Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200358672> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4200358672 abstract "Ultrasound (US) imaging is a widely used clinical technique that requires extensive training to use correctly. Good quality US images are essential for effective interpretation of the results, however numerous sources of error can impair quality. Currently, image quality assessment is performed by an experienced sonographer through visual inspection, however this is usually unachievable by inexperienced users. An autoencoder (AE) is a machine learning technique that has been shown to be effective at anomaly detection and could be used for fast and effective image quality assessment. In this study, we explored the use of an AE to distinguish between good and poor-quality US images (caused by artifacts and noise) by using the reconstruction error to train and test a random forest classifier (RFC) for classification. Good and poor-quality ultrasound images were obtained from forty-nine healthy subjects and were used to train an AE using two different loss functions, with one based on the structural similarity index measure (SSIM) and the other on the mean squared error (MSE). The resulting reconstruction errors of each image were then used to classify the images into two groups based on quality by training and testing an RFC. Using the SSIM based AE, the classifier showed an average accuracy of 71%±4.0% when classifying images based on user errors and an accuracy of 91%±1.0% when sorting images based on noise. The respective accuracies obtained from the AE using the MSE function were 76%±2.0% and 83%±2.0%. The results of this study demonstrate that an AE has the potential to differentiate good quality US images from those with poor quality, which could be used to help less experienced researchers and clinicians obtain a more objective measure of image quality when using US." @default.
- W4200358672 created "2021-12-31" @default.
- W4200358672 creator A5004992178 @default.
- W4200358672 creator A5014307753 @default.
- W4200358672 creator A5029768558 @default.
- W4200358672 creator A5030430929 @default.
- W4200358672 creator A5036437077 @default.
- W4200358672 creator A5075914245 @default.
- W4200358672 date "2021-11-01" @default.
- W4200358672 modified "2023-10-05" @default.
- W4200358672 title "Ultrasound Image Quality Evaluation using a Structural Similarity Based Autoencoder" @default.
- W4200358672 cites W2115505425 @default.
- W4200358672 cites W2133059825 @default.
- W4200358672 cites W2133665775 @default.
- W4200358672 cites W2150734399 @default.
- W4200358672 cites W2162494717 @default.
- W4200358672 cites W2322384450 @default.
- W4200358672 cites W2465492885 @default.
- W4200358672 cites W2592929672 @default.
- W4200358672 cites W2778693718 @default.
- W4200358672 cites W2789895747 @default.
- W4200358672 cites W2792252898 @default.
- W4200358672 cites W2809705434 @default.
- W4200358672 cites W2936136722 @default.
- W4200358672 cites W2948982773 @default.
- W4200358672 cites W2949423562 @default.
- W4200358672 doi "https://doi.org/10.1109/embc46164.2021.9630261" @default.
- W4200358672 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34892108" @default.
- W4200358672 hasPublicationYear "2021" @default.
- W4200358672 type Work @default.
- W4200358672 citedByCount "2" @default.
- W4200358672 countsByYear W42003586722023 @default.
- W4200358672 crossrefType "proceedings-article" @default.
- W4200358672 hasAuthorship W4200358672A5004992178 @default.
- W4200358672 hasAuthorship W4200358672A5014307753 @default.
- W4200358672 hasAuthorship W4200358672A5029768558 @default.
- W4200358672 hasAuthorship W4200358672A5030430929 @default.
- W4200358672 hasAuthorship W4200358672A5036437077 @default.
- W4200358672 hasAuthorship W4200358672A5075914245 @default.
- W4200358672 hasConcept C101738243 @default.
- W4200358672 hasConcept C105795698 @default.
- W4200358672 hasConcept C108583219 @default.
- W4200358672 hasConcept C115961682 @default.
- W4200358672 hasConcept C126838900 @default.
- W4200358672 hasConcept C139945424 @default.
- W4200358672 hasConcept C143753070 @default.
- W4200358672 hasConcept C153180895 @default.
- W4200358672 hasConcept C154945302 @default.
- W4200358672 hasConcept C169258074 @default.
- W4200358672 hasConcept C2778941581 @default.
- W4200358672 hasConcept C31972630 @default.
- W4200358672 hasConcept C33923547 @default.
- W4200358672 hasConcept C41008148 @default.
- W4200358672 hasConcept C55020928 @default.
- W4200358672 hasConcept C71924100 @default.
- W4200358672 hasConcept C95623464 @default.
- W4200358672 hasConceptScore W4200358672C101738243 @default.
- W4200358672 hasConceptScore W4200358672C105795698 @default.
- W4200358672 hasConceptScore W4200358672C108583219 @default.
- W4200358672 hasConceptScore W4200358672C115961682 @default.
- W4200358672 hasConceptScore W4200358672C126838900 @default.
- W4200358672 hasConceptScore W4200358672C139945424 @default.
- W4200358672 hasConceptScore W4200358672C143753070 @default.
- W4200358672 hasConceptScore W4200358672C153180895 @default.
- W4200358672 hasConceptScore W4200358672C154945302 @default.
- W4200358672 hasConceptScore W4200358672C169258074 @default.
- W4200358672 hasConceptScore W4200358672C2778941581 @default.
- W4200358672 hasConceptScore W4200358672C31972630 @default.
- W4200358672 hasConceptScore W4200358672C33923547 @default.
- W4200358672 hasConceptScore W4200358672C41008148 @default.
- W4200358672 hasConceptScore W4200358672C55020928 @default.
- W4200358672 hasConceptScore W4200358672C71924100 @default.
- W4200358672 hasConceptScore W4200358672C95623464 @default.
- W4200358672 hasLocation W42003586721 @default.
- W4200358672 hasLocation W42003586722 @default.
- W4200358672 hasOpenAccess W4200358672 @default.
- W4200358672 hasPrimaryLocation W42003586721 @default.
- W4200358672 hasRelatedWork W2292254049 @default.
- W4200358672 hasRelatedWork W2669956259 @default.
- W4200358672 hasRelatedWork W2897995864 @default.
- W4200358672 hasRelatedWork W2939353110 @default.
- W4200358672 hasRelatedWork W2998168123 @default.
- W4200358672 hasRelatedWork W3165097609 @default.
- W4200358672 hasRelatedWork W3165463024 @default.
- W4200358672 hasRelatedWork W4287178339 @default.
- W4200358672 hasRelatedWork W4287995534 @default.
- W4200358672 hasRelatedWork W4327774331 @default.
- W4200358672 isParatext "false" @default.
- W4200358672 isRetracted "false" @default.
- W4200358672 workType "article" @default.