 5 experienced image viewers (2 nuclear medicine radiologists and 3 postdoctoral researchers). The observers' responses classified each lesion into 1 of 2 classes, depending on whether it was detected or not-detected. The lesions were characterized by 4 parameters: lesion metabolic volume, lesion-to-background contrast, lesion SUV, and lesion-to-background SNR, and each was represented by its associated 4-element vector. The binary detectability data were used to train a linear observer model in the 4D space. Various fractions of the observers' decisions were used for training the model, and the accuracy was evaluated for the model's ability to predict the remaining decisions, i.e. those not used for training. This was performed randomly for 100 realizations at every training level. The findings show that good performance, in terms of matching human accuracy, was achieved with only 20% training. The model was robust, with similar trends for all human observers." @default.
- W2528603996 created "2016-10-14" @default.
- W2528603996 creator A5007085439 @default.
- W2528603996 creator A5040586052 @default.
- W2528603996 date "2015-10-01" @default.
- W2528603996 modified "2023-09-26" @default.
- W2528603996 title "A human-trained numerical observer model for PET lesion detection tasks" @default.
- W2528603996 doi "https://doi.org/10.1109/nssmic.2015.7582063" @default.
- W2528603996 hasPublicationYear "2015" @default.
- W2528603996 type Work @default.
- W2528603996 sameAs 2528603996 @default.
- W2528603996 citedByCount "1" @default.
- W2528603996 countsByYear W25286039962021 @default.
- W2528603996 crossrefType "proceedings-article" @default.
- W2528603996 hasAuthorship W2528603996A5007085439 @default.
- W2528603996 hasAuthorship W2528603996A5040586052 @default.
- W2528603996 hasConcept C115961682 @default.
- W2528603996 hasConcept C126838900 @default.
- W2528603996 hasConcept C142724271 @default.
- W2528603996 hasConcept C154945302 @default.
- W2528603996 hasConcept C2781156865 @default.
- W2528603996 hasConcept C2989005 @default.
- W2528603996 hasConcept C31972630 @default.
- W2528603996 hasConcept C41008148 @default.
- W2528603996 hasConcept C71924100 @default.
- W2528603996 hasConcept C99498987 @default.
- W2528603996 hasConceptScore W2528603996C115961682 @default.
- W2528603996 hasConceptScore W2528603996C126838900 @default.
- W2528603996 hasConceptScore W2528603996C142724271 @default.
- W2528603996 hasConceptScore W2528603996C154945302 @default.
- W2528603996 hasConceptScore W2528603996C2781156865 @default.
- W2528603996 hasConceptScore W2528603996C2989005 @default.
- W2528603996 hasConceptScore W2528603996C31972630 @default.
- W2528603996 hasConceptScore W2528603996C41008148 @default.
- W2528603996 hasConceptScore W2528603996C71924100 @default.
- W2528603996 hasConceptScore W2528603996C99498987 @default.
- W2528603996 hasLocation W25286039961 @default.
- W2528603996 hasOpenAccess W2528603996 @default.
- W2528603996 hasPrimaryLocation W25286039961 @default.
- W2528603996 hasRelatedWork W1982790663 @default.
- W2528603996 hasRelatedWork W2062542133 @default.
- W2528603996 hasRelatedWork W2091106211 @default.
- W2528603996 hasRelatedWork W2091651170 @default.
- W2528603996 hasRelatedWork W2125016105 @default.
- W2528603996 hasRelatedWork W2125644980 @default.
- W2528603996 hasRelatedWork W2167157872 @default.
- W2528603996 hasRelatedWork W2212392582 @default.
- W2528603996 hasRelatedWork W2254830930 @default.
- W2528603996 hasRelatedWork W2546665062 @default.
- W2528603996 hasRelatedWork W2552378901 @default.
- W2528603996 hasRelatedWork W2790635970 @default.
- W2528603996 hasRelatedWork W2802469733 @default.
- W2528603996 hasRelatedWork W2887059102 @default.
- W2528603996 hasRelatedWork W2952567310 @default.
- W2528603996 hasRelatedWork W3034004859 @default.
- W2528603996 hasRelatedWork W3129607688 @default.
- W2528603996 hasRelatedWork W3158802091 @default.
- W2528603996 hasRelatedWork W3165464396 @default.
- W2528603996 hasRelatedWork W2569690199 @default.
- W2528603996 isParatext "false" @default.
- W2528603996 isRetracted "false" @default.
- W2528603996 magId "2528603996" @default.
- W2528603996 workType "article" @default.