Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212357338> ?p ?o ?g. }
- W3212357338 abstract "Purpose: Deep learning-based image super-resolution (DL-SR) has shown great promise in medical imaging applications. To date, most of the proposed methods for DL-SR have only been assessed using traditional measures of image quality (IQ) that are commonly employed in the field of computer vision. However, the impact of these methods on objective measures of IQ that are relevant to medical imaging tasks remains largely unexplored. We investigate the impact of DL-SR methods on binary signal detection performance. Approach: Two popular DL-SR methods, the super-resolution convolutional neural network and the super-resolution generative adversarial network, were trained using simulated medical image data. Binary signal-known-exactly with background-known-statistically and signal-known-statistically with background-known-statistically detection tasks were formulated. Numerical observers (NOs), which included a neural network-approximated ideal observer and common linear NOs, were employed to assess the impact of DL-SR on task performance. The impact of the complexity of the DL-SR network architectures on task performance was quantified. In addition, the utility of DL-SR for improving the task performance of suboptimal observers was investigated. Results: Our numerical experiments confirmed that, as expected, DL-SR improved traditional measures of IQ. However, for many of the study designs considered, the DL-SR methods provided little or no improvement in task performance and even degraded it. It was observed that DL-SR improved the task performance of suboptimal observers under certain conditions. Conclusions: Our study highlights the urgent need for the objective assessment of DL-SR methods and suggests avenues for improving their efficacy in medical imaging applications." @default.
- W3212357338 created "2021-11-22" @default.
- W3212357338 creator A5000482255 @default.
- W3212357338 creator A5017521861 @default.
- W3212357338 creator A5045249494 @default.
- W3212357338 creator A5046506193 @default.
- W3212357338 creator A5068094970 @default.
- W3212357338 date "2021-11-16" @default.
- W3212357338 modified "2023-10-14" @default.
- W3212357338 title "Impact of deep learning-based image super-resolution on binary signal detection" @default.
- W3212357338 cites W1572063013 @default.
- W3212357338 cites W1885185971 @default.
- W3212357338 cites W1966363043 @default.
- W3212357338 cites W2005277092 @default.
- W3212357338 cites W2040504732 @default.
- W3212357338 cites W2066901675 @default.
- W3212357338 cites W2067829201 @default.
- W3212357338 cites W2093500112 @default.
- W3212357338 cites W2094213283 @default.
- W3212357338 cites W2099078477 @default.
- W3212357338 cites W2110140109 @default.
- W3212357338 cites W2129940523 @default.
- W3212357338 cites W2144551243 @default.
- W3212357338 cites W2146200771 @default.
- W3212357338 cites W2160341882 @default.
- W3212357338 cites W2170689809 @default.
- W3212357338 cites W2328176404 @default.
- W3212357338 cites W2794977498 @default.
- W3212357338 cites W2963182372 @default.
- W3212357338 cites W2988368565 @default.
- W3212357338 cites W3013529009 @default.
- W3212357338 cites W3093351201 @default.
- W3212357338 cites W3100045265 @default.
- W3212357338 cites W3106295246 @default.
- W3212357338 cites W3157745967 @default.
- W3212357338 doi "https://doi.org/10.1117/1.jmi.8.6.065501" @default.
- W3212357338 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8594450" @default.
- W3212357338 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34796251" @default.
- W3212357338 hasPublicationYear "2021" @default.
- W3212357338 type Work @default.
- W3212357338 sameAs 3212357338 @default.
- W3212357338 citedByCount "8" @default.
- W3212357338 countsByYear W32123573382022 @default.
- W3212357338 countsByYear W32123573382023 @default.
- W3212357338 crossrefType "journal-article" @default.
- W3212357338 hasAuthorship W3212357338A5000482255 @default.
- W3212357338 hasAuthorship W3212357338A5017521861 @default.
- W3212357338 hasAuthorship W3212357338A5045249494 @default.
- W3212357338 hasAuthorship W3212357338A5046506193 @default.
- W3212357338 hasAuthorship W3212357338A5068094970 @default.
- W3212357338 hasBestOaLocation W32123573381 @default.
- W3212357338 hasConcept C108583219 @default.
- W3212357338 hasConcept C115961682 @default.
- W3212357338 hasConcept C119857082 @default.
- W3212357338 hasConcept C12267149 @default.
- W3212357338 hasConcept C153180895 @default.
- W3212357338 hasConcept C154945302 @default.
- W3212357338 hasConcept C162324750 @default.
- W3212357338 hasConcept C187736073 @default.
- W3212357338 hasConcept C199360897 @default.
- W3212357338 hasConcept C2779843651 @default.
- W3212357338 hasConcept C2780451532 @default.
- W3212357338 hasConcept C33923547 @default.
- W3212357338 hasConcept C41008148 @default.
- W3212357338 hasConcept C48372109 @default.
- W3212357338 hasConcept C50644808 @default.
- W3212357338 hasConcept C55020928 @default.
- W3212357338 hasConcept C66905080 @default.
- W3212357338 hasConcept C71924100 @default.
- W3212357338 hasConcept C81363708 @default.
- W3212357338 hasConcept C94375191 @default.
- W3212357338 hasConceptScore W3212357338C108583219 @default.
- W3212357338 hasConceptScore W3212357338C115961682 @default.
- W3212357338 hasConceptScore W3212357338C119857082 @default.
- W3212357338 hasConceptScore W3212357338C12267149 @default.
- W3212357338 hasConceptScore W3212357338C153180895 @default.
- W3212357338 hasConceptScore W3212357338C154945302 @default.
- W3212357338 hasConceptScore W3212357338C162324750 @default.
- W3212357338 hasConceptScore W3212357338C187736073 @default.
- W3212357338 hasConceptScore W3212357338C199360897 @default.
- W3212357338 hasConceptScore W3212357338C2779843651 @default.
- W3212357338 hasConceptScore W3212357338C2780451532 @default.
- W3212357338 hasConceptScore W3212357338C33923547 @default.
- W3212357338 hasConceptScore W3212357338C41008148 @default.
- W3212357338 hasConceptScore W3212357338C48372109 @default.
- W3212357338 hasConceptScore W3212357338C50644808 @default.
- W3212357338 hasConceptScore W3212357338C55020928 @default.
- W3212357338 hasConceptScore W3212357338C66905080 @default.
- W3212357338 hasConceptScore W3212357338C71924100 @default.
- W3212357338 hasConceptScore W3212357338C81363708 @default.
- W3212357338 hasConceptScore W3212357338C94375191 @default.
- W3212357338 hasFunder F4320332161 @default.
- W3212357338 hasIssue "06" @default.
- W3212357338 hasLocation W32123573381 @default.
- W3212357338 hasLocation W32123573382 @default.
- W3212357338 hasLocation W32123573383 @default.
- W3212357338 hasLocation W32123573384 @default.
- W3212357338 hasOpenAccess W3212357338 @default.
- W3212357338 hasPrimaryLocation W32123573381 @default.
- W3212357338 hasRelatedWork W2731899572 @default.